Compare commits
62
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 jarvis-at-skic
|
b33b59659c | ||
|
jarvis-at-skic
|
86b1c769a3 | ||
|
jarvis-at-skic
|
499049eff3 | ||
|
jarvis-at-skic
|
46bb8b2b48 | ||
|
jarvis-at-skic
|
c88f4dbc25 | ||
|
jarvis-at-skic
|
eea14bf00f | ||
|
jarvis-at-skic
|
4e94ad24fd | ||
|
jarvis-at-skic
|
7472b835e8 | ||
|
jarvis-at-skic
|
8a9363ccb2 | ||
|
jarvis-at-skic
|
3696788082 | ||
|
jarvis-at-skic
|
f23bf1c5f4 | ||
|
jarvis-at-skic
|
d8feeba025 | ||
|
jarvis-at-skic
|
e96e780beb | ||
|
jarvis-at-skic
|
432370473d | ||
|
jarvis-at-skic
|
6b38b128d4 | ||
|
jarvis-at-skic
|
f059f4c324 | ||
|
jarvis-at-skic
|
9a7766b323 | ||
|
jarvis-at-skic
|
a283d6a34a | ||
|
jarvis-at-skic
|
9bacb7043a | ||
|
jarvis-at-skic
|
5c5809d349 | ||
|
jarvis-at-skic
|
fcaa84f3bf | ||
|
jarvis-at-skic
|
1a2d16bc91 | ||
|
jarvis-at-skic
|
88a4375776 | ||
|
jarvis-at-skic
|
f7a68d7e37 | ||
|
jarvis-at-skic
|
c934ddb5e0 | ||
|
jarvis-at-skic
|
e22d3a5c13 | ||
|
jarvis-at-skic
|
386133c8b6 | ||
|
jarvis-at-skic
|
abe00994a1 | ||
|
jarvis-at-skic
|
c4b4c38e62 | ||
|
jarvis-at-skic
|
85852f0744 | ||
|
jarvis-at-skic
|
b9c2047c61 | ||
|
jarvis-at-skic
|
a35cade49c | ||
|
jarvis-at-skic
|
ef169cec58 | ||
|
jarvis-at-skic
|
e0afa78eb2 | ||
|
jarvis-at-skic
|
e087adab1e | ||
|
jarvis-at-skic
|
325363d89c | ||
|
jarvis-at-skic
|
ad7312b65a | ||
|
jarvis-at-skic
|
3238e1d809 | ||
|
jarvis-at-skic
|
fe4c3509d1 | ||
|
jarvis-at-skic
|
8a7dbea852 | ||
|
jarvis-at-skic
|
e10b03dff4 | ||
|
jarvis-at-skic
|
733d6f2ece | ||
|
jarvis-at-skic
|
2a4e058684 | ||
|
jarvis-at-skic
|
63f38597a6 | ||
|
jarvis-at-skic
|
0248baa97b | ||
|
jarvis-at-skic
|
7e3696d2d7 | ||
|
jarvis-at-skic
|
15c5dcb31d | ||
|
jarvis-at-skic
|
64b2d6dae8 | ||
|
jarvis-at-skic
|
20e6f4899c | ||
|
jarvis-at-skic
|
2f68e60cec | ||
|
jarvis-at-skic
|
e149131307 | ||
|
jarvis-at-skic
|
2d63313180 | ||
|
jarvis-at-skic
|
1de7d16d09 | ||
|
jarvis-at-skic
|
b679e6b2b5 | ||
|
jarvis-at-skic
|
8dd54f0ab6 | ||
|
jarvis-at-skic
|
8bfcb3f81d | ||
|
jarvis-at-skic
|
baf79e125b | ||
|
jarvis-at-skic
|
9651417ba7 | ||
|
jarvis-at-skic
|
4cc2bb4dfd | ||
|
jarvis-at-skic
|
afb6a97e97 | ||
|
jarvis-at-skic
|
1057433c2a | ||
|
jarvis-at-skic
|
504d9f8845 |
No files matched your search
@@ -6,3 +6,4 @@ build/
|
||||
.env.*
|
||||
!.env.example
|
||||
static/diagrams/
|
||||
static/presentations/
|
||||
@@ -2,138 +2,244 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Learn before expanding",
|
||||
"title": "TO-BE: Adoption",
|
||||
"output": "static/diagrams/strategy-adoption-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
880,
|
||||
2040
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "choose",
|
||||
"type": "backend",
|
||||
"label": "Choose workflow",
|
||||
"sublabel": "Department outcome",
|
||||
"id": "delivery",
|
||||
"type": "external",
|
||||
"label": "Delivery first",
|
||||
"tag": "Start with a real workflow",
|
||||
"sublabel": "Workflow baseline + canary",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
120
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "coach",
|
||||
"id": "human",
|
||||
"type": "backend",
|
||||
"label": "Coach people",
|
||||
"sublabel": "Verify + recover",
|
||||
"label": "Human",
|
||||
"tag": "Direct + guide + review",
|
||||
"sublabel": "Define outcome; inspect artifacts",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
60,
|
||||
1280
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "canary",
|
||||
"type": "backend",
|
||||
"label": "Run bounded canary",
|
||||
"sublabel": "Qualified skill + client",
|
||||
"id": "agent",
|
||||
"type": "external",
|
||||
"label": "AI Agent",
|
||||
"tag": "Qualified client + authorized pilot",
|
||||
"sublabel": "Produce work within the boundary",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
60,
|
||||
910
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "accept",
|
||||
"type": "backend",
|
||||
"label": "Accept real work",
|
||||
"sublabel": "Independent review",
|
||||
"id": "learn",
|
||||
"type": "external",
|
||||
"label": "Learn from real work",
|
||||
"tag": "Ongoing, reviewed improvement",
|
||||
"sublabel": "Feedback + selected measures\nRetain a manual path\nNo quotas or rankings",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
60,
|
||||
490
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "feedback",
|
||||
"type": "backend",
|
||||
"label": "Review feedback",
|
||||
"sublabel": "Usefulness + non-use",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
740,
|
||||
270
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "expand",
|
||||
"type": "backend",
|
||||
"label": "Expand or revise",
|
||||
"sublabel": "Keep a manual path",
|
||||
"label": "Decide from evidence",
|
||||
"tag": "Owner; new scope is separate",
|
||||
"sublabel": "Retain / improve / hold / stop\nExpansion is a new proposal",
|
||||
"pos": [
|
||||
20,
|
||||
620
|
||||
60,
|
||||
1650
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
240
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "choose",
|
||||
"to": "coach",
|
||||
"label": "Prepare"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "coach",
|
||||
"to": "canary",
|
||||
"label": "support pilot"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "canary",
|
||||
"to": "accept",
|
||||
"label": "Verify"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "accept",
|
||||
"to": "feedback",
|
||||
"label": "learn"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "feedback",
|
||||
"to": "expand",
|
||||
"label": "decide"
|
||||
},
|
||||
{
|
||||
"id": "feedback-loop",
|
||||
"from": "expand",
|
||||
"to": "coach",
|
||||
"label": "Review revision",
|
||||
"variant": "dashed",
|
||||
"id": "delivery-agent",
|
||||
"from": "delivery",
|
||||
"to": "agent",
|
||||
"label": "Practice",
|
||||
"fromSide": "right",
|
||||
"toSide": "right"
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
850,
|
||||
230.0
|
||||
],
|
||||
[
|
||||
850,
|
||||
1020.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
780,
|
||||
870
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "human-agent",
|
||||
"from": "human",
|
||||
"to": "agent",
|
||||
"label": "Direction",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
824,
|
||||
1390.0
|
||||
],
|
||||
[
|
||||
824,
|
||||
1020.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
770,
|
||||
1240
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "agent-human",
|
||||
"from": "agent",
|
||||
"to": "human",
|
||||
"label": "Work to inspect",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1185
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "agent-learn",
|
||||
"from": "agent",
|
||||
"to": "learn",
|
||||
"label": "Observe",
|
||||
"fromSide": "top",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
815
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "learn-delivery",
|
||||
"from": "learn",
|
||||
"to": "delivery",
|
||||
"label": "Improve",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
42,
|
||||
625.0
|
||||
],
|
||||
[
|
||||
42,
|
||||
230.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
80
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "human-expand",
|
||||
"from": "human",
|
||||
"to": "expand",
|
||||
"label": "Accepted work",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1555
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "learn-expand",
|
||||
"from": "learn",
|
||||
"to": "expand",
|
||||
"label": "Feedback",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
20,
|
||||
625.0
|
||||
],
|
||||
[
|
||||
20,
|
||||
1770.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1610
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -2,138 +2,242 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Learn before expanding",
|
||||
"title": "TO-BE: Adoption",
|
||||
"output": "static/diagrams/strategy-adoption/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
2040,
|
||||
1160
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "choose",
|
||||
"type": "backend",
|
||||
"label": "Choose workflow",
|
||||
"sublabel": "Department outcome",
|
||||
"id": "delivery",
|
||||
"type": "external",
|
||||
"label": "Delivery first",
|
||||
"tag": "Start with a real workflow",
|
||||
"sublabel": "Workflow baseline + canary",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
350
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
470,
|
||||
210
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "coach",
|
||||
"id": "human",
|
||||
"type": "backend",
|
||||
"label": "Coach people",
|
||||
"sublabel": "Verify + recover",
|
||||
"label": "Human",
|
||||
"tag": "Direct + guide + review",
|
||||
"sublabel": "Define outcome; inspect artifacts",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
700,
|
||||
90
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
570,
|
||||
190
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "canary",
|
||||
"type": "backend",
|
||||
"label": "Run bounded canary",
|
||||
"sublabel": "Qualified skill + client",
|
||||
"id": "agent",
|
||||
"type": "external",
|
||||
"label": "AI Agent",
|
||||
"tag": "Qualified client + authorized pilot",
|
||||
"sublabel": "Produce work within the boundary",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
700,
|
||||
440
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
570,
|
||||
190
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "accept",
|
||||
"type": "backend",
|
||||
"label": "Accept real work",
|
||||
"sublabel": "Independent review",
|
||||
"id": "learn",
|
||||
"type": "external",
|
||||
"label": "Learn from real work",
|
||||
"tag": "Ongoing, reviewed improvement",
|
||||
"sublabel": "Feedback + selected measures\nRetain a manual path\nNo quotas or rankings",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
700,
|
||||
800
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "feedback",
|
||||
"type": "backend",
|
||||
"label": "Review feedback",
|
||||
"sublabel": "Usefulness + non-use",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
570,
|
||||
270
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "expand",
|
||||
"type": "backend",
|
||||
"label": "Expand or revise",
|
||||
"sublabel": "Keep a manual path",
|
||||
"label": "Decide from evidence",
|
||||
"tag": "Owner; new scope is separate",
|
||||
"sublabel": "Retain / improve / hold / stop\nExpansion is a new proposal",
|
||||
"pos": [
|
||||
260,
|
||||
280
|
||||
1460,
|
||||
360
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
520,
|
||||
240
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "choose",
|
||||
"to": "coach",
|
||||
"label": "Prepare"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "coach",
|
||||
"to": "canary",
|
||||
"label": "support pilot"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "canary",
|
||||
"to": "accept",
|
||||
"label": "Verify"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "accept",
|
||||
"to": "feedback",
|
||||
"label": "learn"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "feedback",
|
||||
"to": "expand",
|
||||
"label": "decide"
|
||||
},
|
||||
{
|
||||
"id": "feedback-loop",
|
||||
"from": "expand",
|
||||
"to": "coach",
|
||||
"label": "Review revision",
|
||||
"variant": "dashed",
|
||||
"id": "delivery-agent",
|
||||
"from": "delivery",
|
||||
"to": "agent",
|
||||
"label": "Practice",
|
||||
"fromSide": "right",
|
||||
"toSide": "right"
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
585,
|
||||
455
|
||||
],
|
||||
[
|
||||
585,
|
||||
535
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
570,
|
||||
600
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "human-agent",
|
||||
"from": "human",
|
||||
"to": "agent",
|
||||
"label": "Direction",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1100,
|
||||
360
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "agent-human",
|
||||
"from": "agent",
|
||||
"to": "human",
|
||||
"label": "Work to inspect",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
630,
|
||||
535
|
||||
],
|
||||
[
|
||||
630,
|
||||
185
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
470,
|
||||
240
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "agent-learn",
|
||||
"from": "agent",
|
||||
"to": "learn",
|
||||
"label": "Observe",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1100,
|
||||
720
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "learn-delivery",
|
||||
"from": "learn",
|
||||
"to": "delivery",
|
||||
"label": "Improve",
|
||||
"fromSide": "left",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
295,
|
||||
935
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
450,
|
||||
900
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "human-expand",
|
||||
"from": "human",
|
||||
"to": "expand",
|
||||
"label": "Accepted work",
|
||||
"fromSide": "right",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1720,
|
||||
185
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1550,
|
||||
140
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "learn-expand",
|
||||
"from": "learn",
|
||||
"to": "expand",
|
||||
"label": "Feedback",
|
||||
"fromSide": "right",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1720,
|
||||
935
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1480,
|
||||
895
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,144 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "Workflow baseline",
|
||||
"output": "static/diagrams/strategy-baseline-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
880,
|
||||
2050
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "workflow",
|
||||
"type": "external",
|
||||
"label": "Current workflow",
|
||||
"tag": "01 / Understand",
|
||||
"sublabel": "Task, scope, people\nTools + handoffs\nCurrent practice",
|
||||
"pos": [
|
||||
90,
|
||||
50
|
||||
],
|
||||
"size": [
|
||||
700,
|
||||
350
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "selection",
|
||||
"type": "frontend",
|
||||
"label": "Relevant selection",
|
||||
"tag": "02 / Choose",
|
||||
"sublabel": "Registry candidates\nReasons for inclusion\nDefer what does not fit",
|
||||
"pos": [
|
||||
90,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
700,
|
||||
350
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "evidence",
|
||||
"type": "frontend",
|
||||
"label": "Feasible evidence",
|
||||
"tag": "03 / Agree",
|
||||
"sublabel": "Sources + period\nPrivacy, access, owner\nTest joins + coverage",
|
||||
"pos": [
|
||||
90,
|
||||
850
|
||||
],
|
||||
"size": [
|
||||
700,
|
||||
350
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "position",
|
||||
"type": "backend",
|
||||
"label": "Starting position",
|
||||
"tag": "04 / Record",
|
||||
"sublabel": "Actual values + limits\nOr unavailable gaps\nNo invented baseline",
|
||||
"pos": [
|
||||
90,
|
||||
1250
|
||||
],
|
||||
"size": [
|
||||
700,
|
||||
350
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "comparison",
|
||||
"type": "backend",
|
||||
"label": "Later comparison",
|
||||
"tag": "05 / Evaluate",
|
||||
"sublabel": "Comparable rules\nContext + uncertainty\nNot causal ROI",
|
||||
"pos": [
|
||||
90,
|
||||
1650
|
||||
],
|
||||
"size": [
|
||||
700,
|
||||
350
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "workflow-selection",
|
||||
"from": "workflow",
|
||||
"to": "selection",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default"
|
||||
},
|
||||
{
|
||||
"id": "selection-evidence",
|
||||
"from": "selection",
|
||||
"to": "evidence",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default"
|
||||
},
|
||||
{
|
||||
"id": "evidence-position",
|
||||
"from": "evidence",
|
||||
"to": "position",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default"
|
||||
},
|
||||
{
|
||||
"id": "position-comparison",
|
||||
"from": "position",
|
||||
"to": "comparison",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,184 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "Workflow baseline",
|
||||
"output": "static/diagrams/strategy-baseline/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
2400,
|
||||
1120
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "workflow",
|
||||
"type": "external",
|
||||
"label": "Current workflow",
|
||||
"tag": "01 / Understand",
|
||||
"sublabel": "Task, scope, people\nTools + handoffs\nCurrent practice",
|
||||
"pos": [
|
||||
40,
|
||||
55
|
||||
],
|
||||
"size": [
|
||||
440,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "selection",
|
||||
"type": "frontend",
|
||||
"label": "Relevant selection",
|
||||
"tag": "02 / Choose",
|
||||
"sublabel": "Registry candidates\nReasons for inclusion\nDefer what does not fit",
|
||||
"pos": [
|
||||
510,
|
||||
235
|
||||
],
|
||||
"size": [
|
||||
440,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "evidence",
|
||||
"type": "frontend",
|
||||
"label": "Feasible evidence",
|
||||
"tag": "03 / Agree",
|
||||
"sublabel": "Sources + period\nPrivacy, access, owner\nTest joins + coverage",
|
||||
"pos": [
|
||||
980,
|
||||
415
|
||||
],
|
||||
"size": [
|
||||
440,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "position",
|
||||
"type": "backend",
|
||||
"label": "Starting position",
|
||||
"tag": "04 / Record",
|
||||
"sublabel": "Actual values + limits\nOr unavailable gaps\nNo invented baseline",
|
||||
"pos": [
|
||||
1450,
|
||||
595
|
||||
],
|
||||
"size": [
|
||||
440,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "comparison",
|
||||
"type": "backend",
|
||||
"label": "Later comparison",
|
||||
"tag": "05 / Evaluate",
|
||||
"sublabel": "Comparable rules\nContext + uncertainty\nNot causal ROI",
|
||||
"pos": [
|
||||
1920,
|
||||
775
|
||||
],
|
||||
"size": [
|
||||
440,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "workflow-selection",
|
||||
"from": "workflow",
|
||||
"to": "selection",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
495.0,
|
||||
200.0
|
||||
],
|
||||
[
|
||||
495.0,
|
||||
380.0
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "selection-evidence",
|
||||
"from": "selection",
|
||||
"to": "evidence",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
965.0,
|
||||
380.0
|
||||
],
|
||||
[
|
||||
965.0,
|
||||
560.0
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "evidence-position",
|
||||
"from": "evidence",
|
||||
"to": "position",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1435.0,
|
||||
560.0
|
||||
],
|
||||
[
|
||||
1435.0,
|
||||
740.0
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "position-comparison",
|
||||
"from": "position",
|
||||
"to": "comparison",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1905.0,
|
||||
740.0
|
||||
],
|
||||
[
|
||||
1905.0,
|
||||
920.0
|
||||
]
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -2,129 +2,246 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Independent approval",
|
||||
"title": "TO-BE: Governance",
|
||||
"output": "static/diagrams/strategy-governance-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
880,
|
||||
2710
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "owner",
|
||||
"type": "security",
|
||||
"label": "Owner proposes",
|
||||
"sublabel": "Existing accountable team",
|
||||
"type": "external",
|
||||
"label": "01 Propose",
|
||||
"tag": "Owning team",
|
||||
"sublabel": "Scope + testable outcome",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
120
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "review",
|
||||
"type": "security",
|
||||
"label": "Independent review",
|
||||
"sublabel": "Quality + risk evidence",
|
||||
"type": "external",
|
||||
"label": "02 Review independently",
|
||||
"tag": "Quality + Security",
|
||||
"sublabel": "Author is not sole approver",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
60,
|
||||
490
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "canary",
|
||||
"type": "security",
|
||||
"label": "Bounded canary",
|
||||
"sublabel": "Qualified client path",
|
||||
"type": "external",
|
||||
"label": "03 Authorize pilot",
|
||||
"tag": "Owning team approver",
|
||||
"sublabel": "Qualified; pin, load, pilot",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
60,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "approve",
|
||||
"type": "security",
|
||||
"label": "Approve revision",
|
||||
"sublabel": "Exact digest + scope",
|
||||
"type": "backend",
|
||||
"label": "04 Decide exact scope",
|
||||
"tag": "Accountable approvers",
|
||||
"sublabel": "Compare pilot: approve / hold",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
60,
|
||||
1230
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "publish",
|
||||
"type": "security",
|
||||
"label": "Publish bundle",
|
||||
"sublabel": "Data & AI catalog",
|
||||
"type": "backend",
|
||||
"label": "05 Publish the bundle",
|
||||
"tag": "Data & AI catalog",
|
||||
"sublabel": "Pin skill, adapter + dependencies",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
60,
|
||||
1600
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "distribute",
|
||||
"type": "security",
|
||||
"label": "Verify effective state",
|
||||
"sublabel": "Platform & IT",
|
||||
"type": "backend",
|
||||
"label": "06 Verify loaded state",
|
||||
"tag": "Platform & IT",
|
||||
"sublabel": "Read revision; verify reload",
|
||||
"pos": [
|
||||
20,
|
||||
620
|
||||
60,
|
||||
1970
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "withdraw",
|
||||
"type": "security",
|
||||
"label": "Withdraw / roll back",
|
||||
"tag": "Unsafe revision",
|
||||
"sublabel": "Revoke; restore or remove candidate",
|
||||
"pos": [
|
||||
60,
|
||||
2340
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"id": "owner-review",
|
||||
"from": "owner",
|
||||
"to": "review",
|
||||
"label": "submit"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
395
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"id": "review-canary",
|
||||
"from": "review",
|
||||
"to": "canary",
|
||||
"label": "qualify"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
765
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"id": "canary-approve",
|
||||
"from": "canary",
|
||||
"to": "approve",
|
||||
"label": "Accept"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1135
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"id": "approve-publish",
|
||||
"from": "approve",
|
||||
"to": "publish",
|
||||
"label": "record approval"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1505
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"id": "publish-distribute",
|
||||
"from": "publish",
|
||||
"to": "distribute",
|
||||
"label": "Deliver"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1875
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "approve-owner",
|
||||
"from": "approve",
|
||||
"to": "owner",
|
||||
"label": "Rework",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
20,
|
||||
1340.0
|
||||
],
|
||||
[
|
||||
20,
|
||||
230.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
80
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "distribute-withdraw",
|
||||
"from": "distribute",
|
||||
"to": "withdraw",
|
||||
"label": "Unsafe",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
610,
|
||||
2245
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -2,129 +2,276 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Independent approval",
|
||||
"title": "TO-BE: Governance",
|
||||
"output": "static/diagrams/strategy-governance/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
1760,
|
||||
1420
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "owner",
|
||||
"type": "security",
|
||||
"label": "Owner proposes",
|
||||
"sublabel": "Existing accountable team",
|
||||
"type": "external",
|
||||
"label": "01 Propose",
|
||||
"tag": "Owning team",
|
||||
"sublabel": "Scope + testable outcome",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
80,
|
||||
60
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "review",
|
||||
"type": "security",
|
||||
"label": "Independent review",
|
||||
"sublabel": "Quality + risk evidence",
|
||||
"type": "external",
|
||||
"label": "02 Review independently",
|
||||
"tag": "Quality + Security",
|
||||
"sublabel": "Author is not sole approver",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
300,
|
||||
280
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "canary",
|
||||
"type": "security",
|
||||
"label": "Bounded canary",
|
||||
"sublabel": "Qualified client path",
|
||||
"type": "external",
|
||||
"label": "03 Authorize pilot",
|
||||
"tag": "Owning team approver",
|
||||
"sublabel": "Qualified; pin, load, pilot",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
520,
|
||||
500
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "approve",
|
||||
"type": "security",
|
||||
"label": "Approve revision",
|
||||
"sublabel": "Exact digest + scope",
|
||||
"type": "backend",
|
||||
"label": "04 Decide exact scope",
|
||||
"tag": "Accountable approvers",
|
||||
"sublabel": "Compare pilot: approve / hold",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
740,
|
||||
720
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "publish",
|
||||
"type": "security",
|
||||
"label": "Publish bundle",
|
||||
"sublabel": "Data & AI catalog",
|
||||
"type": "backend",
|
||||
"label": "05 Publish the bundle",
|
||||
"tag": "Data & AI catalog",
|
||||
"sublabel": "Pin skill, adapter + dependencies",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
960,
|
||||
940
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "distribute",
|
||||
"type": "security",
|
||||
"label": "Verify effective state",
|
||||
"sublabel": "Platform & IT",
|
||||
"type": "backend",
|
||||
"label": "06 Verify loaded state",
|
||||
"tag": "Platform & IT",
|
||||
"sublabel": "Read revision; verify reload",
|
||||
"pos": [
|
||||
260,
|
||||
280
|
||||
1180,
|
||||
1160
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "withdraw",
|
||||
"type": "security",
|
||||
"label": "Withdraw / roll back",
|
||||
"tag": "Unsafe revision",
|
||||
"sublabel": "Revoke; restore or remove candidate",
|
||||
"pos": [
|
||||
80,
|
||||
1160
|
||||
],
|
||||
"size": [
|
||||
660,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"id": "owner-review",
|
||||
"from": "owner",
|
||||
"to": "review",
|
||||
"label": "submit"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
330,
|
||||
255
|
||||
],
|
||||
[
|
||||
550,
|
||||
255
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"id": "review-canary",
|
||||
"from": "review",
|
||||
"to": "canary",
|
||||
"label": "qualify"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
550,
|
||||
475
|
||||
],
|
||||
[
|
||||
770,
|
||||
475
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"id": "canary-approve",
|
||||
"from": "canary",
|
||||
"to": "approve",
|
||||
"label": "Accept"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
770,
|
||||
695
|
||||
],
|
||||
[
|
||||
990,
|
||||
695
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"id": "approve-publish",
|
||||
"from": "approve",
|
||||
"to": "publish",
|
||||
"label": "record approval"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
990,
|
||||
915
|
||||
],
|
||||
[
|
||||
1210,
|
||||
915
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"id": "publish-distribute",
|
||||
"from": "publish",
|
||||
"to": "distribute",
|
||||
"label": "Deliver"
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1210,
|
||||
1135
|
||||
],
|
||||
[
|
||||
1430,
|
||||
1135
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "approve-owner",
|
||||
"from": "approve",
|
||||
"to": "owner",
|
||||
"label": "Rework",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
40,
|
||||
805
|
||||
],
|
||||
[
|
||||
40,
|
||||
145
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
180,
|
||||
680
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "distribute-withdraw",
|
||||
"from": "distribute",
|
||||
"to": "withdraw",
|
||||
"label": "Unsafe",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
950,
|
||||
1220
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -2,140 +2,157 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Maintain trust over time",
|
||||
"title": "TO-BE: Maintenance",
|
||||
"output": "static/diagrams/strategy-maintenance-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
880,
|
||||
3080
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "monitor",
|
||||
"type": "backend",
|
||||
"label": "Monitor skills",
|
||||
"sublabel": "Usefulness + safety",
|
||||
"id": "observe",
|
||||
"type": "external",
|
||||
"label": "Observe use",
|
||||
"tag": "Owner + Data & AI",
|
||||
"sublabel": "Selected evidence + drift",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
120
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "triage",
|
||||
"type": "backend",
|
||||
"label": "Triage changes",
|
||||
"sublabel": "Owner + risk review",
|
||||
"type": "external",
|
||||
"label": "Triage the signal",
|
||||
"tag": "Owning team",
|
||||
"sublabel": "Useful? Safe? Still needed?",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
60,
|
||||
490
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "correct",
|
||||
"type": "backend",
|
||||
"label": "Correct and test",
|
||||
"sublabel": "Independent regression",
|
||||
"id": "change",
|
||||
"type": "external",
|
||||
"label": "Change the skill",
|
||||
"tag": "Reviewed correction",
|
||||
"sublabel": "New immutable revision",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
60,
|
||||
1230
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decision",
|
||||
"type": "backend",
|
||||
"label": "Approve or hold",
|
||||
"sublabel": "Exact revised bundle",
|
||||
"id": "validate",
|
||||
"type": "external",
|
||||
"label": "Revalidate",
|
||||
"tag": "Quality Engineering reviewer",
|
||||
"sublabel": "Fitness + regression + client checks",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
60,
|
||||
1600
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "promote",
|
||||
"id": "release",
|
||||
"type": "backend",
|
||||
"label": "Promote safely",
|
||||
"sublabel": "Verify state + monitor",
|
||||
"label": "Approve + version",
|
||||
"tag": "Accountable human authority",
|
||||
"sublabel": "Verify distribution and recovery",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
60,
|
||||
1970
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "observe",
|
||||
"id": "safe",
|
||||
"type": "backend",
|
||||
"label": "Quarantine / rollback",
|
||||
"sublabel": "Revoke unsafe revision",
|
||||
"label": "Continue safe use",
|
||||
"tag": "Substantive review passes",
|
||||
"sublabel": "Keep owner + next review date",
|
||||
"pos": [
|
||||
20,
|
||||
620
|
||||
60,
|
||||
2710
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "retire",
|
||||
"type": "external",
|
||||
"label": "Retire deliberately",
|
||||
"tag": "No longer useful",
|
||||
"sublabel": "Reconcile consumers; no new use",
|
||||
"pos": [
|
||||
60,
|
||||
2340
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "contain",
|
||||
"type": "security",
|
||||
"label": "Contain unsafe use",
|
||||
"tag": "Security + Platform & IT",
|
||||
"sublabel": "Revoke + quarantine + roll back\nNo automatic reinstatement",
|
||||
"pos": [
|
||||
60,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "monitor",
|
||||
"to": "triage",
|
||||
"label": "Detect"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "triage",
|
||||
"to": "correct",
|
||||
"label": "scope correction"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "correct",
|
||||
"to": "decision",
|
||||
"label": "Prove"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "decision",
|
||||
"to": "promote",
|
||||
"label": "authorize"
|
||||
},
|
||||
|
||||
{
|
||||
"id": "unsafe",
|
||||
"from": "triage",
|
||||
"to": "observe",
|
||||
"label": "Unsafe",
|
||||
"variant": "security",
|
||||
"fromSide": "right",
|
||||
"toSide": "right"
|
||||
},
|
||||
{
|
||||
"id": "review-loop",
|
||||
"from": "observe",
|
||||
"to": "correct",
|
||||
"label": "Requalify",
|
||||
"variant": "dashed"
|
||||
}
|
||||
{"id":"observe-triage","from":"observe","to":"triage","label":"","fromSide":"bottom","toSide":"top","route":"straight","width":4,"variant":"default"},
|
||||
{"id":"triage-change","from":"triage","to":"change","label":"Correct","fromSide":"right","toSide":"right","route":"straight","width":4,"variant":"default","via":[[824,600],[824,1340]],"labelAt":[640,1190]},
|
||||
{"id":"change-validate","from":"change","to":"validate","label":"","fromSide":"bottom","toSide":"top","route":"straight","width":4,"variant":"default"},
|
||||
{"id":"validate-release","from":"validate","to":"release","label":"","fromSide":"bottom","toSide":"top","route":"straight","width":4,"variant":"default"},
|
||||
{"id":"release-observe","from":"release","to":"observe","label":"","fromSide":"left","toSide":"left","route":"straight","width":4,"variant":"default","via":[[42,2080],[42,230]]},
|
||||
{"id":"triage-safe","from":"triage","to":"safe","label":"Safe","fromSide":"right","toSide":"right","route":"straight","width":4,"variant":"default","via":[[872,600],[872,2820]],"labelAt":[620,2670]},
|
||||
{"id":"triage-retire","from":"triage","to":"retire","label":"Retire","fromSide":"right","toSide":"right","route":"straight","width":4,"variant":"default","via":[[850,600],[850,2450]],"labelAt":[620,2300]},
|
||||
{"id":"triage-contain","from":"triage","to":"contain","label":"Unsafe","fromSide":"bottom","toSide":"top","route":"straight","width":4,"variant":"security","labelAt":[610,795]},
|
||||
{"id":"contain-change","from":"contain","to":"change","label":"Reviewed fix","fromSide":"bottom","toSide":"top","route":"straight","width":4,"variant":"security","labelAt":[610,1135]},
|
||||
{"id":"safe-observe","from":"safe","to":"observe","label":"Keep watching","fromSide":"left","toSide":"left","route":"straight","width":4,"variant":"default","via":[[20,2820],[20,230]],"labelAt":[620,80]}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -2,140 +2,369 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Maintain trust over time",
|
||||
"title": "TO-BE: Maintenance",
|
||||
"output": "static/diagrams/strategy-maintenance/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
2630,
|
||||
1300
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "monitor",
|
||||
"type": "backend",
|
||||
"label": "Monitor skills",
|
||||
"sublabel": "Usefulness + safety",
|
||||
"id": "observe",
|
||||
"type": "external",
|
||||
"label": "Observe use",
|
||||
"tag": "Owner + Data & AI",
|
||||
"sublabel": "Selected evidence + drift",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
670,
|
||||
60
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
560,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "triage",
|
||||
"type": "backend",
|
||||
"label": "Triage changes",
|
||||
"sublabel": "Owner + risk review",
|
||||
"type": "external",
|
||||
"label": "Triage the signal",
|
||||
"tag": "Owning team",
|
||||
"sublabel": "Useful? Safe? Still needed?",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
1340,
|
||||
330
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
500,
|
||||
190
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "correct",
|
||||
"type": "backend",
|
||||
"label": "Correct and test",
|
||||
"sublabel": "Independent regression",
|
||||
"id": "change",
|
||||
"type": "external",
|
||||
"label": "Change the skill",
|
||||
"tag": "Reviewed correction",
|
||||
"sublabel": "New immutable revision",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
1240,
|
||||
750
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
520,
|
||||
180
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decision",
|
||||
"type": "backend",
|
||||
"label": "Approve or hold",
|
||||
"sublabel": "Exact revised bundle",
|
||||
"id": "validate",
|
||||
"type": "external",
|
||||
"label": "Revalidate",
|
||||
"tag": "Quality Engineering reviewer",
|
||||
"sublabel": "Fitness + regression + client checks",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
560,
|
||||
970
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
560,
|
||||
180
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "promote",
|
||||
"id": "release",
|
||||
"type": "backend",
|
||||
"label": "Promote safely",
|
||||
"sublabel": "Verify state + monitor",
|
||||
"label": "Approve + version",
|
||||
"tag": "Accountable human authority",
|
||||
"sublabel": "Verify distribution and recovery",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
70,
|
||||
570
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
540,
|
||||
180
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "observe",
|
||||
"id": "safe",
|
||||
"type": "backend",
|
||||
"label": "Quarantine / rollback",
|
||||
"sublabel": "Revoke unsafe revision",
|
||||
"label": "Continue safe use",
|
||||
"tag": "Substantive review passes",
|
||||
"sublabel": "Keep owner + next review date",
|
||||
"pos": [
|
||||
260,
|
||||
280
|
||||
2010,
|
||||
80
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
550,
|
||||
180
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "retire",
|
||||
"type": "external",
|
||||
"label": "Retire deliberately",
|
||||
"tag": "No longer useful",
|
||||
"sublabel": "Reconcile consumers; no new use",
|
||||
"pos": [
|
||||
2010,
|
||||
430
|
||||
],
|
||||
"size": [
|
||||
550,
|
||||
180
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "contain",
|
||||
"type": "security",
|
||||
"label": "Contain unsafe use",
|
||||
"tag": "Security + Platform & IT",
|
||||
"sublabel": "Revoke + quarantine + roll back\nNo automatic reinstatement",
|
||||
"pos": [
|
||||
2010,
|
||||
800
|
||||
],
|
||||
"size": [
|
||||
550,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "monitor",
|
||||
"to": "triage",
|
||||
"label": "Detect"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "triage",
|
||||
"to": "correct",
|
||||
"label": "scope correction"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "correct",
|
||||
"to": "decision",
|
||||
"label": "Prove"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "decision",
|
||||
"to": "promote",
|
||||
"label": "authorize"
|
||||
},
|
||||
|
||||
{
|
||||
"id": "unsafe",
|
||||
"from": "triage",
|
||||
"to": "observe",
|
||||
"label": "Unsafe",
|
||||
"variant": "security",
|
||||
"fromSide": "right",
|
||||
"toSide": "right"
|
||||
},
|
||||
{
|
||||
"id": "review-loop",
|
||||
"id": "observe-triage",
|
||||
"from": "observe",
|
||||
"to": "correct",
|
||||
"label": "Requalify",
|
||||
"variant": "dashed"
|
||||
"to": "triage",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1590,
|
||||
145
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "triage-change",
|
||||
"from": "triage",
|
||||
"to": "change",
|
||||
"label": "Correct",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1590,
|
||||
620
|
||||
],
|
||||
[
|
||||
1500,
|
||||
620
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1450,
|
||||
680
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "change-validate",
|
||||
"from": "change",
|
||||
"to": "validate",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1500,
|
||||
1060
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "validate-release",
|
||||
"from": "validate",
|
||||
"to": "release",
|
||||
"label": "",
|
||||
"fromSide": "left",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
340,
|
||||
1060
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "release-observe",
|
||||
"from": "release",
|
||||
"to": "observe",
|
||||
"label": "",
|
||||
"fromSide": "top",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
340,
|
||||
145
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "triage-safe",
|
||||
"from": "triage",
|
||||
"to": "safe",
|
||||
"label": "Safe",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1920,
|
||||
425
|
||||
],
|
||||
[
|
||||
1920,
|
||||
170
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1930,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "triage-retire",
|
||||
"from": "triage",
|
||||
"to": "retire",
|
||||
"label": "Retire",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1950,
|
||||
425
|
||||
],
|
||||
[
|
||||
1950,
|
||||
520
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1930,
|
||||
490
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "triage-contain",
|
||||
"from": "triage",
|
||||
"to": "contain",
|
||||
"label": "Unsafe",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
1590,
|
||||
580
|
||||
],
|
||||
[
|
||||
1850,
|
||||
580
|
||||
],
|
||||
[
|
||||
1850,
|
||||
910
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1900,
|
||||
720
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "contain-change",
|
||||
"from": "contain",
|
||||
"to": "change",
|
||||
"label": "Reviewed fix",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
2285,
|
||||
1230
|
||||
],
|
||||
[
|
||||
1500,
|
||||
1230
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1900,
|
||||
1190
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "safe-observe",
|
||||
"from": "safe",
|
||||
"to": "observe",
|
||||
"label": "Keep watching",
|
||||
"fromSide": "top",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
2285,
|
||||
20
|
||||
],
|
||||
[
|
||||
950,
|
||||
20
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1640,
|
||||
45
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -1,130 +1,20 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Evidence before claims",
|
||||
"output": "static/diagrams/strategy-measurement-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"meta": {"title": "Two connected measurement tracks", "output": "static/diagrams/strategy-measurement-mobile/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}, "viewBox": [880, 2450]},
|
||||
"components": [
|
||||
{
|
||||
"id": "collect",
|
||||
"type": "backend",
|
||||
"label": "Collect evidence",
|
||||
"sublabel": "Task / CI / incident",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "validate",
|
||||
"type": "backend",
|
||||
"label": "Validate sources",
|
||||
"sublabel": "Joins + missingness",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "calculate",
|
||||
"type": "backend",
|
||||
"label": "Calculate measures",
|
||||
"sublabel": "16 exact contracts",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "balance",
|
||||
"type": "backend",
|
||||
"label": "Read balanced signals",
|
||||
"sublabel": "Quality / flow / risk",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "weigh",
|
||||
"type": "backend",
|
||||
"label": "Weigh benefit and cost",
|
||||
"sublabel": "Outcomes / cost / people",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "backend",
|
||||
"label": "Continue or change",
|
||||
"sublabel": "No causal ROI claim",
|
||||
"pos": [
|
||||
20,
|
||||
620
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
}
|
||||
{"id": "workflow", "type": "backend", "label": "Workflow effectiveness", "tag": "01 / Baseline current work", "sublabel": "Accepted work, time, failures\nCost, effort + experience\nSelect relevant contracts only\nSkills need not exist yet", "pos": [90, 50], "size": [700, 350], "icon": "none"},
|
||||
{"id": "compare", "type": "backend", "label": "Compare the same outcomes", "tag": "02 / After introducing skills", "sublabel": "Same workflow + acceptance\nSame follow-up + source coverage\nKeep gaps and task mix visible\nBefore / after is not causality", "pos": [90, 450], "size": [700, 350], "icon": "none"},
|
||||
{"id": "interpret", "type": "external", "label": "Is work getting better?", "tag": "03 / Interpret workflow evidence", "sublabel": "Balance value, quality and risk\nMore adoption is not better work\nKeep live outcomes separate\nfrom skill evaluation cases", "pos": [90, 850], "size": [700, 350], "icon": "none"},
|
||||
{"id": "skills", "type": "frontend", "label": "Skills effectiveness & health", "tag": "01 / Qualify named skill versions", "sublabel": "Quality: artifact fitness + safety\nCandidate / approved regression\nSelection precision + recall\nNo applicable skills: N/A", "pos": [90, 1250], "size": [700, 350], "icon": "none"},
|
||||
{"id": "observe", "type": "frontend", "label": "Observe use + upkeep", "tag": "02 / Adoption and maintenance", "sublabel": "Supported bundle coverage\nApproved-workflow adoption\nSubstantive review evidence\nMissing observations: unknown", "pos": [90, 1650], "size": [700, 350], "icon": "none"},
|
||||
{"id": "improve", "type": "external", "label": "Improve, retain or retire", "tag": "03 / Use both tracks together", "sublabel": "Owner + independent evidence\nRetain / improve / stop\nNew scope needs new comparison\nNo mandatory collection", "pos": [90, 2050], "size": [700, 350], "icon": "none"}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "collect",
|
||||
"to": "validate",
|
||||
"label": "Check"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "validate",
|
||||
"to": "calculate",
|
||||
"label": "apply definitions"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "calculate",
|
||||
"to": "balance",
|
||||
"label": "compare"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "balance",
|
||||
"to": "weigh",
|
||||
"label": "consider together"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "weigh",
|
||||
"to": "decide",
|
||||
"label": "decide"
|
||||
}
|
||||
{"id": "workflow-compare", "from": "workflow", "to": "compare", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "compare-interpret", "from": "compare", "to": "interpret", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "skills-observe", "from": "skills", "to": "observe", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "observe-improve", "from": "observe", "to": "improve", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "interpret-improve", "from": "interpret", "to": "improve", "label": "", "fromSide": "right", "toSide": "right", "route": "straight", "width": 4, "variant": "default", "via": [[835, 1025], [835, 2225]]}
|
||||
]
|
||||
}
|
||||
@@ -1,130 +1,20 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Evidence before claims",
|
||||
"output": "static/diagrams/strategy-measurement/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"meta": {"title": "Two connected measurement tracks", "output": "static/diagrams/strategy-measurement/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}, "viewBox": [2400, 960]},
|
||||
"components": [
|
||||
{
|
||||
"id": "collect",
|
||||
"type": "backend",
|
||||
"label": "Collect evidence",
|
||||
"sublabel": "Task / CI / incident",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "validate",
|
||||
"type": "backend",
|
||||
"label": "Validate sources",
|
||||
"sublabel": "Joins + missingness",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "calculate",
|
||||
"type": "backend",
|
||||
"label": "Calculate measures",
|
||||
"sublabel": "16 exact contracts",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "balance",
|
||||
"type": "backend",
|
||||
"label": "Read balanced signals",
|
||||
"sublabel": "Quality / flow / risk",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "weigh",
|
||||
"type": "backend",
|
||||
"label": "Weigh benefit and cost",
|
||||
"sublabel": "Outcomes / cost / people",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "backend",
|
||||
"label": "Continue or change",
|
||||
"sublabel": "No causal ROI claim",
|
||||
"pos": [
|
||||
260,
|
||||
280
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
}
|
||||
{"id": "workflow", "type": "backend", "label": "Workflow effectiveness", "tag": "01 / Baseline current work", "sublabel": "Accepted work, time, failures\nCost, effort + experience\nSelect relevant contracts only\nSkills need not exist yet", "pos": [40, 40], "size": [720, 310], "icon": "none"},
|
||||
{"id": "compare", "type": "backend", "label": "Compare the same outcomes", "tag": "02 / After introducing skills", "sublabel": "Same workflow + acceptance\nSame follow-up + source coverage\nKeep gaps and task mix visible\nBefore / after is not causality", "pos": [840, 40], "size": [720, 310], "icon": "none"},
|
||||
{"id": "interpret", "type": "external", "label": "Is work getting better?", "tag": "03 / Interpret workflow evidence", "sublabel": "Balance value, quality and risk\nMore adoption is not better work\nKeep live outcomes separate\nfrom skill evaluation cases", "pos": [1640, 40], "size": [720, 310], "icon": "none"},
|
||||
{"id": "skills", "type": "frontend", "label": "Skills effectiveness & health", "tag": "01 / Qualify named skill versions", "sublabel": "Quality: artifact fitness + safety\nCandidate / approved regression\nSelection precision + recall\nNo applicable skills: N/A", "pos": [40, 590], "size": [720, 310], "icon": "none"},
|
||||
{"id": "observe", "type": "frontend", "label": "Observe use + upkeep", "tag": "02 / Adoption and maintenance", "sublabel": "Supported bundle coverage\nApproved-workflow adoption\nSubstantive review evidence\nMissing observations: unknown", "pos": [840, 590], "size": [720, 310], "icon": "none"},
|
||||
{"id": "improve", "type": "external", "label": "Improve, retain or retire", "tag": "03 / Use both tracks together", "sublabel": "Owner + independent evidence\nRetain / improve / stop\nNew scope needs new comparison\nNo mandatory collection", "pos": [1640, 590], "size": [720, 310], "icon": "none"}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "collect",
|
||||
"to": "validate",
|
||||
"label": "Check"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "validate",
|
||||
"to": "calculate",
|
||||
"label": "apply definitions"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "calculate",
|
||||
"to": "balance",
|
||||
"label": "compare"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "balance",
|
||||
"to": "weigh",
|
||||
"label": "consider together"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "weigh",
|
||||
"to": "decide",
|
||||
"label": "decide"
|
||||
}
|
||||
{"id": "workflow-compare", "from": "workflow", "to": "compare", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "compare-interpret", "from": "compare", "to": "interpret", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "skills-observe", "from": "skills", "to": "observe", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "observe-improve", "from": "observe", "to": "improve", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
|
||||
{"id": "interpret-improve", "from": "interpret", "to": "improve", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"}
|
||||
]
|
||||
}
|
||||
@@ -2,129 +2,261 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Risk-tiered qualification",
|
||||
"title": "TO-BE: Quality",
|
||||
"output": "static/diagrams/strategy-quality-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
880,
|
||||
2800
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "risk",
|
||||
"type": "security",
|
||||
"label": "Classify risk",
|
||||
"sublabel": "R1 / R2 / R3",
|
||||
"id": "selection",
|
||||
"type": "external",
|
||||
"label": "Right skill?",
|
||||
"tag": "Selection evidence",
|
||||
"sublabel": "Triggers, near misses, negatives",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
120
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "plan",
|
||||
"type": "security",
|
||||
"label": "Agree evaluation",
|
||||
"sublabel": "Task mix + thresholds",
|
||||
"id": "safety",
|
||||
"type": "external",
|
||||
"label": "Safe execution?",
|
||||
"tag": "Safety evidence",
|
||||
"sublabel": "Permissions + adversarial trials",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
60,
|
||||
490
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "trial",
|
||||
"type": "security",
|
||||
"label": "Repeat trials",
|
||||
"sublabel": "Candidate vs approved",
|
||||
"id": "artifact",
|
||||
"type": "external",
|
||||
"label": "Valid artifact?",
|
||||
"tag": "Independent inspection",
|
||||
"sublabel": "Tests + human assessment",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
60,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "verify",
|
||||
"type": "security",
|
||||
"label": "Verify artifacts",
|
||||
"sublabel": "Independent checks",
|
||||
"id": "outcome",
|
||||
"type": "external",
|
||||
"label": "Useful outcome?",
|
||||
"tag": "Declared evaluation cases",
|
||||
"sublabel": "Fitness + revision regression",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
60,
|
||||
1230
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "gate",
|
||||
"type": "security",
|
||||
"label": "All gates pass?",
|
||||
"sublabel": "Safety cannot be traded",
|
||||
"label": "Every gate must pass",
|
||||
"tag": "Risk sets evaluation depth",
|
||||
"sublabel": "No averaging away harm\nCritical effect blocks promotion\nMissing coverage = incomplete",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
60,
|
||||
1600
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
310
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "promote",
|
||||
"type": "security",
|
||||
"label": "Promote or hold",
|
||||
"sublabel": "Owner decision",
|
||||
"id": "accept",
|
||||
"type": "backend",
|
||||
"label": "Accept evidence",
|
||||
"tag": "Quality Engineering reviewer",
|
||||
"sublabel": "Owner decides bounded pilot",
|
||||
"pos": [
|
||||
20,
|
||||
620
|
||||
60,
|
||||
2060
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "rework",
|
||||
"type": "security",
|
||||
"label": "Rework / retest",
|
||||
"tag": "Any failure or missing evidence",
|
||||
"sublabel": "Keep failures in the record",
|
||||
"pos": [
|
||||
60,
|
||||
2430
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
220
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "risk",
|
||||
"to": "plan",
|
||||
"label": "Scope"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "plan",
|
||||
"to": "trial",
|
||||
"label": "freeze plan"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "trial",
|
||||
"to": "verify",
|
||||
"label": "Assess"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "verify",
|
||||
"id": "selection-gate",
|
||||
"from": "selection",
|
||||
"to": "gate",
|
||||
"label": "review evidence"
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
850,
|
||||
230.0
|
||||
],
|
||||
[
|
||||
850,
|
||||
1755.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1560
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"id": "safety-gate",
|
||||
"from": "safety",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
850,
|
||||
600.0
|
||||
],
|
||||
[
|
||||
850,
|
||||
1755.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1560
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "artifact-gate",
|
||||
"from": "artifact",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
850,
|
||||
970.0
|
||||
],
|
||||
[
|
||||
850,
|
||||
1755.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1560
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "outcome-gate",
|
||||
"from": "outcome",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1505
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "gate-accept",
|
||||
"from": "gate",
|
||||
"to": "promote",
|
||||
"label": "decide"
|
||||
"to": "accept",
|
||||
"label": "Pass",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
610,
|
||||
1965
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "gate-rework",
|
||||
"from": "gate",
|
||||
"to": "rework",
|
||||
"label": "Fail",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
824,
|
||||
1755.0
|
||||
],
|
||||
[
|
||||
824,
|
||||
2540.0
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
2390
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -2,129 +2,265 @@
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Risk-tiered qualification",
|
||||
"title": "TO-BE: Quality",
|
||||
"output": "static/diagrams/strategy-quality/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"viewBox": [
|
||||
2000,
|
||||
1050
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "risk",
|
||||
"type": "security",
|
||||
"label": "Classify risk",
|
||||
"sublabel": "R1 / R2 / R3",
|
||||
"id": "selection",
|
||||
"type": "external",
|
||||
"label": "Right skill?",
|
||||
"tag": "Selection evidence",
|
||||
"sublabel": "Triggers, near misses, negatives",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
60,
|
||||
70
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
510,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "plan",
|
||||
"type": "security",
|
||||
"label": "Agree evaluation",
|
||||
"sublabel": "Task mix + thresholds",
|
||||
"id": "safety",
|
||||
"type": "external",
|
||||
"label": "Safe execution?",
|
||||
"tag": "Safety evidence",
|
||||
"sublabel": "Permissions + adversarial trials",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
60,
|
||||
310
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
510,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "trial",
|
||||
"type": "security",
|
||||
"label": "Repeat trials",
|
||||
"sublabel": "Candidate vs approved",
|
||||
"id": "artifact",
|
||||
"type": "external",
|
||||
"label": "Valid artifact?",
|
||||
"tag": "Independent inspection",
|
||||
"sublabel": "Tests + human assessment",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
60,
|
||||
550
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
510,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "verify",
|
||||
"type": "security",
|
||||
"label": "Verify artifacts",
|
||||
"sublabel": "Independent checks",
|
||||
"id": "outcome",
|
||||
"type": "external",
|
||||
"label": "Useful outcome?",
|
||||
"tag": "Declared evaluation cases",
|
||||
"sublabel": "Fitness + revision regression",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
60,
|
||||
790
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
510,
|
||||
170
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "gate",
|
||||
"type": "security",
|
||||
"label": "All gates pass?",
|
||||
"sublabel": "Safety cannot be traded",
|
||||
"label": "Every gate must pass",
|
||||
"tag": "Risk sets evaluation depth",
|
||||
"sublabel": "No averaging away harm\nCritical effect blocks promotion\nMissing coverage = incomplete",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
740,
|
||||
350
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
520,
|
||||
310
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "promote",
|
||||
"type": "security",
|
||||
"label": "Promote or hold",
|
||||
"sublabel": "Owner decision",
|
||||
"id": "accept",
|
||||
"type": "backend",
|
||||
"label": "Accept evidence",
|
||||
"tag": "Quality Engineering reviewer",
|
||||
"sublabel": "Owner decides bounded pilot",
|
||||
"pos": [
|
||||
260,
|
||||
280
|
||||
1430,
|
||||
160
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
510,
|
||||
190
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "rework",
|
||||
"type": "security",
|
||||
"label": "Rework / retest",
|
||||
"tag": "Any failure or missing evidence",
|
||||
"sublabel": "Keep failures in the record",
|
||||
"pos": [
|
||||
1430,
|
||||
760
|
||||
],
|
||||
"size": [
|
||||
510,
|
||||
190
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "risk",
|
||||
"to": "plan",
|
||||
"label": "Scope"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "plan",
|
||||
"to": "trial",
|
||||
"label": "freeze plan"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "trial",
|
||||
"to": "verify",
|
||||
"label": "Assess"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "verify",
|
||||
"id": "selection-gate",
|
||||
"from": "selection",
|
||||
"to": "gate",
|
||||
"label": "review evidence"
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
650,
|
||||
155
|
||||
],
|
||||
[
|
||||
650,
|
||||
505
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"id": "safety-gate",
|
||||
"from": "safety",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
650,
|
||||
395
|
||||
],
|
||||
[
|
||||
650,
|
||||
505
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "artifact-gate",
|
||||
"from": "artifact",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
650,
|
||||
635
|
||||
],
|
||||
[
|
||||
650,
|
||||
505
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "outcome-gate",
|
||||
"from": "outcome",
|
||||
"to": "gate",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
650,
|
||||
875
|
||||
],
|
||||
[
|
||||
650,
|
||||
505
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "gate-accept",
|
||||
"from": "gate",
|
||||
"to": "promote",
|
||||
"label": "decide"
|
||||
"to": "accept",
|
||||
"label": "Pass",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1340,
|
||||
505
|
||||
],
|
||||
[
|
||||
1340,
|
||||
255
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1330,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "gate-rework",
|
||||
"from": "gate",
|
||||
"to": "rework",
|
||||
"label": "Fail",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
1340,
|
||||
505
|
||||
],
|
||||
[
|
||||
1340,
|
||||
855
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1325,
|
||||
900
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Stage 1: Delivery first",
|
||||
"output": "static/diagrams/strategy-roadmap-adoption-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Stage 1: Delivery first"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"delivery",
|
||||
"remaining"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "delivery",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -140.0,
|
||||
"type": "backend",
|
||||
"label": "Delivery first",
|
||||
"sublabel": "Human + AI Agent; keep improving.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "remaining",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 140.0,
|
||||
"type": "backend",
|
||||
"label": "Other SDLC phases",
|
||||
"sublabel": "Expand adoption; order not yet decided.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "delivery",
|
||||
"to": "remaining",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Stage 1: Delivery first",
|
||||
"output": "static/diagrams/strategy-roadmap-adoption/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Stage 1: Delivery first"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"delivery",
|
||||
"remaining"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "delivery",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 0,
|
||||
"type": "backend",
|
||||
"label": "Delivery first",
|
||||
"sublabel": "Human + AI Agent; keep improving.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "remaining",
|
||||
"lane": "adoption",
|
||||
"col": 1,
|
||||
"yOffset": 0,
|
||||
"type": "backend",
|
||||
"label": "Other SDLC phases",
|
||||
"sublabel": "Expand adoption; order not yet decided.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "delivery",
|
||||
"to": "remaining",
|
||||
"role": "main",
|
||||
"fromSide": "right",
|
||||
"toSide": "left"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Improve within each phase",
|
||||
"output": "static/diagrams/strategy-roadmap-loop-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Improve within each phase"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"understand",
|
||||
"baseline",
|
||||
"topology"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "understand",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -700.0,
|
||||
"type": "backend",
|
||||
"label": "Understand today",
|
||||
"sublabel": "Actual practices, tools and problems.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "baseline",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -420.0,
|
||||
"type": "backend",
|
||||
"label": "Set metrics / KPIs",
|
||||
"sublabel": "Establish a baseline before changes.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "topology",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -140.0,
|
||||
"type": "backend",
|
||||
"label": "Engineer topology",
|
||||
"sublabel": "Connect skills, triggers and handoffs.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "use",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 140.0,
|
||||
"type": "backend",
|
||||
"label": "Qualify, then pilot",
|
||||
"sublabel": "Authorize bounded human + AI work.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "collect",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 420.0,
|
||||
"type": "backend",
|
||||
"label": "Collect results",
|
||||
"sublabel": "Metrics, friction and human feedback.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "reassess",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 700.0,
|
||||
"type": "backend",
|
||||
"label": "Understand anew",
|
||||
"sublabel": "Compare with baseline; repeat the loop.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "understand",
|
||||
"to": "baseline",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "baseline",
|
||||
"to": "topology",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "topology",
|
||||
"to": "use",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "use",
|
||||
"to": "collect",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "collect",
|
||||
"to": "reassess",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "repeat",
|
||||
"from": "reassess",
|
||||
"to": "understand",
|
||||
"role": "return",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "return-left"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Improve within each phase",
|
||||
"output": "static/diagrams/strategy-roadmap-loop/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Improve within each phase"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"understand",
|
||||
"baseline",
|
||||
"topology"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "understand",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -160,
|
||||
"type": "backend",
|
||||
"label": "Understand today",
|
||||
"sublabel": "Actual practices, tools and problems.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "baseline",
|
||||
"lane": "adoption",
|
||||
"col": 1,
|
||||
"yOffset": -160,
|
||||
"type": "backend",
|
||||
"label": "Set metrics / KPIs",
|
||||
"sublabel": "Establish a baseline before changes.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "topology",
|
||||
"lane": "adoption",
|
||||
"col": 2,
|
||||
"yOffset": -160,
|
||||
"type": "backend",
|
||||
"label": "Engineer topology",
|
||||
"sublabel": "Connect skills, triggers and handoffs.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "use",
|
||||
"lane": "adoption",
|
||||
"col": 2,
|
||||
"yOffset": 160,
|
||||
"type": "backend",
|
||||
"label": "Qualify, then pilot",
|
||||
"sublabel": "Authorize bounded human + AI work.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "collect",
|
||||
"lane": "adoption",
|
||||
"col": 1,
|
||||
"yOffset": 160,
|
||||
"type": "backend",
|
||||
"label": "Collect results",
|
||||
"sublabel": "Metrics, friction and human feedback.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "reassess",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 160,
|
||||
"type": "backend",
|
||||
"label": "Understand anew",
|
||||
"sublabel": "Compare with baseline; repeat the loop.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "understand",
|
||||
"to": "baseline",
|
||||
"role": "main",
|
||||
"fromSide": "right",
|
||||
"toSide": "left"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "baseline",
|
||||
"to": "topology",
|
||||
"role": "main",
|
||||
"fromSide": "right",
|
||||
"toSide": "left"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "topology",
|
||||
"to": "use",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "use",
|
||||
"to": "collect",
|
||||
"role": "main",
|
||||
"fromSide": "left",
|
||||
"toSide": "right"
|
||||
},
|
||||
{
|
||||
"id": "flow-4",
|
||||
"from": "collect",
|
||||
"to": "reassess",
|
||||
"role": "main",
|
||||
"fromSide": "left",
|
||||
"toSide": "right"
|
||||
},
|
||||
{
|
||||
"id": "repeat",
|
||||
"from": "reassess",
|
||||
"to": "understand",
|
||||
"role": "return",
|
||||
"fromSide": "top",
|
||||
"toSide": "bottom",
|
||||
"route": "straight"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,110 +0,0 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Evidence-gated rollout",
|
||||
"output": "static/diagrams/strategy-roadmap-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "foundation",
|
||||
"type": "backend",
|
||||
"label": "1 \u00b7 Foundation",
|
||||
"sublabel": "People + data + baseline",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "backend",
|
||||
"label": "2 \u00b7 Skills pilot",
|
||||
"sublabel": "Qualified, useful work",
|
||||
"pos": [
|
||||
20,
|
||||
140
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "distribution",
|
||||
"type": "backend",
|
||||
"label": "3 \u00b7 Distribution",
|
||||
"sublabel": "Revocation + recovery",
|
||||
"pos": [
|
||||
20,
|
||||
260
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "coordination",
|
||||
"type": "backend",
|
||||
"label": "4 \u00b7 Coordination",
|
||||
"sublabel": "Human takeover proven",
|
||||
"pos": [
|
||||
20,
|
||||
380
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "expansion",
|
||||
"type": "backend",
|
||||
"label": "5 \u00b7 Departments",
|
||||
"sublabel": "Outcomes + cost + risk",
|
||||
"pos": [
|
||||
20,
|
||||
500
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "foundation",
|
||||
"to": "pilot",
|
||||
"label": "Charter"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "pilot",
|
||||
"to": "distribution",
|
||||
"label": "quality + coverage"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "distribution",
|
||||
"to": "coordination",
|
||||
"label": "Controls"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "coordination",
|
||||
"to": "expansion",
|
||||
"label": "authority drills pass"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Two stages toward Target",
|
||||
"output": "static/diagrams/strategy-roadmap-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Two stages toward Target"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"skills",
|
||||
"autonomy"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "skills",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": -140.0,
|
||||
"type": "backend",
|
||||
"label": "Adopt skills",
|
||||
"sublabel": "Human + AI Agent in each SDLC phase.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "autonomy",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 140.0,
|
||||
"type": "backend",
|
||||
"label": "Autonomous Agent",
|
||||
"sublabel": "Future: separately justified authority.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "skills",
|
||||
"to": "autonomy",
|
||||
"role": "main",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,110 +0,0 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: Evidence-gated rollout",
|
||||
"output": "static/diagrams/strategy-roadmap/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "foundation",
|
||||
"type": "backend",
|
||||
"label": "1 \u00b7 Foundation",
|
||||
"sublabel": "People + data + baseline",
|
||||
"pos": [
|
||||
20,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "backend",
|
||||
"label": "2 \u00b7 Skills pilot",
|
||||
"sublabel": "Qualified, useful work",
|
||||
"pos": [
|
||||
260,
|
||||
20
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "distribution",
|
||||
"type": "backend",
|
||||
"label": "3 \u00b7 Distribution",
|
||||
"sublabel": "Revocation + recovery",
|
||||
"pos": [
|
||||
260,
|
||||
150
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "coordination",
|
||||
"type": "backend",
|
||||
"label": "4 \u00b7 Coordination",
|
||||
"sublabel": "Human takeover proven",
|
||||
"pos": [
|
||||
20,
|
||||
150
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "expansion",
|
||||
"type": "backend",
|
||||
"label": "5 \u00b7 Departments",
|
||||
"sublabel": "Outcomes + cost + risk",
|
||||
"pos": [
|
||||
20,
|
||||
280
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
60
|
||||
]
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "foundation",
|
||||
"to": "pilot",
|
||||
"label": "Charter"
|
||||
},
|
||||
{
|
||||
"id": "flow-1",
|
||||
"from": "pilot",
|
||||
"to": "distribution",
|
||||
"label": "quality + coverage"
|
||||
},
|
||||
{
|
||||
"id": "flow-2",
|
||||
"from": "distribution",
|
||||
"to": "coordination",
|
||||
"label": "Controls"
|
||||
},
|
||||
{
|
||||
"id": "flow-3",
|
||||
"from": "coordination",
|
||||
"to": "expansion",
|
||||
"label": "authority drills pass"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"schema_version": 2,
|
||||
"diagram_type": "workflow",
|
||||
"meta": {
|
||||
"title": "Two stages toward Target",
|
||||
"output": "static/diagrams/strategy-roadmap/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"animation": "none",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
}
|
||||
},
|
||||
"lanes": [
|
||||
{
|
||||
"id": "adoption",
|
||||
"label": "Two stages toward Target"
|
||||
}
|
||||
],
|
||||
"mainPath": [
|
||||
"skills",
|
||||
"autonomy"
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"id": "skills",
|
||||
"lane": "adoption",
|
||||
"col": 0,
|
||||
"yOffset": 0,
|
||||
"type": "backend",
|
||||
"label": "Adopt skills",
|
||||
"sublabel": "Human + AI Agent in each SDLC phase.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
},
|
||||
{
|
||||
"id": "autonomy",
|
||||
"lane": "adoption",
|
||||
"col": 1,
|
||||
"yOffset": 0,
|
||||
"type": "backend",
|
||||
"label": "Autonomous Agent",
|
||||
"sublabel": "Future: separately justified authority.",
|
||||
"width": 340,
|
||||
"height": 240
|
||||
}
|
||||
],
|
||||
"edges": [
|
||||
{
|
||||
"id": "flow-0",
|
||||
"from": "skills",
|
||||
"to": "autonomy",
|
||||
"role": "main",
|
||||
"fromSide": "right",
|
||||
"toSide": "left"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,249 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "Proposed: first six months as AI Architect",
|
||||
"output": "static/diagrams/strategy-six-months-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
1000,
|
||||
2950
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "baseline",
|
||||
"type": "external",
|
||||
"label": "Month 1: discover",
|
||||
"tag": "Architect + CTO + willing teams",
|
||||
"sublabel": "Current AI workflows + constraints\nPair with developers and reviewers\nChoose an evidenced bottleneck",
|
||||
"pos": [
|
||||
200,
|
||||
40
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "engineer",
|
||||
"type": "external",
|
||||
"label": "Month 2: agree experiment",
|
||||
"tag": "Architect + partner lead + reviewer",
|
||||
"sublabel": "One workflow + feasible baseline\nChoose context, coaching or tooling\nSkills only if they fit the problem",
|
||||
"pos": [
|
||||
200,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "qualify",
|
||||
"type": "security",
|
||||
"label": "Month 3: pair and pilot",
|
||||
"tag": "Team agrees time; owner permits scope",
|
||||
"sublabel": "Independent checks before live work\nCollect accepted work and burden\nUnsafe or unsupported: stop",
|
||||
"pos": [
|
||||
200,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "external",
|
||||
"label": "Month 4: decide from evidence",
|
||||
"tag": "Workflow owner + CTO review",
|
||||
"sublabel": "Compare current practice and pilot\nRetain / change / hold / stop\nIncomplete: bounded extension only",
|
||||
"pos": [
|
||||
200,
|
||||
1270
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "security",
|
||||
"label": "Month 5: transfer selectively",
|
||||
"tag": "Willing champion + team lead",
|
||||
"sublabel": "Only if value and upkeep hold\nTry another team with new baseline\nNo capacity: stay narrow or retire",
|
||||
"pos": [
|
||||
200,
|
||||
1680
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "maintain",
|
||||
"type": "external",
|
||||
"label": "Month 6: hand over or stop",
|
||||
"tag": "Team owner + CTO investment decision",
|
||||
"sublabel": "Evidence, costs and limits visible\nOwned workflow or documented stop\nNext quarter is not automatic AI",
|
||||
"pos": [
|
||||
200,
|
||||
2090
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "reference",
|
||||
"type": "backend",
|
||||
"label": "Proposed six-month plan",
|
||||
"tag": "Solo architect; no team authority",
|
||||
"sublabel": "Month 6 → 2: revise next question\nMonth 5 → 1: baseline new scope\nProposed, not company commitments",
|
||||
"pos": [
|
||||
200,
|
||||
2500
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "baseline-engineer",
|
||||
"from": "baseline",
|
||||
"to": "engineer",
|
||||
"label": "Problem",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
405
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "engineer-qualify",
|
||||
"from": "engineer",
|
||||
"to": "qualify",
|
||||
"label": "Agreement",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
815
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "qualify-pilot",
|
||||
"from": "qualify",
|
||||
"to": "pilot",
|
||||
"label": "Evidence",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
1225
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot-decide",
|
||||
"from": "pilot",
|
||||
"to": "decide",
|
||||
"label": "Decision",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
1635
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-maintain",
|
||||
"from": "decide",
|
||||
"to": "maintain",
|
||||
"label": "Handover",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
2045
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "maintain-engineer",
|
||||
"from": "maintain",
|
||||
"to": "engineer",
|
||||
"label": "",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
145,
|
||||
2240
|
||||
],
|
||||
[
|
||||
145,
|
||||
600
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-baseline",
|
||||
"from": "decide",
|
||||
"to": "baseline",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
980,
|
||||
1830
|
||||
],
|
||||
[
|
||||
980,
|
||||
190
|
||||
]
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,271 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "Proposed: first six months as AI Architect",
|
||||
"output": "static/diagrams/strategy-six-months/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
2400,
|
||||
1580
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "baseline",
|
||||
"type": "external",
|
||||
"label": "Month 1: discover",
|
||||
"tag": "Architect + CTO + willing teams",
|
||||
"sublabel": "Current AI workflows + constraints\nPair with developers and reviewers\nChoose an evidenced bottleneck",
|
||||
"pos": [
|
||||
100,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "engineer",
|
||||
"type": "external",
|
||||
"label": "Month 2: agree experiment",
|
||||
"tag": "Architect + partner lead + reviewer",
|
||||
"sublabel": "One workflow + feasible baseline\nChoose context, coaching or tooling\nSkills only if they fit the problem",
|
||||
"pos": [
|
||||
900,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "qualify",
|
||||
"type": "security",
|
||||
"label": "Month 3: pair and pilot",
|
||||
"tag": "Team agrees time; owner permits scope",
|
||||
"sublabel": "Independent checks before live work\nCollect accepted work and burden\nUnsafe or unsupported: stop",
|
||||
"pos": [
|
||||
1700,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "external",
|
||||
"label": "Month 4: decide from evidence",
|
||||
"tag": "Workflow owner + CTO review",
|
||||
"sublabel": "Compare current practice and pilot\nRetain / change / hold / stop\nIncomplete: bounded extension only",
|
||||
"pos": [
|
||||
1700,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "security",
|
||||
"label": "Month 5: transfer selectively",
|
||||
"tag": "Willing champion + team lead",
|
||||
"sublabel": "Only if value and upkeep hold\nTry another team with new baseline\nNo capacity: stay narrow or retire",
|
||||
"pos": [
|
||||
900,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "maintain",
|
||||
"type": "external",
|
||||
"label": "Month 6: hand over or stop",
|
||||
"tag": "Team owner + CTO investment decision",
|
||||
"sublabel": "Evidence, costs and limits visible\nOwned workflow or documented stop\nNext quarter is not automatic AI",
|
||||
"pos": [
|
||||
100,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "reference",
|
||||
"type": "backend",
|
||||
"label": "Proposed six-month plan",
|
||||
"tag": "Solo architect; no team authority",
|
||||
"sublabel": "Month 6 → 2: revise next question\nMonth 5 → 1: baseline new scope\nProposed, not company commitments",
|
||||
"pos": [
|
||||
100,
|
||||
1270
|
||||
],
|
||||
"size": [
|
||||
2200,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "baseline-engineer",
|
||||
"from": "baseline",
|
||||
"to": "engineer",
|
||||
"label": "Problem",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
800,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "engineer-qualify",
|
||||
"from": "engineer",
|
||||
"to": "qualify",
|
||||
"label": "Agreement",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1600,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "qualify-pilot",
|
||||
"from": "qualify",
|
||||
"to": "pilot",
|
||||
"label": "Evidence",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
2000,
|
||||
520
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
2010,
|
||||
535
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot-decide",
|
||||
"from": "pilot",
|
||||
"to": "decide",
|
||||
"label": "Decision",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1600,
|
||||
840
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-maintain",
|
||||
"from": "decide",
|
||||
"to": "maintain",
|
||||
"label": "Handover",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
800,
|
||||
840
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "maintain-engineer",
|
||||
"from": "maintain",
|
||||
"to": "engineer",
|
||||
"label": "Next question",
|
||||
"fromSide": "top",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
400,
|
||||
550
|
||||
],
|
||||
[
|
||||
1200,
|
||||
550
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
800,
|
||||
535
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-baseline",
|
||||
"from": "decide",
|
||||
"to": "baseline",
|
||||
"label": "New scope",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1200,
|
||||
1150
|
||||
],
|
||||
[
|
||||
60,
|
||||
1150
|
||||
],
|
||||
[
|
||||
60,
|
||||
430
|
||||
],
|
||||
[
|
||||
400,
|
||||
430
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1135
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,249 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: stage01",
|
||||
"output": "static/diagrams/strategy-stage01-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
1000,
|
||||
2950
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "baseline",
|
||||
"type": "external",
|
||||
"label": "Understand + baseline",
|
||||
"tag": "Product Engineering workflow owner",
|
||||
"sublabel": "Workflow map + desired improvement\nSelected measures + starting evidence\nGovernance: people, scope, authority",
|
||||
"pos": [
|
||||
200,
|
||||
40
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "engineer",
|
||||
"type": "external",
|
||||
"label": "Choose an intervention",
|
||||
"tag": "Owning team + independent reviewer",
|
||||
"sublabel": "Context, coaching, tooling or skills\nPinned candidate + client + limits\nDeliver: patch and regression tests",
|
||||
"pos": [
|
||||
200,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "qualify",
|
||||
"type": "security",
|
||||
"label": "Fit for a bounded pilot?",
|
||||
"tag": "Quality evidence \u2192 owning approver",
|
||||
"sublabel": "Artifact + safety + regression report\nPass: authorize exact pilot scope\nFail / incomplete: hold or rework",
|
||||
"pos": [
|
||||
200,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "external",
|
||||
"label": "Pilot real work",
|
||||
"tag": "Human + AI Agent; independent review",
|
||||
"sublabel": "Use qualified revision within scope\nAccepted / failed work + feedback\nManual path; no new release power",
|
||||
"pos": [
|
||||
200,
|
||||
1270
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "security",
|
||||
"label": "Retain, improve or stop?",
|
||||
"tag": "Workflow owner + reviewed evidence",
|
||||
"sublabel": "Compare with baseline, not trials\nNo justified benefit: hold / stop\nNew scope: baseline + new approval",
|
||||
"pos": [
|
||||
200,
|
||||
1680
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "maintain",
|
||||
"type": "external",
|
||||
"label": "Maintain + requalify",
|
||||
"tag": "Owner, Quality, Platform & Security",
|
||||
"sublabel": "Retain: support approved revision\nDrift / defects: revise and retest\nHarm: contain; never auto-restore",
|
||||
"pos": [
|
||||
200,
|
||||
2090
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "reference",
|
||||
"type": "backend",
|
||||
"label": "Governance + Measurement",
|
||||
"tag": "Throughout, not one-time gates",
|
||||
"sublabel": "Left return: changed revision\nRight return: new scope needs baseline\nSelected evidence; no forced rollout",
|
||||
"pos": [
|
||||
200,
|
||||
2500
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "baseline-engineer",
|
||||
"from": "baseline",
|
||||
"to": "engineer",
|
||||
"label": "Map",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
405
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "engineer-qualify",
|
||||
"from": "engineer",
|
||||
"to": "qualify",
|
||||
"label": "Candidate",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
815
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "qualify-pilot",
|
||||
"from": "qualify",
|
||||
"to": "pilot",
|
||||
"label": "Authorized",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
1225
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot-decide",
|
||||
"from": "pilot",
|
||||
"to": "decide",
|
||||
"label": "Outcomes",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
1635
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-maintain",
|
||||
"from": "decide",
|
||||
"to": "maintain",
|
||||
"label": "Retain",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
2045
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "maintain-engineer",
|
||||
"from": "maintain",
|
||||
"to": "engineer",
|
||||
"label": "",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
145,
|
||||
2240
|
||||
],
|
||||
[
|
||||
145,
|
||||
600
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-baseline",
|
||||
"from": "decide",
|
||||
"to": "baseline",
|
||||
"label": "",
|
||||
"fromSide": "right",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
980,
|
||||
1830
|
||||
],
|
||||
[
|
||||
980,
|
||||
190
|
||||
]
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,271 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: stage01",
|
||||
"output": "static/diagrams/strategy-stage01/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
2400,
|
||||
1580
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "baseline",
|
||||
"type": "external",
|
||||
"label": "Understand + baseline",
|
||||
"tag": "Product Engineering workflow owner",
|
||||
"sublabel": "Workflow map + desired improvement\nSelected measures + starting evidence\nGovernance: people, scope, authority",
|
||||
"pos": [
|
||||
100,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "engineer",
|
||||
"type": "external",
|
||||
"label": "Choose an intervention",
|
||||
"tag": "Owning team + independent reviewer",
|
||||
"sublabel": "Context, coaching, tooling or skills\nPinned candidate + client + limits\nDeliver: patch and regression tests",
|
||||
"pos": [
|
||||
900,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "qualify",
|
||||
"type": "security",
|
||||
"label": "Fit for a bounded pilot?",
|
||||
"tag": "Quality evidence \u2192 owning approver",
|
||||
"sublabel": "Artifact + safety + regression report\nPass: authorize exact pilot scope\nFail / incomplete: hold or rework",
|
||||
"pos": [
|
||||
1700,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "pilot",
|
||||
"type": "external",
|
||||
"label": "Pilot real work",
|
||||
"tag": "Human + AI Agent; independent review",
|
||||
"sublabel": "Use qualified revision within scope\nAccepted / failed work + feedback\nManual path; no new release power",
|
||||
"pos": [
|
||||
1700,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decide",
|
||||
"type": "security",
|
||||
"label": "Retain, improve or stop?",
|
||||
"tag": "Workflow owner + reviewed evidence",
|
||||
"sublabel": "Compare with baseline, not trials\nNo justified benefit: hold / stop\nNew scope: baseline + new approval",
|
||||
"pos": [
|
||||
900,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "maintain",
|
||||
"type": "external",
|
||||
"label": "Maintain + requalify",
|
||||
"tag": "Owner, Quality, Platform & Security",
|
||||
"sublabel": "Retain: support approved revision\nDrift / defects: revise and retest\nHarm: contain; never auto-restore",
|
||||
"pos": [
|
||||
100,
|
||||
730
|
||||
],
|
||||
"size": [
|
||||
600,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "reference",
|
||||
"type": "backend",
|
||||
"label": "Governance + Measurement",
|
||||
"tag": "Throughout, not one-time gates",
|
||||
"sublabel": "Left return: changed revision\nRight return: new scope needs baseline\nSelected evidence; no forced rollout",
|
||||
"pos": [
|
||||
100,
|
||||
1270
|
||||
],
|
||||
"size": [
|
||||
2200,
|
||||
260
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "baseline-engineer",
|
||||
"from": "baseline",
|
||||
"to": "engineer",
|
||||
"label": "Map",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
800,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "engineer-qualify",
|
||||
"from": "engineer",
|
||||
"to": "qualify",
|
||||
"label": "Candidate",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1600,
|
||||
210
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "qualify-pilot",
|
||||
"from": "qualify",
|
||||
"to": "pilot",
|
||||
"label": "Authorized",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
2000,
|
||||
520
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
2010,
|
||||
535
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "pilot-decide",
|
||||
"from": "pilot",
|
||||
"to": "decide",
|
||||
"label": "Outcomes",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
1600,
|
||||
840
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-maintain",
|
||||
"from": "decide",
|
||||
"to": "maintain",
|
||||
"label": "Retain",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
800,
|
||||
840
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "maintain-engineer",
|
||||
"from": "maintain",
|
||||
"to": "engineer",
|
||||
"label": "Changed revision",
|
||||
"fromSide": "top",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
400,
|
||||
550
|
||||
],
|
||||
[
|
||||
1200,
|
||||
550
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
800,
|
||||
535
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decide-baseline",
|
||||
"from": "decide",
|
||||
"to": "baseline",
|
||||
"label": "New scope",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "bottom",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1200,
|
||||
1150
|
||||
],
|
||||
[
|
||||
60,
|
||||
1150
|
||||
],
|
||||
[
|
||||
60,
|
||||
430
|
||||
],
|
||||
[
|
||||
400,
|
||||
430
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
620,
|
||||
1135
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,212 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: stage02",
|
||||
"output": "static/diagrams/strategy-stage02-mobile/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
1000,
|
||||
2540
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "proven",
|
||||
"type": "external",
|
||||
"label": "Dependable Stage 01",
|
||||
"tag": "Existing human-directed workflow",
|
||||
"sublabel": "Proven skills + limits + outcome record\nNo inherited autonomous authority",
|
||||
"pos": [
|
||||
200,
|
||||
40
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "case",
|
||||
"type": "external",
|
||||
"label": "Justify extra authority",
|
||||
"tag": "Owning department proposes scope",
|
||||
"sublabel": "Why needed? Exact data + effects\nObservation first, then proposals",
|
||||
"pos": [
|
||||
200,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decision",
|
||||
"type": "security",
|
||||
"label": "Authorize or hold",
|
||||
"tag": "Human decision; roles named first",
|
||||
"sublabel": "Security: boundary; Quality: evidence\nPlatform & IT: enforcement + takeover\nOwning approver: exact permitted scope",
|
||||
"pos": [
|
||||
200,
|
||||
860
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "execute",
|
||||
"type": "backend",
|
||||
"label": "Bounded execution",
|
||||
"tag": "Only within recorded authorization",
|
||||
"sublabel": "Exact-artifact checks + audit\nChanged boundary: reopen decision",
|
||||
"pos": [
|
||||
200,
|
||||
1270
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "stop",
|
||||
"type": "security",
|
||||
"label": "Independent stop + takeover",
|
||||
"tag": "Platform & IT + Security + owner",
|
||||
"sublabel": "Revoke mutations; preserve evidence\nRecover manually; requalify correction",
|
||||
"pos": [
|
||||
200,
|
||||
1680
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "hold",
|
||||
"type": "external",
|
||||
"label": "Hold / return to Stage 01",
|
||||
"tag": "Missing authority or readiness",
|
||||
"sublabel": "Fix gaps, narrow scope or stay here\nNo automatic progression",
|
||||
"pos": [
|
||||
200,
|
||||
2090
|
||||
],
|
||||
"size": [
|
||||
740,
|
||||
300
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "proven-case",
|
||||
"from": "proven",
|
||||
"to": "case",
|
||||
"label": "Need / limits",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
405
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "case-decision",
|
||||
"from": "case",
|
||||
"to": "decision",
|
||||
"label": "Proposal",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
815
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decision-execute",
|
||||
"from": "decision",
|
||||
"to": "execute",
|
||||
"label": "Authorized",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
570,
|
||||
1225
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "execute-stop",
|
||||
"from": "execute",
|
||||
"to": "stop",
|
||||
"label": "Harm / stop",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
570,
|
||||
1635
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decision-hold",
|
||||
"from": "decision",
|
||||
"to": "hold",
|
||||
"label": "",
|
||||
"fromSide": "left",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
105,
|
||||
1010
|
||||
],
|
||||
[
|
||||
105,
|
||||
2240
|
||||
]
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "stop-hold",
|
||||
"from": "stop",
|
||||
"to": "hold",
|
||||
"label": "Requalify",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
570,
|
||||
2045
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,236 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"diagram_type": "architecture",
|
||||
"meta": {
|
||||
"title": "TO-BE: stage02",
|
||||
"output": "static/diagrams/strategy-stage02/index.html",
|
||||
"quality_profile": "showcase",
|
||||
"legend": {
|
||||
"mode": "hidden"
|
||||
},
|
||||
"viewBox": [
|
||||
2740,
|
||||
1260
|
||||
]
|
||||
},
|
||||
"components": [
|
||||
{
|
||||
"id": "proven",
|
||||
"type": "external",
|
||||
"label": "Dependable Stage 01",
|
||||
"tag": "Existing human-directed workflow",
|
||||
"sublabel": "Proven skills + limits + outcome record\nNo inherited autonomous authority",
|
||||
"pos": [
|
||||
60,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
680,
|
||||
230
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "case",
|
||||
"type": "external",
|
||||
"label": "Justify extra authority",
|
||||
"tag": "Owning department proposes scope",
|
||||
"sublabel": "Why needed? Exact data + effects\nObservation first, then proposals",
|
||||
"pos": [
|
||||
60,
|
||||
550
|
||||
],
|
||||
"size": [
|
||||
680,
|
||||
230
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "decision",
|
||||
"type": "security",
|
||||
"label": "Authorize or hold",
|
||||
"tag": "Human decision; roles named first",
|
||||
"sublabel": "Security: boundary; Quality: evidence\nPlatform & IT: enforcement + takeover\nOwning approver: exact permitted scope",
|
||||
"pos": [
|
||||
1000,
|
||||
340
|
||||
],
|
||||
"size": [
|
||||
720,
|
||||
290
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "execute",
|
||||
"type": "backend",
|
||||
"label": "Bounded execution",
|
||||
"tag": "Only within recorded authorization",
|
||||
"sublabel": "Exact-artifact checks + audit\nChanged boundary: reopen decision",
|
||||
"pos": [
|
||||
1980,
|
||||
100
|
||||
],
|
||||
"size": [
|
||||
680,
|
||||
230
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "stop",
|
||||
"type": "security",
|
||||
"label": "Independent stop + takeover",
|
||||
"tag": "Platform & IT + Security + owner",
|
||||
"sublabel": "Revoke mutations; preserve evidence\nRecover manually; requalify correction",
|
||||
"pos": [
|
||||
1980,
|
||||
650
|
||||
],
|
||||
"size": [
|
||||
680,
|
||||
230
|
||||
],
|
||||
"icon": "none"
|
||||
},
|
||||
{
|
||||
"id": "hold",
|
||||
"type": "external",
|
||||
"label": "Hold / return to Stage 01",
|
||||
"tag": "Missing authority or readiness",
|
||||
"sublabel": "Fix gaps, narrow scope or stay here\nNo automatic progression",
|
||||
"pos": [
|
||||
1000,
|
||||
960
|
||||
],
|
||||
"size": [
|
||||
720,
|
||||
230
|
||||
],
|
||||
"icon": "none"
|
||||
}
|
||||
],
|
||||
"connections": [
|
||||
{
|
||||
"id": "proven-case",
|
||||
"from": "proven",
|
||||
"to": "case",
|
||||
"label": "Need / limits",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"labelAt": [
|
||||
410,
|
||||
440
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "case-decision",
|
||||
"from": "case",
|
||||
"to": "decision",
|
||||
"label": "Proposal",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
860,
|
||||
665
|
||||
],
|
||||
[
|
||||
860,
|
||||
485
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
860,
|
||||
650
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decision-execute",
|
||||
"from": "decision",
|
||||
"to": "execute",
|
||||
"label": "Authorized",
|
||||
"fromSide": "right",
|
||||
"toSide": "left",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "default",
|
||||
"via": [
|
||||
[
|
||||
1850,
|
||||
485
|
||||
],
|
||||
[
|
||||
1850,
|
||||
215
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1840,
|
||||
200
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "execute-stop",
|
||||
"from": "execute",
|
||||
"to": "stop",
|
||||
"label": "Harm / stop",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
2320,
|
||||
500
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "decision-hold",
|
||||
"from": "decision",
|
||||
"to": "hold",
|
||||
"label": "Hold",
|
||||
"fromSide": "bottom",
|
||||
"toSide": "top",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"labelAt": [
|
||||
1360,
|
||||
810
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "stop-hold",
|
||||
"from": "stop",
|
||||
"to": "hold",
|
||||
"label": "Requalify",
|
||||
"fromSide": "left",
|
||||
"toSide": "right",
|
||||
"route": "straight",
|
||||
"width": 4,
|
||||
"variant": "security",
|
||||
"via": [
|
||||
[
|
||||
1840,
|
||||
765
|
||||
],
|
||||
[
|
||||
1840,
|
||||
1075
|
||||
]
|
||||
],
|
||||
"labelAt": [
|
||||
1840,
|
||||
1060
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -3,25 +3,49 @@
|
||||
"diagram_type": "architecture",
|
||||
"meta": {"title": "TO-BE: autonomous SDLC, human direction", "output": "static/diagrams/strategy-target-mobile/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}},
|
||||
"components": [
|
||||
{"id": "humans", "type": "backend", "label": "Humans", "sublabel": "Direct, guide and review", "pos": [20, 20], "size": [240, 80]},
|
||||
{"id": "agent", "type": "security", "label": "Autonomous agent", "sublabel": "Executes and governs SDLC", "pos": [20, 180], "size": [240, 80]},
|
||||
{"id": "scope", "type": "backend", "label": "Scope", "sublabel": "01", "pos": [20, 340], "size": [240, 80]},
|
||||
{"id": "architecture", "type": "backend", "label": "Architecture", "sublabel": "02", "pos": [20, 500], "size": [240, 80]},
|
||||
{"id": "ui-ux", "type": "backend", "label": "UI/UX", "sublabel": "03", "pos": [20, 660], "size": [240, 80]},
|
||||
{"id": "planning", "type": "backend", "label": "Planning", "sublabel": "04", "pos": [20, 820], "size": [240, 80]},
|
||||
{"id": "delivery", "type": "backend", "label": "Delivery", "sublabel": "05", "pos": [20, 980], "size": [240, 80]},
|
||||
{"id": "uat", "type": "backend", "label": "UAT", "sublabel": "06", "pos": [20, 1140], "size": [240, 80]},
|
||||
{"id": "releases", "type": "backend", "label": "Releases", "sublabel": "07", "pos": [20, 1300], "size": [240, 80]}
|
||||
{"id":"agent","type":"security","label":"Autonomous agent","sublabel":"Human Controlled","pos":[140,200],"size":[360,120]},
|
||||
{"id":"scope","type":"backend","label":"Scope","sublabel":"01","pos":[100,440],"size":[240,100]},
|
||||
{"id":"architecture","type":"backend","label":"Architecture","sublabel":"02","pos":[100,660],"size":[240,100]},
|
||||
{"id":"ui-ux","type":"backend","label":"UI/UX","sublabel":"03","pos":[100,880],"size":[240,100]},
|
||||
{"id":"planning","type":"backend","label":"Planning","sublabel":"04","pos":[100,1100],"size":[240,100]},
|
||||
{"id":"delivery","type":"backend","label":"Delivery","sublabel":"05","pos":[100,1320],"size":[240,100]},
|
||||
{"id":"uat","type":"backend","label":"UAT","sublabel":"06","pos":[100,1540],"size":[240,100]},
|
||||
{"id":"security","type":"backend","label":"Security","sublabel":"07","pos":[100,1760],"size":[240,100]},
|
||||
{"id":"releases","type":"backend","label":"Releases","sublabel":"08","pos":[100,1980],"size":[240,100]},
|
||||
{"id":"code-scope","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,440],"size":[240,100]},
|
||||
{"id":"code-architecture","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,660],"size":[240,100]},
|
||||
{"id":"code-ui-ux","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,880],"size":[240,100]},
|
||||
{"id":"code-planning","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,1100],"size":[240,100]},
|
||||
{"id":"code-delivery","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,1320],"size":[240,100]},
|
||||
{"id":"code-uat","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,1540],"size":[240,100]},
|
||||
{"id":"code-security","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,1760],"size":[240,100]},
|
||||
{"id":"code-releases","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[400,1980],"size":[240,100]}
|
||||
],
|
||||
"connections": [
|
||||
{"id": "human-direction", "from": "humans", "to": "agent", "label": "Guide", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "agent-lifecycle", "from": "agent", "to": "scope", "label": "Entire cycle", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-1", "from": "scope", "to": "architecture", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-2", "from": "architecture", "to": "ui-ux", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-3", "from": "ui-ux", "to": "planning", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-4", "from": "planning", "to": "delivery", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-5", "from": "delivery", "to": "uat", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-6", "from": "uat", "to": "releases", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-7", "from": "releases", "to": "scope", "label": "Repeat indefinitely", "fromSide": "right", "toSide": "right", "via": [[300, 1340], [300, 380]], "labelAt": [180, 1430]}
|
||||
|
||||
{"id":"govern-scope","from":"agent","to":"scope","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,490]]},
|
||||
{"id":"govern-architecture","from":"agent","to":"architecture","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,710]]},
|
||||
{"id":"govern-ui-ux","from":"agent","to":"ui-ux","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,930]]},
|
||||
{"id":"govern-planning","from":"agent","to":"planning","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,1150]]},
|
||||
{"id":"govern-delivery","from":"agent","to":"delivery","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,1370]]},
|
||||
{"id":"govern-uat","from":"agent","to":"uat","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,1590]]},
|
||||
{"id":"govern-security","from":"agent","to":"security","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,1810]]},
|
||||
{"id":"govern-releases","from":"agent","to":"releases","label":"","variant":"security","fromSide":"left","toSide":"left","via":[[60,260],[60,2030]]},
|
||||
{"id":"stage-1","from":"scope","to":"architecture","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-2","from":"architecture","to":"ui-ux","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-3","from":"ui-ux","to":"planning","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-4","from":"planning","to":"delivery","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-5","from":"delivery","to":"uat","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-6","from":"uat","to":"security","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-7","from":"security","to":"releases","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-8","from":"releases","to":"scope","label":"Repeat indefinitely","variant":"emphasis","fromSide":"bottom","toSide":"top","via":[[220,2140],[680,2140],[680,380],[220,380]],"labelAt":[440,2180]},
|
||||
{"id":"contribute-scope","from":"code-scope","to":"scope","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-architecture","from":"code-architecture","to":"architecture","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-ui-ux","from":"code-ui-ux","to":"ui-ux","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-planning","from":"code-planning","to":"planning","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-delivery","from":"code-delivery","to":"delivery","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-uat","from":"code-uat","to":"uat","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-security","from":"code-security","to":"security","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"},
|
||||
{"id":"contribute-releases","from":"code-releases","to":"releases","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right"}
|
||||
]
|
||||
}
|
||||
@@ -3,25 +3,49 @@
|
||||
"diagram_type": "architecture",
|
||||
"meta": {"title": "TO-BE: autonomous SDLC, human direction", "output": "static/diagrams/strategy-target/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}},
|
||||
"components": [
|
||||
{"id": "humans", "type": "backend", "label": "Humans", "sublabel": "Direct, guide and review", "pos": [40, 20], "size": [240, 80]},
|
||||
{"id": "agent", "type": "security", "label": "Autonomous agent", "sublabel": "Executes and governs SDLC", "pos": [360, 20], "size": [240, 80]},
|
||||
{"id": "scope", "type": "backend", "label": "Scope", "sublabel": "01", "pos": [40, 220], "size": [240, 80]},
|
||||
{"id": "architecture", "type": "backend", "label": "Architecture", "sublabel": "02", "pos": [360, 220], "size": [240, 80]},
|
||||
{"id": "ui-ux", "type": "backend", "label": "UI/UX", "sublabel": "03", "pos": [680, 220], "size": [240, 80]},
|
||||
{"id": "planning", "type": "backend", "label": "Planning", "sublabel": "04", "pos": [680, 380], "size": [240, 80]},
|
||||
{"id": "delivery", "type": "backend", "label": "Delivery", "sublabel": "05", "pos": [680, 540], "size": [240, 80]},
|
||||
{"id": "uat", "type": "backend", "label": "UAT", "sublabel": "06", "pos": [360, 540], "size": [240, 80]},
|
||||
{"id": "releases", "type": "backend", "label": "Releases", "sublabel": "07", "pos": [40, 540], "size": [240, 80]}
|
||||
{"id":"agent","type":"security","label":"Autonomous agent","sublabel":"Human Controlled","pos":[465,450],"size":[270,90]},
|
||||
{"id":"scope","type":"backend","label":"Scope","sublabel":"01","pos":[510,187.5],"size":[180,75]},
|
||||
{"id":"architecture","type":"backend","label":"Architecture","sublabel":"02","pos":[780,187.5],"size":[180,75]},
|
||||
{"id":"ui-ux","type":"backend","label":"UI/UX","sublabel":"03","pos":[780,457.5],"size":[180,75]},
|
||||
{"id":"planning","type":"backend","label":"Planning","sublabel":"04","pos":[780,727.5],"size":[180,75]},
|
||||
{"id":"delivery","type":"backend","label":"Delivery","sublabel":"05","pos":[510,727.5],"size":[180,75]},
|
||||
{"id":"uat","type":"backend","label":"UAT","sublabel":"06","pos":[240,727.5],"size":[180,75]},
|
||||
{"id":"security","type":"backend","label":"Security","sublabel":"07","pos":[240,457.5],"size":[180,75]},
|
||||
{"id":"releases","type":"backend","label":"Releases","sublabel":"08","pos":[240,187.5],"size":[180,75]},
|
||||
{"id":"code-scope","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[510,37.5],"size":[180,75]},
|
||||
{"id":"code-architecture","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[780,37.5],"size":[180,75]},
|
||||
{"id":"code-ui-ux","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[1005,457.5],"size":[180,75]},
|
||||
{"id":"code-planning","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[780,877.5],"size":[180,75]},
|
||||
{"id":"code-delivery","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[510,877.5],"size":[180,75]},
|
||||
{"id":"code-uat","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[240,877.5],"size":[180,75]},
|
||||
{"id":"code-security","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[15,457.5],"size":[180,75]},
|
||||
{"id":"code-releases","type":"frontend","label":"AI Agent","sublabel":"Human-controlled","pos":[240,37.5],"size":[180,75]}
|
||||
],
|
||||
"connections": [
|
||||
{"id": "human-direction", "from": "humans", "to": "agent", "label": "Guide", "fromSide": "right", "toSide": "left"},
|
||||
{"id": "agent-lifecycle", "from": "agent", "to": "scope", "label": "Entire cycle", "fromSide": "bottom", "toSide": "top", "via": [[480, 160], [160, 160]], "labelAt": [320, 145]},
|
||||
{"id": "stage-1", "from": "scope", "to": "architecture", "label": "Then", "fromSide": "right", "toSide": "left"},
|
||||
{"id": "stage-2", "from": "architecture", "to": "ui-ux", "label": "Then", "fromSide": "right", "toSide": "left"},
|
||||
{"id": "stage-3", "from": "ui-ux", "to": "planning", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-4", "from": "planning", "to": "delivery", "label": "Then", "fromSide": "bottom", "toSide": "top"},
|
||||
{"id": "stage-5", "from": "delivery", "to": "uat", "label": "Then", "fromSide": "left", "toSide": "right"},
|
||||
{"id": "stage-6", "from": "uat", "to": "releases", "label": "Then", "fromSide": "left", "toSide": "right"},
|
||||
{"id": "stage-7", "from": "releases", "to": "scope", "label": "Repeat indefinitely", "fromSide": "top", "toSide": "bottom", "via": [[160, 460], [160, 380]], "labelAt": [260, 420]}
|
||||
|
||||
{"id":"govern-scope","from":"agent","to":"scope","label":"","variant":"security","fromSide":"top","toSide":"bottom","route":"straight"},
|
||||
{"id":"govern-architecture","from":"agent","to":"architecture","label":"","variant":"security","fromSide":"top","toSide":"bottom","via":[[600,345],[870,345]]},
|
||||
{"id":"govern-ui-ux","from":"agent","to":"ui-ux","label":"","variant":"security","fromSide":"right","toSide":"left","route":"straight"},
|
||||
{"id":"govern-planning","from":"agent","to":"planning","label":"","variant":"security","fromSide":"bottom","toSide":"top","via":[[600,645],[870,645]]},
|
||||
{"id":"govern-delivery","from":"agent","to":"delivery","label":"","variant":"security","fromSide":"bottom","toSide":"top","route":"straight"},
|
||||
{"id":"govern-uat","from":"agent","to":"uat","label":"","variant":"security","fromSide":"bottom","toSide":"top","via":[[600,645],[330,645]]},
|
||||
{"id":"govern-security","from":"agent","to":"security","label":"","variant":"security","fromSide":"left","toSide":"right","route":"straight"},
|
||||
{"id":"govern-releases","from":"agent","to":"releases","label":"","variant":"security","fromSide":"top","toSide":"bottom","via":[[600,345],[330,345]]},
|
||||
{"id":"stage-1","from":"scope","to":"architecture","label":"Then","variant":"emphasis","fromSide":"right","toSide":"left"},
|
||||
{"id":"stage-2","from":"architecture","to":"ui-ux","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-3","from":"ui-ux","to":"planning","label":"Then","variant":"emphasis","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"stage-4","from":"planning","to":"delivery","label":"Then","variant":"emphasis","fromSide":"left","toSide":"right"},
|
||||
{"id":"stage-5","from":"delivery","to":"uat","label":"Then","variant":"emphasis","fromSide":"left","toSide":"right"},
|
||||
{"id":"stage-6","from":"uat","to":"security","label":"Then","variant":"emphasis","fromSide":"top","toSide":"bottom"},
|
||||
{"id":"stage-7","from":"security","to":"releases","label":"Then","variant":"emphasis","fromSide":"top","toSide":"bottom"},
|
||||
{"id":"stage-8","from":"releases","to":"scope","label":"Repeat indefinitely","variant":"emphasis","fromSide":"right","toSide":"left","labelAt":[465,170]},
|
||||
{"id":"contribute-scope","from":"code-scope","to":"scope","label":"Contribute","variant":"dashed","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"contribute-architecture","from":"code-architecture","to":"architecture","label":"Contribute","variant":"dashed","fromSide":"bottom","toSide":"top"},
|
||||
{"id":"contribute-ui-ux","from":"code-ui-ux","to":"ui-ux","label":"Contribute","variant":"dashed","fromSide":"left","toSide":"right","labelAt":[990,570]},
|
||||
{"id":"contribute-planning","from":"code-planning","to":"planning","label":"Contribute","variant":"dashed","fromSide":"top","toSide":"bottom"},
|
||||
{"id":"contribute-delivery","from":"code-delivery","to":"delivery","label":"Contribute","variant":"dashed","fromSide":"top","toSide":"bottom"},
|
||||
{"id":"contribute-uat","from":"code-uat","to":"uat","label":"Contribute","variant":"dashed","fromSide":"top","toSide":"bottom"},
|
||||
{"id":"contribute-security","from":"code-security","to":"security","label":"Contribute","variant":"dashed","fromSide":"right","toSide":"left","labelAt":[220,570]},
|
||||
{"id":"contribute-releases","from":"code-releases","to":"releases","label":"Contribute","variant":"dashed","fromSide":"bottom","toSide":"top"}
|
||||
]
|
||||
}
|
||||
@@ -15,7 +15,7 @@ description: Author typed JSON diagrams and embed their local interactive viewer
|
||||
| Dataflow | Sources, processing and destinations |
|
||||
| Lifecycle | States and transitions |
|
||||
|
||||
The standalone viewer provides pan/zoom, node inspection, search/focus, relationship tracing, light/dark themes, and an export menu. Motion is opt-in. The Organization views exercise architecture mode; other diagram types use the same build interface but do not yet have portal-specific examples. Browser-dependent exports such as video are not acceptance-tested by this integration.
|
||||
The standalone viewer provides pan/zoom, node inspection, search/focus, relationship tracing, light/dark themes, and an export menu. Motion is opt-in. The Organization views exercise architecture mode; Roadmap uses native Workflow v2 with a horizontal desktop path and the same stages stacked on mobile. Other diagram types use the same build interface but do not yet have portal-specific examples. Browser-dependent exports such as video are not acceptance-tested by this integration.
|
||||
|
||||
## Author a diagram
|
||||
|
||||
@@ -23,6 +23,8 @@ Create `diagrams/<name>.<type>.json` using the matching schema and authoring gui
|
||||
|
||||
Set `meta.output` to `static/diagrams/<name>/index.html`. The build validates the typed source with the upstream showcase profile, renders locally, checks the artifact, and publishes the standalone HTML. Editable JSON stays in the repository; the portal does not publish source-download files.
|
||||
|
||||
Roadmap has a scoped multiline typography adapter in `scripts/roadmap-viewer.mjs`. Its two `.workflow.json` sources use the native v2 schema, one lane, `mainPath`, logical columns and native routes. The native renderer validates the schema and solves geometry; the adapter wraps the existing action/output/exit copy, removes the redundant lane frame and trims empty canvas. The final artifact then passes the upstream showcase composition checker. This path records source, adapter and final artifact hashes in private `.cache/archify/*.portal.json` receipts, not upstream `deliver` provenance. Keep the vendor unchanged and run the Roadmap browser check at 1440, 390 and 320 pixels after any copy or sizing change. Typography is embedded in the SVG so exports retain it.
|
||||
|
||||
```sh
|
||||
pnpm diagrams:build
|
||||
pnpm test
|
||||
|
||||
@@ -28,7 +28,10 @@ Include `title` and `description` frontmatter. Place each page in its owning sec
|
||||
| Contribution | `docs/contribution/` | `sidebars/contribution.ts` |
|
||||
| Portal maintenance and reference | `docs/core/` | `sidebars.ts` |
|
||||
|
||||
Keep these content roots disjoint. Preserve existing URLs when moving pages. Specific AI initiatives and organizational reporting lines remain subject to agreement.
|
||||
Keep these content roots disjoint. Preserve existing URLs unless a URL migration is explicitly approved; provide precise redirects for approved moves. Metric details live on individual canonical pages directly under Measurement, alongside shared collection safeguards and the synthetic example. Specific AI initiatives and organizational reporting lines remain subject to agreement.
|
||||
Every published documentation page must have a navigable sidebar entry. Nested references are welcome; hidden documentation is not. Linked category overviews count as entries, but an in-page anchor is not a separate document. Portal-maintenance pages keep their existing `/docs/` routes and dedicated sidebar, reachable from Contribution → Portal maintenance.
|
||||
|
||||
`pnpm verify:build` compares all Docusaurus-generated document IDs/routes with resolved sidebar trees (including linked category overviews), checks reachability from the navbar, rejects missing/duplicate entries and unclassified HTML routes, and checks every document’s local links and anchors. The inventory is written to `.cache/sidebar-coverage.json`. Only the homepage, not-found page, search-results UI, legacy Strategy redirect, exact legacy measurement-contracts hash-aware redirect and standalone diagram viewers are non-document HTML routes; no documentation page is exempt. The metric migration manifest in `research/ai-adoption/measurement-migration.json` records old anchors, canonical IDs/URLs, implementation status and preserved-contract hashes.
|
||||
|
||||
## Validate the change
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: Structure
|
||||
pagination_next: structure/product
|
||||
description: Eldorado’s organizational operating model, departments, teams and responsibilities.
|
||||
---
|
||||
|
||||
@@ -26,90 +27,12 @@ Functional leaders translate company priorities into departmental plans. Team le
|
||||
|
||||
Product has **two teams** and Technology has **five teams**. Operations, Marketing, Finance & Accounting, and HR & Administration each have **one squad** covering their departmental workstreams. Each team belongs to one department, with its own leadership and responsibilities. The departments collaborate on delivery without sharing team ownership.
|
||||
|
||||
### Product
|
||||
|
||||
**Purpose:** improve the buyer and seller experience and turn marketplace opportunities into valuable product capabilities.
|
||||
|
||||
| Team | Responsibilities |
|
||||
| --- | --- |
|
||||
| Product Management | Product strategy, roadmaps, priorities and outcome measurement across discovery, categories, orders, seller tools, payments and operational workflows. |
|
||||
| Product Design | User research, interaction design, design consistency and accessible buyer and seller experiences. |
|
||||
|
||||
Product Management owns what to improve and why. Product Design shapes the experience. Both work with Technology teams while remaining within Product.
|
||||
|
||||
### Technology
|
||||
|
||||
**Purpose:** build and operate a secure, reliable marketplace and improve the effectiveness of engineering.
|
||||
|
||||
| Team | Responsibilities |
|
||||
| --- | --- |
|
||||
| Product Engineering | Build and maintain marketplace capabilities, including search, orders, seller tools, checkout, wallet and operational tooling. |
|
||||
| Platform & IT | Platform services, delivery infrastructure, observability, reliability, performance, internal systems, employee devices and identity administration. |
|
||||
| Architecture & Security | Technical standards, system design, security architecture and secure engineering practices. |
|
||||
| Quality Engineering | Test strategy, automation, release quality and defect prevention. |
|
||||
| Data & AI | Analytics, experimentation, ranking, recommendations, marketplace ML and safe AI-assisted engineering workflows. |
|
||||
|
||||
The CTO owns technology direction. The Head of Engineering leads engineering delivery through Group Engineering Managers and Engineering Managers. The AI Architect coordinates AI enablement within Data & AI, working with Architecture & Security and the other Technology teams. These are leadership roles within the five-team structure, not additional teams.
|
||||
|
||||
### Operations
|
||||
|
||||
**Purpose:** keep marketplace trading dependable and resolve customer issues fairly and efficiently.
|
||||
|
||||
**Operations Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Customer Support | Buyer and seller assistance, knowledge management, self-service and support workflow automation. |
|
||||
| Trust & Resolution | Disputes, appeals, refunds, warranties, chargebacks and complex customer cases. |
|
||||
| Risk & Fraud | Transaction and account risk, fraud prevention, investigations and operational controls. |
|
||||
| Operational Quality | Independent case reviews, quality standards, calibration, service accuracy and improvement tracking across operational teams. |
|
||||
|
||||
The COO coordinates Operations. Team leads manage specialists and daily service delivery. Operational Quality reports directly to the COO and reviews quality across teams.
|
||||
|
||||
### Marketing
|
||||
|
||||
**Purpose:** attract and retain customers, build the Eldorado brand and grow marketplace demand.
|
||||
|
||||
**Marketing Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Brand & Community | Brand positioning, campaigns, organic social, community and brand partnerships. |
|
||||
| Creative | Campaign concepts, visual assets and performance creative. |
|
||||
| SEO | Organic discovery, search visibility and content performance. |
|
||||
| PPC & Affiliate | Paid acquisition, affiliate channels and return on marketing investment. |
|
||||
| Influencer | Creator relationships, influencer programs and campaign delivery. |
|
||||
| CRM | Customer lifecycle communication, retention, reactivation and campaign personalization. |
|
||||
|
||||
The CMO coordinates Marketing. The Brand Team Lead owns Brand & Community, with shared support from Creative and the other marketing workstreams.
|
||||
|
||||
### Finance & Accounting
|
||||
|
||||
**Purpose:** maintain financial control, support business decisions and keep marketplace money flows dependable.
|
||||
|
||||
**Finance & Accounting Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Financial Planning & Analysis | Budgets, forecasts, profitability, management reporting and investment analysis. |
|
||||
| Accounting, Tax & Controls | Accounting, financial reporting, tax, audit coordination and internal controls. |
|
||||
| Treasury & Payment Operations | Cash management, reconciliation, payout oversight, payment-provider coordination and financial risk. |
|
||||
|
||||
The CFO coordinates Finance & Accounting and works with executive leadership on business performance. Finance, Operations and Product share responsibility for effective payment and withdrawal processes, each within its own area of expertise.
|
||||
|
||||
### HR & Administration
|
||||
|
||||
**Purpose:** help teams attract, develop and retain people and provide an effective working environment.
|
||||
|
||||
**People & Administration Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Talent Acquisition | Recruitment, candidate experience, hiring coordination and workforce demand support. |
|
||||
| People Operations | Employee onboarding, development, performance processes, policies and employee experience. |
|
||||
| Office & Administration | Workplace services, office operations and administrative coordination. |
|
||||
|
||||
HR partners with department leaders on team capacity and development. People Operations works with Platform & IT on employee onboarding, role changes and offboarding.
|
||||
- <span id="product">[Product](./structure/product.mdx)</span>
|
||||
- <span id="technology">[Technology](./structure/technology.mdx)</span>
|
||||
- <span id="operations">[Operations](./structure/operations.mdx)</span>
|
||||
- <span id="marketing">[Marketing](./structure/marketing.mdx)</span>
|
||||
- <span id="finance--accounting">[Finance & Accounting](./structure/finance-accounting.mdx)</span>
|
||||
- <span id="hr--administration">[HR & Administration](./structure/hr-administration.mdx)</span>
|
||||
|
||||
## Related pages
|
||||
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
---
|
||||
title: Finance & Accounting
|
||||
pagination_prev: structure/marketing
|
||||
pagination_next: structure/hr-administration
|
||||
description: Finance & Accounting purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** maintain financial control, support business decisions and keep marketplace money flows dependable.
|
||||
|
||||
**Finance & Accounting Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Financial Planning & Analysis | Budgets, forecasts, profitability, management reporting and investment analysis. |
|
||||
| Accounting, Tax & Controls | Accounting, financial reporting, tax, audit coordination and internal controls. |
|
||||
| Treasury & Payment Operations | Cash management, reconciliation, payout oversight, payment-provider coordination and financial risk. |
|
||||
|
||||
The CFO coordinates Finance & Accounting and works with executive leadership on business performance. Finance, Operations and Product share responsibility for effective payment and withdrawal processes, each within its own area of expertise.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,20 @@
|
||||
---
|
||||
title: HR & Administration
|
||||
pagination_prev: structure/finance-accounting
|
||||
pagination_next: collaboration
|
||||
description: HR & Administration purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** help teams attract, develop and retain people and provide an effective working environment.
|
||||
|
||||
**People & Administration Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Talent Acquisition | Recruitment, candidate experience, hiring coordination and workforce demand support. |
|
||||
| People Operations | Employee onboarding, development, performance processes, policies and employee experience. |
|
||||
| Office & Administration | Workplace services, office operations and administrative coordination. |
|
||||
|
||||
HR partners with department leaders on team capacity and development. People Operations works with Platform & IT on employee onboarding, role changes and offboarding.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,23 @@
|
||||
---
|
||||
title: Marketing
|
||||
pagination_prev: structure/operations
|
||||
pagination_next: structure/finance-accounting
|
||||
description: Marketing purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** attract and retain customers, build the Eldorado brand and grow marketplace demand.
|
||||
|
||||
**Marketing Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Brand & Community | Brand positioning, campaigns, organic social, community and brand partnerships. |
|
||||
| Creative | Campaign concepts, visual assets and performance creative. |
|
||||
| SEO | Organic discovery, search visibility and content performance. |
|
||||
| PPC & Affiliate | Paid acquisition, affiliate channels and return on marketing investment. |
|
||||
| Influencer | Creator relationships, influencer programs and campaign delivery. |
|
||||
| CRM | Customer lifecycle communication, retention, reactivation and campaign personalization. |
|
||||
|
||||
The CMO coordinates Marketing. The Brand Team Lead owns Brand & Community, with shared support from Creative and the other marketing workstreams.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,21 @@
|
||||
---
|
||||
title: Operations
|
||||
pagination_prev: structure/technology
|
||||
pagination_next: structure/marketing
|
||||
description: Operations purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** keep marketplace trading dependable and resolve customer issues fairly and efficiently.
|
||||
|
||||
**Operations Squad** delivers the department’s responsibilities across the following workstreams.
|
||||
|
||||
| Workstream | Responsibilities |
|
||||
| --- | --- |
|
||||
| Customer Support | Buyer and seller assistance, knowledge management, self-service and support workflow automation. |
|
||||
| Trust & Resolution | Disputes, appeals, refunds, warranties, chargebacks and complex customer cases. |
|
||||
| Risk & Fraud | Transaction and account risk, fraud prevention, investigations and operational controls. |
|
||||
| Operational Quality | Independent case reviews, quality standards, calibration, service accuracy and improvement tracking across operational teams. |
|
||||
|
||||
The COO coordinates Operations. Team leads manage specialists and daily service delivery. Operational Quality reports directly to the COO and reviews quality across teams.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,17 @@
|
||||
---
|
||||
title: Product
|
||||
pagination_prev: structure
|
||||
pagination_next: structure/technology
|
||||
description: Product purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** improve the buyer and seller experience and turn marketplace opportunities into valuable product capabilities.
|
||||
|
||||
| Team | Responsibilities |
|
||||
| --- | --- |
|
||||
| Product Management | Product strategy, roadmaps, priorities and outcome measurement across discovery, categories, orders, seller tools, payments and operational workflows. |
|
||||
| Product Design | User research, interaction design, design consistency and accessible buyer and seller experiences. |
|
||||
|
||||
Product Management owns what to improve and why. Product Design shapes the experience. Both work with Technology teams while remaining within Product.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,20 @@
|
||||
---
|
||||
title: Technology
|
||||
pagination_prev: structure/product
|
||||
pagination_next: structure/operations
|
||||
description: Technology purpose, teams and responsibilities in Eldorado’s operating model.
|
||||
---
|
||||
|
||||
**Purpose:** build and operate a secure, reliable marketplace and improve the effectiveness of engineering.
|
||||
|
||||
| Team | Responsibilities |
|
||||
| --- | --- |
|
||||
| Product Engineering | Build and maintain marketplace capabilities, including search, orders, seller tools, checkout, wallet and operational tooling. |
|
||||
| Platform & IT | Platform services, delivery infrastructure, observability, reliability, performance, internal systems, employee devices and identity administration. |
|
||||
| Architecture & Security | Technical standards, system design, security architecture and secure engineering practices. |
|
||||
| Quality Engineering | Test strategy, automation, release quality and defect prevention. |
|
||||
| Data & AI | Analytics, experimentation, ranking, recommendations, marketplace ML and safe AI-assisted engineering workflows. |
|
||||
|
||||
The CTO owns technology direction. The Head of Engineering leads engineering delivery through Group Engineering Managers and Engineering Managers. The AI Architect coordinates AI enablement within Data & AI, working with Architecture & Security and the other Technology teams. These are leadership roles within the five-team structure, not additional teams.
|
||||
|
||||
[Return to Structure overview](../structure.mdx)
|
||||
@@ -0,0 +1,66 @@
|
||||
---
|
||||
id: baseline
|
||||
title: Baseline
|
||||
sidebar_label: Baseline
|
||||
description: Understand a workflow, select relevant candidate metrics and establish feasible starting evidence for later comparison.
|
||||
pagination_prev: measurement/index
|
||||
pagination_next: skills-governance
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
Establish a starting position for one workflow before choosing an intervention in months 1–2 of the [6 Months Roadmap](./six-months-roadmap.mdx). Baseline current uneven AI-assisted practice, not an assumed no-AI organization. This is not a mandatory company-wide baseline of every metric in the [Measurement registry](./measurement/index.mdx). The [EXP-01 packet](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) assembles a practical comparison and budget. Departmental role names below are proposed functions to map with the partner team, not verified company appointments.
|
||||
|
||||
<ArchifyDiagram name="strategy-baseline" title="From current workflow through relevant selection and feasible evidence to a starting position and later comparison" story />
|
||||
|
||||
**Target operating model — no actual baseline values or approved thresholds are established here.** Missing evidence remains an explicit gap, not an invented starting value.
|
||||
|
||||
## Delivery example: know what must improve
|
||||
|
||||
In the [illustrative Delivery workflow](./stage-01-skills-adoption.mdx), Product Engineering maps a bounded code change through regression tests, independent review and existing release controls. Suppose the concern is repeated rework because regression evidence is incomplete: first verify the cause from actual changes, rather than assuming a skill will fix it.
|
||||
|
||||
Consider accepted-task outcomes, escaped-quality follow-up and review/rework inputs to cost if their contracts fit. Select only evidence that can inform that concern; deployment frequency need not help. The output is a workflow map and comparison record, not a pass/fail score. The owning team's designated workflow owner confirms scope with the independent Quality Engineering reviewer; unresolved source or acceptance gaps limit later conclusions, not authorize a pilot.
|
||||
|
||||
## Understand the current workflow
|
||||
|
||||
Describe the task, team or service, intended outcome, current tools, handoffs, controls and known friction. Bound what is in and out of scope. For Delivery, start with codebase structure and existing principles, system-logic sources, tests, builds and packaging, then deployments. Record current practice, including any existing AI use; do not label it “no-skill” unless that is true.
|
||||
|
||||
## Select relevant metrics, with reasons
|
||||
|
||||
Start with **Workflow effectiveness**: select relevant current-workflow outcomes before standardized skills adoption—accepted work, delivery time, failures/rework, cost, human effort/experience or business acceptance where the contracts apply. Choose the registry entries that answer this workflow's questions. Record why each selected metric applies, what decision it can inform, and why other candidates are irrelevant or deferred. There is no required universal subset. A service-level DORA metric, a qualification test and a people survey have different populations; they are not interchangeable.
|
||||
|
||||
Keep **Skills effectiveness & health** separate. If no applicable skills exist, selection, bundle, adoption and review measures may be N/A, not zero; they are not prerequisites for baselining current work. If skills already exist, record that starting context and qualify named revisions separately. Do not mix sandbox skill evaluations into validated workflow task success or live policy-effect rates.
|
||||
|
||||
Agree what counts as a started task, independent acceptance and completed follow-up before counting outcomes. Freeze eligibility and acceptance rules and verify event joins. Select a complete comparable workflow cycle and a predeclared precision/sample requirement appropriate to the decision. Do not select a convenient end date after seeing results. Where those requirements cannot be met, record the resulting evidence limitation.
|
||||
|
||||
## Agree feasible evidence
|
||||
|
||||
Confirm collection feasibility, period, sources, owner, independent reviewer, access, lawful basis, privacy and retention before collecting. Use the [shared safeguards](./measurement/collection-and-safeguards.mdx) and each selected contract's input requirements. Proposed owner/cadence entries are not already assigned responsibilities.
|
||||
|
||||
Start with a controlled worksheet or export if automation is unavailable. Join task IDs to acceptance records, PR/commit IDs, CI results and later defects where relevant; test source coverage and permissions. Repository and CI evidence support verification, but a green build alone is not task acceptance. Record exact skill revisions and client/model configurations when present; keep missing versions unknown.
|
||||
|
||||
## Record the starting position
|
||||
|
||||
Collect prospective current-practice evidence over the agreed period. Record actual starting values only when supported by traceable evidence. Include units, population, observation period, counts, exclusions, source coverage, calculation version, uncertainty and limitations. Zero denominators mean “not available,” not zero performance.
|
||||
|
||||
For each selected metric, keep one of these explicit records:
|
||||
|
||||
- **Available:** evidenced starting value, source links, calculation, owner and limits.
|
||||
- **Unavailable:** missing input or permission, affected comparison, responsible owner and proposed next action or review point. Never fill the gap with the synthetic example or an assumed industry value.
|
||||
|
||||
Record deferred and non-applicable candidates separately from selected-but-unavailable metrics. This page is the recording method, not an Eldorado baseline report or a set of approved targets.
|
||||
|
||||
## Keep later evaluation comparable
|
||||
|
||||
Retain task class, service, skill, client/model configuration and concurrent changes. In [Adoption](./skills-adoption.mdx), use the same agreed eligibility, acceptance and observation rules; in [Maintenance](./skills-maintenance.mdx), record any changes and breaks in comparability rather than silently replacing the starting position.
|
||||
|
||||
A matched or randomized comparison may be used when practical and ethical. Label observational trends as descriptive, not causal ROI; report confounding, selection and uncertainty. Missing or small samples limit conclusions. Baseline values describe current practice; they do not establish acceptable risk or authorize expansion.
|
||||
|
||||
**Next:** [Govern skill ownership and authority →](./skills-governance.mdx)
|
||||
|
||||
Carry the map, selected definitions and evidence limits into candidate design. Return here from [Adoption](./skills-adoption.mdx) when scope changes, or from [Maintenance](./skills-maintenance.mdx) when the current workflow no longer matches the comparison. See the [whole Stage 01 journey](./stage-01-skills-adoption.mdx).
|
||||
|
||||
</div>
|
||||
@@ -1,54 +0,0 @@
|
||||
---
|
||||
id: index
|
||||
title: AI adoption strategy
|
||||
description: An autonomous SDLC cycle directed, guided and reviewed by humans, supported by governed skills.
|
||||
slug: /
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
|
||||
## Autonomous SDLC, human direction
|
||||
|
||||
<ArchifyDiagram name="strategy-target" title="Autonomous agent executes and governs the SDLC; humans direct, guide and review" story />
|
||||
|
||||
An autonomous agent executes and governs the SDLC. Humans direct, guide and review the work throughout the cycle.
|
||||
|
||||
**Scope → Architecture → UI/UX → Planning → Delivery → UAT → Releases → Scope**
|
||||
|
||||
Releases returns to Scope and the cycle repeats indefinitely. Governed skills and measured outcomes support the path toward this target; they are not a substitute for it.
|
||||
|
||||
<details>
|
||||
<summary>Strategy rationale and reading map</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
### Govern skills first, expand authority only with evidence
|
||||
|
||||
Eldorado's target is to make AI-assisted work dependable across the organization: useful guidance, clear human ownership, controlled execution and measurable outcomes. The first investment is a governed skills system, not an autonomous replacement for the organization. A skill packages reusable working knowledge, prerequisites and verification steps. It helps an agent perform a task; it does not grant permission or guarantee that the work is correct.
|
||||
|
||||
The target combines an autonomous agent executing and governing the SDLC with humans directing, guiding and reviewing it. Developer choice on local laptops remains a supporting option: Copilot, Claude Code and Cline can receive reviewed portable skill content through qualified adapters. Repository, CI and release controls support execution; detailed approval policies remain implementation decisions, not new roles established by this strategy.
|
||||
|
||||
The strategy describes the intended operating model and the evidence required to introduce it. It does not establish that these controls are installed, that every client is supported, or that AI has improved Eldorado's performance. The current reference is the documented six-department organization. Rollout begins by validating actual clients, responsibilities, data boundaries and available evidence.
|
||||
|
||||
Success means accepted outcomes with maintained quality, controlled risk and understood total cost. Faster activity without reliable outcomes is not success. More skill invocations, generated lines or tool subscriptions are not productivity targets. People remain accountable for product, customer, financial and personnel decisions.
|
||||
|
||||
## Navigate the strategy
|
||||
|
||||
- [Target operating model](./target-operating-model.mdx) — The autonomous SDLC cycle, with human direction, guidance and review.
|
||||
- [Skills governance](./skills-governance.mdx) — Contract, lifecycle, decision rights, adapters, locking, exceptions.
|
||||
- [Skills quality](./skills-quality.mdx) — Risk tiers, independent evaluation, repeated trials, adversarial conformance.
|
||||
- [Skills adoption](./skills-adoption.mdx) — Workflow-led coaching, client choice, feedback, manual path.
|
||||
- [Measurement](./measurement.mdx) — Full KPI contracts, minimal events, illustrative calculations, privacy and limits.
|
||||
- [Skills maintenance](./skills-maintenance.mdx) — Review, drift, deprecation, rollback and incident handling.
|
||||
- [Roadmap](./roadmap.mdx) — Evidence-gated phases, no promised dates or budgets.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Explore the autonomous SDLC cycle →](./target-operating-model.mdx)
|
||||
|
||||
</div>
|
||||
@@ -1,385 +0,0 @@
|
||||
---
|
||||
id: measurement
|
||||
title: Measurement
|
||||
description: Full KPI contracts, minimal events, illustrative calculations, privacy and limits.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
|
||||
## Is AI-assisted work worth continuing?
|
||||
|
||||
Judge accepted outcomes alongside quality, delivery flow, risk, cost and human experience. Validate source coverage before calculating; missing evidence is unknown, not success.
|
||||
|
||||
<ArchifyDiagram name="strategy-measurement" title="Collect evidence, validate it, calculate balanced measures and decide" story />
|
||||
|
||||
**Illustrative only:** 1 accepted task ÷ 4 matured starts × 100 = **25%** confirmed success. One unresolved task stays in the denominator; known-outcome coverage is **75%**. These are synthetic data, not Eldorado results.
|
||||
|
||||
- **16 contracts:** exact definitions below; 9 prototype calculations, 7 explicitly unimplemented metrics.
|
||||
- **Balanced evidence:** no productivity rankings, composite score or causal ROI claim.
|
||||
- **Privacy first:** no raw prompts or code by default; protect small cohorts and agree retention before collection.
|
||||
|
||||
<details>
|
||||
<summary>Collection, baseline, event and privacy contracts</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
### Decide what counts before counting
|
||||
|
||||
Use the metric contracts below for exact definitions. Every report states its eligible population, observation window, numerator and denominator or distribution sample count, source coverage, exclusions and calculation version. Zero denominators return “not available.” Missing telemetry is unknown, not inactivity, compliance or success. Examples are explicitly synthetic and illustrative.
|
||||
|
||||
Begin with task acceptance, repository, CI, deployment and incident systems because they can independently establish outcomes. Add catalog/version inventory and task-level declarations. Client telemetry is supplementary and version-dependent; enabling rich tool details may collect sensitive commands and identifiers. Do not enable it merely to count skills. A normalized adapter may report approved skill identifiers without forwarding raw arguments.
|
||||
|
||||
Validated success uses all eligible initiated tasks whose predeclared observation window has matured. Failed and abandoned tasks remain nonsuccess. Unresolved or unobserved outcomes remain in the denominator, with known-outcome coverage shown alongside the conservative confirmed-success share. They are not relabeled as observed failure. A task cancelled before start is excluded; cancellation after start remains visible. Count a task once across retries and multiple skills. For timeliness, also show unfinished work and age; accepted-only lead-time distributions have survivorship limitations.
|
||||
|
||||
Track all five service-level DORA measures: commit-to-production lead time, deployment frequency, change fail rate, failed deployment recovery time and deployment rework rate. Do not substitute PR-open-to-merge time or all-incident MTTR. Pair them with matured escaped-quality rates, policy effects, total cost per accepted outcome, support coverage, adoption, human experience and catalog maintenance. Keep customer/business outcomes linked to their departmental hypotheses; do not infer conversion, trust or revenue improvement from delivery telemetry.
|
||||
|
||||
### Baseline and interpretation
|
||||
|
||||
Before a pilot, freeze eligibility and acceptance rules and verify event joins. Collect prospective no-skill/current-practice evidence over a complete comparable workflow cycle and until the preregistered precision/sample requirement is met. Do not select a convenient end date after seeing results. Retain task class, service, skill, client/model configuration and concurrent changes. A matched or randomized comparison may be used when practical and ethical; label observational trends as descriptive and report confounding, selection and uncertainty.
|
||||
|
||||
Elapsed time and human effort are different quantities. Parallel agents may reduce waiting while increasing review or compute. Include failed attempts and human review/rework in cost, do not multiply a multi-skill task's value across every invocation, and do not convert survey perceptions into proven time savings. Small or incomplete populations yield evidence limits, not an ROI percentage.
|
||||
|
||||
### Event and privacy contract
|
||||
|
||||
Use a versioned event envelope and required fields per event. Source producer plus event ID deduplicates transport retries. Conflicting payloads under the same key are quarantined. Attempts have distinct IDs under one task. Domain IDs deduplicate deployments, defects and approvals even when multiple feeds describe them. Late arrivals produce versioned aggregate corrections; never silently overwrite a published result. Preserve occurrence and receipt times, reject impossible orderings and flag clock skew. Missing terminal events remain unresolved until the work owner reconciles them.
|
||||
|
||||
Many-to-many task/attempt/skill/client associations preserve exact immutable versions. Unknown version stays null with a reason; never assign the latest revision retroactively. Client declarations, server facts and self-reports remain separately labeled. A skill-loaded event is evidence of loading only. The minimal prototype can operate without actor identity except where a lawful, necessary adoption denominator requires pseudonymous cohort membership.
|
||||
|
||||
The privacy starting proposal is 30 days for raw structured analytics events and 12 months for aggregated trends, subject to the responsible owners' review. Keep the approved catalog/approval record for the supported revision's lifetime and its required audit period, which must be decided separately. Incident evidence uses a restricted, explicitly authorized hold and deletion schedule, not an indefinite analytics exception. Suppress reports below five people and prohibit drill-down or overlapping cohort slices that reconstruct identities. Five is a proposed minimum, not a guarantee against re-identification. No raw prompts, code, screens, customer cases or secrets are collected by default. Publish the purpose, lawful collection basis, access/deletion route and retention before collecting. Consent is not presumed to be an appropriate employment-law basis.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>All 16 KPI contracts — formulas, populations, owners and limits</summary>
|
||||
|
||||
## Metric contracts
|
||||
|
||||
Each contract is a prospective collection design. No live source or observed baseline is established. N and D refer to the numerator and denominator shown for that metric.
|
||||
|
||||
### Validated task success
|
||||
|
||||
Confirmed independently accepted tasks as a share of all eligible initiated tasks in a matured start cohort; a conservative confirmed-success share, not observed failure rate.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct matured task_ids with valid independent task.accepted evidence by as_of |
|
||||
| Denominator | All distinct eligible task_ids started in window with started_at + preregistered task_observation_hours <= as_of |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Tasks in a preregistered workflow cohort, started in window; each counted once across retries, skills and clients. |
|
||||
| Exclusions | Cancelled before start, sandbox/evaluation tasks and out-of-scope workflows; never post-start failures/abandonments. |
|
||||
| Events and source | task.started; task.accepted; task.failed; task.abandoned; task.cancelled; work-management acceptance record |
|
||||
| Owner / cadence | Quality Engineering / Weekly pilot; monthly departmental outcome review |
|
||||
| Missing evidence | Unresolved/missing terminal outcomes remain in denominator with unknown count and known-outcome coverage; do not label them failed. Invalid/missing start excluded from calculation but flagged as orphan evidence. |
|
||||
| Gaming and limits | Split easy tasks or omit starts; reconcile starts to approved backlog and audit acceptance rubrics. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Maturation horizon is workflow-specific and must be approved; no automatic abandonment on timeout. |
|
||||
|
||||
|
||||
### Skill selection precision
|
||||
|
||||
Correct activations among activations on an independently labeled evaluation corpus.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | True-positive activations for the requested workflow |
|
||||
| Denominator | True-positive plus false-positive activations |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | All candidate/client labeled evaluation task-trials with known activation and relevance. |
|
||||
| Exclusions | Unlabeled/unknown activations excluded with coverage; no cherry-picked failed trials. |
|
||||
| Events and source | eval.selection; versioned labeled corpus and runner |
|
||||
| Owner / cadence | Data & AI / Each skill/client qualification |
|
||||
| Missing evidence | Unknown activation/relevance is unscorable; publish missing count and deny qualification if planned coverage incomplete. |
|
||||
| Gaming and limits | Choose easy labels or hide negative cases; freeze corpus and independently review labels. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Does not show execution success; precision depends on corpus prevalence. |
|
||||
|
||||
|
||||
### Skill selection recall
|
||||
|
||||
Relevant task-trials in which the intended skill activates.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | True-positive activations |
|
||||
| Denominator | True-positive plus false-negative task-trials |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Independently labeled relevant evaluation task-trials for a skill/client tuple. |
|
||||
| Exclusions | Irrelevant tasks; missing relevance or activation reported as unscorable, not negative. |
|
||||
| Events and source | eval.selection; versioned labeled corpus and runner |
|
||||
| Owner / cadence | Data & AI / Each skill/client qualification |
|
||||
| Missing evidence | Report evaluation coverage; null if no relevant labeled tasks. |
|
||||
| Gaming and limits | Overtrigger to maximize recall; always pair with precision and negative cases. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Loading the right skill is not adherence. |
|
||||
|
||||
|
||||
### Supported bundle coverage
|
||||
|
||||
Inventoried active installations with verified effective approved, supported and nonrevoked bundle/adapter tuple.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Eligible installation_ids with valid inventory evidence within approved freshness window and matching support matrix |
|
||||
| Denominator | All expected active installation_ids in the managed pilot inventory |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Active installation inventory frozen for report, including invisible/offline entries until authoritative offboarding. |
|
||||
| Exclusions | Verified decommissioned installations and nonpilot assets; lack of telemetry alone never excludes. |
|
||||
| Events and source | inventory.observed; catalog.published; catalog.revoked; device inventory |
|
||||
| Owner / cadence | Platform & IT / Weekly and at revocation |
|
||||
| Missing evidence | Unknown/stale versions count outside numerator, inside denominator. Show inventory discovery coverage versus eligible device roster; if roster unknown metric is provisional. |
|
||||
| Gaming and limits | Remove silent devices or trust declared versions; reconcile managed inventory and separately label attestation trust. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Even verified file digests do not prove a private model followed the content. |
|
||||
|
||||
|
||||
### Approved-workflow adoption
|
||||
|
||||
Eligible participants with at least one approved-skill workflow use; usefulness assessed separately through accepted outcomes and feedback.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct eligible pseudonymous participants with workflow-linked skill.used on approved revision |
|
||||
| Denominator | Distinct eligible participants in frozen invited cohort |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Consented or otherwise lawfully enrolled pilot cohort for the period; supported workflow available. |
|
||||
| Exclusions | Outside pilot and formally recorded leave before period; nonresponders remain eligible, not excluded. |
|
||||
| Events and source | skill.used; cohort.snapshot; optional qualified client adapter or declaration |
|
||||
| Owner / cadence | Data & AI / Monthly |
|
||||
| Missing evidence | Show observed lower bound and telemetry/response coverage; missing usage unknown rather than non-use. |
|
||||
| Gaming and limits | Invocation quotas and coercion; no target usage count, split server/client/self-report origins. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Self-report is not verified use; installation/loading is not use or benefit. Suppress small groups. |
|
||||
|
||||
|
||||
### Change lead time
|
||||
|
||||
Arithmetic mean commit-to-first-successful-production-deployment duration; also publish median/p90 and sample count.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum of elapsed hours from committed_at to first successful production deployment for each service+commit |
|
||||
| Denominator | Count of eligible service+commit pairs with valid mappings |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | hours/change |
|
||||
| Eligible population | Changes first successfully deployed to a service in reporting window; rollout retries collapse to same logical deployment. |
|
||||
| Exclusions | Nonproduction, duplicates, no-op deployment with no new commits; missing mappings shown as coverage loss. |
|
||||
| Events and source | change.committed; deployment.completed; VCS immutable commit timestamps and release manifest |
|
||||
| Owner / cadence | Platform & IT / Weekly per service |
|
||||
| Missing evidence | Missing commit mapping or negative/skewed duration excluded from numeric sample, reported explicitly; no zero substitution. |
|
||||
| Gaming and limits | Timestamp rewriting and cherry-picking fast work; lock change mapping and show undeployed backlog age. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Not PR cycle time, effort saved, or a complete view of unfinished changes. p90 uses nearest-rank sorted sample. |
|
||||
|
||||
|
||||
### Deployment frequency
|
||||
|
||||
Distinct successful logical production deployments per complete service-day of observation.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct service_id+deployment_id successful production deployments in window |
|
||||
| Denominator | Observed service-days in window |
|
||||
| Expression | N / D |
|
||||
| Aggregation | ratio |
|
||||
| Unit | deployments/service-day |
|
||||
| Eligible population | Declared production services and complete UTC observation days; report each service before pooled views. |
|
||||
| Exclusions | Test/staging, failed attempts without production effect, duplicate callbacks and retries of the same rollout. |
|
||||
| Events and source | deployment.completed; authoritative deployment service |
|
||||
| Owner / cadence | Platform & IT / Weekly per service |
|
||||
| Missing evidence | Missing feed periods not zero; report coverage and no unqualified overall rate when period incomplete. |
|
||||
| Gaming and limits | Split deployments without value; pair with success, rework and failure measures. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. More deployments alone do not establish better performance; affected unsuccessful changes remain in change-fail population. |
|
||||
|
||||
|
||||
### Change fail rate
|
||||
|
||||
Production deployment effects requiring unplanned remediation, rollback or hotfix, not solely outage declarations.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct matured production deployment_ids linked to qualifying immediate intervention |
|
||||
| Denominator | All distinct production deployment_ids that reached production in the matured deployment cohort |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Deployments with production effect during window and approved intervention follow-up horizon elapsed. |
|
||||
| Exclusions | Failed preproduction attempts, duplicate callbacks and no-effect retries; failures after production effect stay included. |
|
||||
| Events and source | deployment.completed; deployment.failed; incident.linked; release and incident records |
|
||||
| Owner / cadence | Quality Engineering / Weekly; finalized after horizon |
|
||||
| Missing evidence | Known failures / all eligible deployments is a lower bound where incident linkage incomplete; label provisional and report unknown links. |
|
||||
| Gaming and limits | Avoid incident links or relabel intervention planned; reconcile rollbacks/hotfixes independently. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Define immediate intervention and follow-up horizon before pilot; no universal incident-to-AI attribution. |
|
||||
|
||||
|
||||
### Failed deployment recovery time
|
||||
|
||||
Mean elapsed time from production deployment failure onset to service restoration, with median/p90 and unresolved count/age.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum of recovery_at minus failure_started_at in hours for recovered eligible deployment failures |
|
||||
| Denominator | Count of recovered eligible deployment failures with valid timestamps |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | hours/failure |
|
||||
| Eligible population | Production deployment failures beginning in window; latest verified restoration if a recovery is rescinded. |
|
||||
| Exclusions | Nondeployment incidents; invalid timestamp pairs reported missing, not treated as instantaneous recovery. |
|
||||
| Events and source | deployment.failed; service.restored; incident service |
|
||||
| Owner / cadence | Platform & IT / Weekly with unresolved failures |
|
||||
| Missing evidence | Unresolved failures reported separately and excluded only from recovered-duration distribution; prevent declaring improvement without their visibility. |
|
||||
| Gaming and limits | Premature recovery declarations or omit hard cases; require operational readback and carry unresolved ages. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Not all-incident MTTR; recovered-only sample has survivorship bias. p90 nearest rank. |
|
||||
|
||||
|
||||
### Deployment rework rate
|
||||
|
||||
Unplanned production deployment effects triggered by a production incident as a share of deployment effects.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct incident-linked deployment_ids classified unplanned remediation |
|
||||
| Denominator | All distinct production deployment_ids with production effect in window |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Production deployment effects in window with immutable planned/unplanned classification and incident linkage. |
|
||||
| Exclusions | Nonproduction, no-effect retries and duplicates; do not exclude unclassified changes silently. |
|
||||
| Events and source | deployment.completed; incident.linked; release intent classification |
|
||||
| Owner / cadence | Platform & IT / Weekly |
|
||||
| Missing evidence | Unknown classification stays denominator; observed numerator is lower bound until reconciliation; show classification coverage. |
|
||||
| Gaming and limits | Call hotfixes planned; freeze reason and independently reconcile incident/deployment links. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Distinct from failure rate: one failed deployment can lead to multiple separate rework deployments. |
|
||||
|
||||
|
||||
### Changes with escaped quality issues
|
||||
|
||||
Accepted changes with at least one confirmed post-acceptance defect during approved follow-up, split by severity.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct eligible change_ids with one or more linked confirmed defects in follow-up |
|
||||
| Denominator | Accepted change_ids with completed predeclared follow-up horizon |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Accepted changes in acceptance window whose follow-up is complete by as_of. |
|
||||
| Exclusions | Immature changes shown separately; duplicates/unconfirmed reports excluded but counted as pending triage. |
|
||||
| Events and source | change.accepted; defect.confirmed; defect tracking and acceptance evidence |
|
||||
| Owner / cadence | Quality Engineering / Monthly mature cohorts |
|
||||
| Missing evidence | Unknown linkage is a coverage warning; no fabricated clean outcome. Show absolute defect and severe incident counts as well. |
|
||||
| Gaming and limits | Shorten follow-up or downgrade severity; freeze horizon and rubric and independently sample defects. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Counts affected changes, not raw defects per change; no presumption defects are AI-caused. |
|
||||
|
||||
|
||||
### Confirmed policy effects
|
||||
|
||||
Eligible evaluated attempts with an actual confirmed prohibited effect; report attempts, blocked attempts and effects separately.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct attempt_ids with confirmed prohibited action effect |
|
||||
| Denominator | All evaluated eligible attempt_ids including failed and abandoned runs |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Governed skill trials or supported workflow attempts, reported separately for eval and live populations. |
|
||||
| Exclusions | Out-of-scope runs; detection gaps remain coverage issues, not exclusions from known initiated population. |
|
||||
| Events and source | attempt.started; policy.violation; gate.blocked; security audit and incident triage |
|
||||
| Owner / cadence | Architecture & Security / Immediate incident action; weekly aggregates |
|
||||
| Missing evidence | Unknown outcomes remain visible; zero detected effects never proves safety. Missing audits make rate provisional. |
|
||||
| Gaming and limits | Hide incidents or inflate harmless trials; absolute severity counts and fixed task mix accompany rate. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Blocked attempts are not actual effects; any critical effect blocks promotion regardless of aggregate rate. |
|
||||
|
||||
|
||||
### Cost per accepted outcome
|
||||
|
||||
Allocated total workflow cost including unsuccessful attempts, licenses, compute, tooling and human review/rework divided by accepted outcomes.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum allocated costs in one approved reporting currency for all tasks/attempts in matured start cohort |
|
||||
| Denominator | Distinct independently accepted tasks in same cohort |
|
||||
| Expression | N / D |
|
||||
| Aggregation | ratio |
|
||||
| Unit | currency/accepted outcome |
|
||||
| Eligible population | Matured eligible started-task cohort, with all attempt costs through as_of and allocated shared period costs. |
|
||||
| Exclusions | Unrelated projects and documented taxes/transfers outside chosen accounting basis; never failed/abandoned attempts. |
|
||||
| Events and source | cost.recorded; task.accepted; finance invoices, usage ledger, sampled effort with approved rates |
|
||||
| Owner / cadence | Finance & Accounting Squad / Monthly with late invoice restatement |
|
||||
| Missing evidence | Missing cost buckets produce partial estimate plus coverage, not a total. Mixed currency requires dated approved conversion; zero accepted outcomes = null with full cost shown. |
|
||||
| Gaming and limits | Count tokens only or hide labor/failures; reconcile invoice and allocation totals without double counting. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Allocation and sampled labor carry uncertainty; no ROI without independently measured business benefit. |
|
||||
|
||||
|
||||
### Verification confidence and cognitive load
|
||||
|
||||
Three separate anonymous 1–5 item distributions: confidence in verifying output, manageable workload, usefulness. Primary item: verification confidence mean; report full distributions and response rate.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum valid 1–5 verification-confidence responses, one per participant per survey wave |
|
||||
| Denominator | Count valid responses to that item |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | points (1–5) |
|
||||
| Eligible population | Invited eligible cohort at fixed survey wave; voluntary responses. |
|
||||
| Exclusions | Invalid/out-of-range answers and superseded duplicate submission; nonresponders stay in response-rate denominator. |
|
||||
| Events and source | survey.response; anonymous survey with single-use token and aggregate invitation count |
|
||||
| Owner / cadence | People & Administration Squad / After pilot workflow cycle; periodic follow-up |
|
||||
| Missing evidence | Report valid response count / invited count and item nonresponse; no imputation. Suppress people cohorts below five. |
|
||||
| Gaming and limits | Pressure to respond positively; no manager access to individual responses, avoid identifying free text. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Perception and selection bias; not measured time savings. No composite productivity index. |
|
||||
|
||||
|
||||
### Skills within substantive review window
|
||||
|
||||
Active approved skill revisions with an accountable owner and completed substantive review not past due.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct active approved skill revisions with current owner, review evidence and review_due_at >= as_of |
|
||||
| Denominator | All active approved skill revisions in catalog snapshot |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Approved revisions currently supported for use at as_of. |
|
||||
| Exclusions | Experimental and retired revisions; deprecated/revoked in-use counts reported independently, not hidden. |
|
||||
| Events and source | catalog.published; catalog.reviewed; catalog.deprecated; catalog.revoked; version inventory |
|
||||
| Owner / cadence | Data & AI / Monthly and each release |
|
||||
| Missing evidence | Missing owner/date/evidence outside numerator; show ownerless, deprecated-in-use and revoked-in-use absolute counts. |
|
||||
| Gaming and limits | Rubber-stamp review dates; require linked regression/security/usefulness evidence. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. A current review is not proof of effectiveness; consumer inventory may miss shadow copies. |
|
||||
|
||||
|
||||
### Workflow-specific business acceptance
|
||||
|
||||
Independently accepted domain outcomes against a predeclared business rubric, separate from technical completion.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Eligible completed-observation task_ids meeting the department-specific outcome rubric |
|
||||
| Denominator | All eligible initiated workflow task_ids with matured business-outcome horizon |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | One named departmental workflow and predeclared start cohort; never pool unlike rubrics. |
|
||||
| Exclusions | Cancelled-before-start and unrelated workflows; unsuccessful or abandoned eligible work remains. |
|
||||
| Events and source | task.started; business.accepted; departmental case/content/reconciliation/onboarding review record |
|
||||
| Owner / cadence | Product Management / Each pilot cycle with owning department |
|
||||
| Missing evidence | Unknown follow-up stays denominator with unresolved count; no claim actual business outcome changed without source evidence. |
|
||||
| Gaming and limits | Weaken rubric or count drafts as customer benefit; lock rubric and independently audit acceptance. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Domain owner signs acceptance: Operations service accuracy; Marketing claims/rights; Finance reconciliation accuracy; HR policy correctness; Product usability/value. Not revenue uplift. |
|
||||
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>Run the nine-metric synthetic prototype and inspect omissions</summary>
|
||||
|
||||
## Run the synthetic measurement example
|
||||
|
||||
**Executed synthetic example — not Eldorado results.** The bundled fixture produces 1 independently accepted task from 4 matured starts: 25% confirmed success. One unresolved task remains in that denominator; known-outcome coverage is 75%. Selection precision and recall are each 1 / 2 = 50%. Allocated synthetic cost is EUR 60 / 1 accepted outcome = EUR 60 per accepted outcome. These deliberately small samples demonstrate arithmetic and missingness, not a baseline, target or ROI claim.
|
||||
|
||||
From the private documentation checkout, run `node scripts/ai-kpi.mjs` and `node --test scripts/ai-kpi.test.mjs`. The fixture `scripts/fixtures/ai-kpi-synthetic.json` is labeled synthetic; every result carries the same label and calculation version. This prototype has no network collectors and does not enable employee telemetry.
|
||||
|
||||
The executable covers validated success, selection precision/recall, change fail and rework rates, escaped quality, policy effects, cost and human experience. Other catalog metrics remain contracts rather than implemented collectors; output lists the omissions. Snapshot inputs are simplified, pre-reconciled records, not a production ingestion system. Conflicting duplicates reject the calculation rather than silently choosing a value.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Use findings to maintain, quarantine or replace skills →](./skills-maintenance.mdx)
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
id: approved-workflow-adoption
|
||||
slug: /measurement/approved-workflow-adoption
|
||||
title: Approved-workflow adoption
|
||||
description: Definition, collection evidence and limitations for approved-workflow adoption.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Eligible participants with at least one approved-skill workflow use; usefulness assessed separately through accepted outcomes and feedback.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct eligible pseudonymous participants with workflow-linked skill.used on approved revision |
|
||||
| Denominator | Distinct eligible participants in frozen invited cohort |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Consented or otherwise lawfully enrolled pilot cohort for the period; supported workflow available. |
|
||||
| Exclusions | Outside pilot and formally recorded leave before period; nonresponders remain eligible, not excluded. |
|
||||
| Events and source | skill.used; cohort.snapshot; optional qualified client adapter or declaration |
|
||||
| Owner / cadence | Data & AI / Monthly |
|
||||
| Missing evidence | Show observed lower bound and telemetry/response coverage; missing usage unknown rather than non-use. |
|
||||
| Gaming and limits | Invocation quotas and coercion; no target usage count, split server/client/self-report origins. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Self-report is not verified use; installation/loading is not use or benefit. Suppress small groups. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
In [Stage 01](../stage-01-skills-adoption.mdx), authorization to test an experimental revision is not general approved status. This contract counts approved-revision use only; do not relabel experimental pilot use to raise its numerator. [Adoption](../skills-adoption.mdx) still evaluates that pilot through independent work outcomes and [Quality's fitness evidence](../skills-quality.mdx). Use this reach measure only where its approved-revision population applies.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: change-fail-rate
|
||||
slug: /measurement/change-fail-rate
|
||||
title: Change fail rate
|
||||
description: Definition, collection evidence and limitations for change fail rate.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Production deployment effects requiring unplanned remediation, rollback or hotfix, not solely outage declarations.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct matured production deployment_ids linked to qualifying immediate intervention |
|
||||
| Denominator | All distinct production deployment_ids that reached production in the matured deployment cohort |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Deployments with production effect during window and approved intervention follow-up horizon elapsed. |
|
||||
| Exclusions | Failed preproduction attempts, duplicate callbacks and no-effect retries; failures after production effect stay included. |
|
||||
| Events and source | deployment.completed; deployment.failed; incident.linked; release and incident records |
|
||||
| Owner / cadence | Quality Engineering / Weekly; finalized after horizon |
|
||||
| Missing evidence | Known failures / all eligible deployments is a lower bound where incident linkage incomplete; label provisional and report unknown links. |
|
||||
| Gaming and limits | Avoid incident links or relabel intervention planned; reconcile rollbacks/hotfixes independently. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Define immediate intervention and follow-up horizon before pilot; no universal incident-to-AI attribution. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: change-lead-time
|
||||
slug: /measurement/change-lead-time
|
||||
title: Change lead time
|
||||
description: Definition, collection evidence and limitations for change lead time.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Arithmetic mean commit-to-first-successful-production-deployment duration; also publish median/p90 and sample count.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum of elapsed hours from committed_at to first successful production deployment for each service+commit |
|
||||
| Denominator | Count of eligible service+commit pairs with valid mappings |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | hours/change |
|
||||
| Eligible population | Changes first successfully deployed to a service in reporting window; rollout retries collapse to same logical deployment. |
|
||||
| Exclusions | Nonproduction, duplicates, no-op deployment with no new commits; missing mappings shown as coverage loss. |
|
||||
| Events and source | change.committed; deployment.completed; VCS immutable commit timestamps and release manifest |
|
||||
| Owner / cadence | Platform & IT / Weekly per service |
|
||||
| Missing evidence | Missing commit mapping or negative/skewed duration excluded from numeric sample, reported explicitly; no zero substitution. |
|
||||
| Gaming and limits | Timestamp rewriting and cherry-picking fast work; lock change mapping and show undeployed backlog age. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Not PR cycle time, effort saved, or a complete view of unfinished changes. p90 uses nearest-rank sorted sample. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: changes-with-escaped-quality-issues
|
||||
slug: /measurement/changes-with-escaped-quality-issues
|
||||
title: Changes with escaped quality issues
|
||||
description: Definition, collection evidence and limitations for changes with escaped quality issues.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Accepted changes with at least one confirmed post-acceptance defect during approved follow-up, split by severity.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct eligible change_ids with one or more linked confirmed defects in follow-up |
|
||||
| Denominator | Accepted change_ids with completed predeclared follow-up horizon |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Accepted changes in acceptance window whose follow-up is complete by as_of. |
|
||||
| Exclusions | Immature changes shown separately; duplicates/unconfirmed reports excluded but counted as pending triage. |
|
||||
| Events and source | change.accepted; defect.confirmed; defect tracking and acceptance evidence |
|
||||
| Owner / cadence | Quality Engineering / Monthly mature cohorts |
|
||||
| Missing evidence | Unknown linkage is a coverage warning; no fabricated clean outcome. Show absolute defect and severe incident counts as well. |
|
||||
| Gaming and limits | Shorten follow-up or downgrade severity; freeze horizon and rubric and independently sample defects. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Counts affected changes, not raw defects per change; no presumption defects are AI-caused. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,44 @@
|
||||
---
|
||||
id: collection-and-safeguards
|
||||
slug: /measurement/collection-and-safeguards
|
||||
title: Collection and safeguards
|
||||
description: Shared interpretation rules, event contracts and privacy safeguards for selected metrics.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** Registry inclusion does not require use, collection or baselining. All owner and cadence entries are proposals to confirm for selected metrics, not assigned responsibilities or approved schedules.
|
||||
|
||||
{/* preserved:start */}
|
||||
Use these safeguards throughout the [Stage 01 journey](../stage-01-skills-adoption.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
### Decide what counts before counting
|
||||
|
||||
Use the [metric definitions](./index.mdx#metric-definitions) for exact definitions. Every report states its eligible population, observation window, numerator and denominator or distribution sample count, source coverage, exclusions and calculation version. Zero denominators return “not available.” Missing telemetry is unknown, not inactivity, compliance or success. Examples are explicitly synthetic and illustrative.
|
||||
|
||||
Begin with task acceptance, repository, CI, deployment and incident systems because they can independently establish outcomes. Add catalog/version inventory and task-level declarations. Client telemetry is supplementary and version-dependent; enabling rich tool details may collect sensitive commands and identifiers. Do not enable it merely to count skills. A normalized adapter may report approved skill identifiers without forwarding raw arguments.
|
||||
|
||||
Validated success uses all eligible initiated tasks whose predeclared observation window has matured. Failed and abandoned tasks remain nonsuccess. Unresolved or unobserved outcomes remain in the denominator, with known-outcome coverage shown alongside the conservative confirmed-success share. They are not relabeled as observed failure. A task cancelled before start is excluded; cancellation after start remains visible. Count a task once across retries and multiple skills. For timeliness, also show unfinished work and age; accepted-only lead-time distributions have survivorship limitations.
|
||||
|
||||
The registry includes five service-level DORA measures: commit-to-production lead time, deployment frequency, change fail rate, failed deployment recovery time and deployment rework rate. Select them only where applicable; do not substitute PR-open-to-merge time or all-incident MTTR. Where relevant, interpret them alongside selected quality, policy, cost, support, adoption, experience or maintenance evidence. Keep customer/business outcomes linked to their departmental hypotheses; do not infer conversion, trust or revenue improvement from delivery telemetry.
|
||||
|
||||
### Interpretation limits {#baseline-and-interpretation}
|
||||
|
||||
See [Baseline](../baseline.mdx) for selecting relevant metrics and establishing comparable current-practice evidence. Pilot application belongs to [Adoption](../skills-adoption.mdx); ongoing reporting belongs to [Maintenance](../skills-maintenance.mdx).
|
||||
|
||||
Elapsed time and human effort are different quantities. Parallel agents may reduce waiting while increasing review or compute. Include failed attempts and human review/rework in cost, do not multiply a multi-skill task's value across every invocation, and do not convert survey perceptions into proven time savings. Small or incomplete populations yield evidence limits, not an ROI percentage.
|
||||
|
||||
### Event and privacy contract
|
||||
|
||||
Use a versioned event envelope and required fields per event. Source producer plus event ID deduplicates transport retries. Conflicting payloads under the same key are quarantined. Attempts have distinct IDs under one task. Domain IDs deduplicate deployments, defects and approvals even when multiple feeds describe them. Late arrivals produce versioned aggregate corrections; never silently overwrite a published result. Preserve occurrence and receipt times, reject impossible orderings and flag clock skew. Missing terminal events remain unresolved until the work owner reconciles them.
|
||||
|
||||
Many-to-many task/attempt/skill/client associations preserve exact immutable versions. Unknown version stays null with a reason; never assign the latest revision retroactively. Client declarations, server facts and self-reports remain separately labeled. A skill-loaded event is evidence of loading only. The minimal prototype can operate without actor identity except where a lawful, necessary adoption denominator requires pseudonymous cohort membership.
|
||||
|
||||
The privacy starting proposal is 30 days for raw structured analytics events and 12 months for aggregated trends, subject to the responsible owners' review. Keep the approved catalog/approval record for the supported revision's lifetime and its required audit period, which must be decided separately. Incident evidence uses a restricted, explicitly authorized hold and deletion schedule, not an indefinite analytics exception. Suppress reports below five people and prohibit drill-down or overlapping cohort slices that reconstruct identities. Five is a proposed minimum, not a guarantee against re-identification. No raw prompts, code, screens, customer cases or secrets are collected by default. Publish the purpose, lawful collection basis, access/deletion route and retention before collecting. Consent is not presumed to be an appropriate employment-law basis.
|
||||
{/* preserved:end */}
|
||||
|
||||
Return to the [Skills Measurement index](./index.mdx) for every metric definition.
|
||||
|
||||
For the illustrative Delivery comparison, agree sources, permissions and independent acceptance before collection. Carry the population and gap record from [Baseline](../baseline.mdx) into [Adoption](../skills-adoption.mdx). Keep [Quality's qualification trials](../skills-quality.mdx) separate from live workflow starts; revised reports must preserve that boundary.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: confirmed-policy-effects
|
||||
slug: /measurement/confirmed-policy-effects
|
||||
title: Confirmed policy effects
|
||||
description: Definition, collection evidence and limitations for confirmed policy effects.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Eligible evaluated attempts with an actual confirmed prohibited effect; report attempts, blocked attempts and effects separately.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct attempt_ids with confirmed prohibited action effect |
|
||||
| Denominator | All evaluated eligible attempt_ids including failed and abandoned runs |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Governed skill trials or supported workflow attempts, reported separately for eval and live populations. |
|
||||
| Exclusions | Out-of-scope runs; detection gaps remain coverage issues, not exclusions from known initiated population. |
|
||||
| Events and source | attempt.started; policy.violation; gate.blocked; security audit and incident triage |
|
||||
| Owner / cadence | Architecture & Security / Immediate incident action; weekly aggregates |
|
||||
| Missing evidence | Unknown outcomes remain visible; zero detected effects never proves safety. Missing audits make rate provisional. |
|
||||
| Gaming and limits | Hide incidents or inflate harmless trials; absolute severity counts and fixed task mix accompany rate. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Blocked attempts are not actual effects; any critical effect blocks promotion regardless of aggregate rate. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: cost-per-accepted-outcome
|
||||
slug: /measurement/cost-per-accepted-outcome
|
||||
title: Cost per accepted outcome
|
||||
description: Definition, collection evidence and limitations for cost per accepted outcome.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Allocated total workflow cost including unsuccessful attempts, licenses, compute, tooling and human review/rework divided by accepted outcomes.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum allocated costs in one approved reporting currency for all tasks/attempts in matured start cohort |
|
||||
| Denominator | Distinct independently accepted tasks in same cohort |
|
||||
| Expression | N / D |
|
||||
| Aggregation | ratio |
|
||||
| Unit | currency/accepted outcome |
|
||||
| Eligible population | Matured eligible started-task cohort, with all attempt costs through as_of and allocated shared period costs. |
|
||||
| Exclusions | Unrelated projects and documented taxes/transfers outside chosen accounting basis; never failed/abandoned attempts. |
|
||||
| Events and source | cost.recorded; task.accepted; finance invoices, usage ledger, sampled effort with approved rates |
|
||||
| Owner / cadence | Finance & Accounting Squad / Monthly with late invoice restatement |
|
||||
| Missing evidence | Missing cost buckets produce partial estimate plus coverage, not a total. Mixed currency requires dated approved conversion; zero accepted outcomes = null with full cost shown. |
|
||||
| Gaming and limits | Count tokens only or hide labor/failures; reconcile invoice and allocation totals without double counting. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Allocation and sampled labor carry uncertainty; no ROI without independently measured business benefit. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: deployment-frequency
|
||||
slug: /measurement/deployment-frequency
|
||||
title: Deployment frequency
|
||||
description: Definition, collection evidence and limitations for deployment frequency.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Distinct successful logical production deployments per complete service-day of observation.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct service_id+deployment_id successful production deployments in window |
|
||||
| Denominator | Observed service-days in window |
|
||||
| Expression | N / D |
|
||||
| Aggregation | ratio |
|
||||
| Unit | deployments/service-day |
|
||||
| Eligible population | Declared production services and complete UTC observation days; report each service before pooled views. |
|
||||
| Exclusions | Test/staging, failed attempts without production effect, duplicate callbacks and retries of the same rollout. |
|
||||
| Events and source | deployment.completed; authoritative deployment service |
|
||||
| Owner / cadence | Platform & IT / Weekly per service |
|
||||
| Missing evidence | Missing feed periods not zero; report coverage and no unqualified overall rate when period incomplete. |
|
||||
| Gaming and limits | Split deployments without value; pair with success, rework and failure measures. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. More deployments alone do not establish better performance; affected unsuccessful changes remain in change-fail population. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: deployment-rework-rate
|
||||
slug: /measurement/deployment-rework-rate
|
||||
title: Deployment rework rate
|
||||
description: Definition, collection evidence and limitations for deployment rework rate.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Unplanned production deployment effects triggered by a production incident as a share of deployment effects.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct incident-linked deployment_ids classified unplanned remediation |
|
||||
| Denominator | All distinct production deployment_ids with production effect in window |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Production deployment effects in window with immutable planned/unplanned classification and incident linkage. |
|
||||
| Exclusions | Nonproduction, no-effect retries and duplicates; do not exclude unclassified changes silently. |
|
||||
| Events and source | deployment.completed; incident.linked; release intent classification |
|
||||
| Owner / cadence | Platform & IT / Weekly |
|
||||
| Missing evidence | Unknown classification stays denominator; observed numerator is lower bound until reconciliation; show classification coverage. |
|
||||
| Gaming and limits | Call hotfixes planned; freeze reason and independently reconcile incident/deployment links. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Distinct from failure rate: one failed deployment can lead to multiple separate rework deployments. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: failed-deployment-recovery-time
|
||||
slug: /measurement/failed-deployment-recovery-time
|
||||
title: Failed deployment recovery time
|
||||
description: Definition, collection evidence and limitations for failed deployment recovery time.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Mean elapsed time from production deployment failure onset to service restoration, with median/p90 and unresolved count/age.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum of recovery_at minus failure_started_at in hours for recovered eligible deployment failures |
|
||||
| Denominator | Count of recovered eligible deployment failures with valid timestamps |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | hours/failure |
|
||||
| Eligible population | Production deployment failures beginning in window; latest verified restoration if a recovery is rescinded. |
|
||||
| Exclusions | Nondeployment incidents; invalid timestamp pairs reported missing, not treated as instantaneous recovery. |
|
||||
| Events and source | deployment.failed; service.restored; incident service |
|
||||
| Owner / cadence | Platform & IT / Weekly with unresolved failures |
|
||||
| Missing evidence | Unresolved failures reported separately and excluded only from recovered-duration distribution; prevent declaring improvement without their visibility. |
|
||||
| Gaming and limits | Premature recovery declarations or omit hard cases; require operational readback and carry unresolved ages. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Not all-incident MTTR; recovered-only sample has survivorship bias. p90 nearest rank. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,87 @@
|
||||
---
|
||||
id: index
|
||||
slug: /measurement
|
||||
title: Measuring real output
|
||||
sidebar_label: Measurement
|
||||
description: Optional contracts for workflow effectiveness and skills effectiveness and health, with distinct populations and honest implementation limits.
|
||||
pagination_prev: stage-01-skills-adoption
|
||||
pagination_next: baseline
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
Start with how current AI-assisted work performs; compare relevant outcomes after the selected intervention, whether context, coaching, tooling or skills. Separately assess skill fitness and health only where skills exist. Registry inclusion does not require a metric to be used, collected or baselined. More adoption does not prove improved work.
|
||||
|
||||
<ArchifyDiagram name="strategy-measurement" title="Workflow effectiveness / Skills effectiveness & health" story />
|
||||
|
||||
**Target operating model — candidate definitions, not installed telemetry or a collection plan.** Proposed owners and cadences in the contracts apply only if selected and agreed for a workflow.
|
||||
|
||||
## Read a candidate contract
|
||||
|
||||
For the [EXP-01 Delivery hypothesis](../six-months-roadmap.mdx#exp-01-a-small-decision-ready-example), start with three questions, not all 16 contracts. **Matured task acceptance** asks whether bounded work reaches independent acceptance; the architect joins tracker starts to PR/reviewer evidence, and the independent reviewer checks the cohort weekly. **Review/rework minutes** reveal shifted burden; participating authors/reviewers record short effort entries, not inferred PR waiting time. **Escaped defects and severity** balance apparent speed; the workflow owner links accepted changes to defects after the agreed follow-up. Agree these proposed responsibilities and lawful access in month 2. An approved worksheet is enough; no enterprise telemetry platform is assumed.
|
||||
|
||||
Record setup, qualification, onboarding, ongoing support, tool spend and missing cost buckets alongside these measures. The owner uses the comparison to retain, change or stop; the CTO uses the total investment and capacity evidence to fund or decline transfer. If effort cannot be collected without disproportionate burden, or defects cannot be linked, report the missing evidence and limit the decision—do not claim efficiency or safety. Deployment frequency and organization-wide adoption are initially deferred because they do not diagnose this rework hypothesis. A tiny cohort's experience survey may be suppressed; do not waive privacy to populate a dashboard.
|
||||
|
||||
**Where this misleads:** accepted counts change with task mix, staffing and unfinished work; a fast PR may merely shift checking to reviewers; defects mature later; volunteers and coached tasks are not representative of every team. Keep failed, abandoned and unresolved matured starts, coverage, complexity slices, client/model changes and concurrent process changes visible. Compare the same eligibility, acceptance and follow-up rules before/after; use matched or randomized allocation only when feasible and ethical. Report uncertainty, not a causal ROI claim. Invocation counts, generated lines and individual rankings are not productivity measures. Skill benchmark success does not establish real workflow improvement.
|
||||
|
||||
Each entry explains meaning and applicability, calculation, required inputs and evidence, exclusions, missing-evidence behavior, limitations and implementation status. The two groups below classify every contract by its primary question; conditional reuse never merges populations. A delivery metric need not fit a non-delivery workflow.
|
||||
|
||||
To select a relevant subset and establish actual starting evidence, use [Baseline](../baseline.mdx). Pilot application belongs to [Adoption](../skills-adoption.mdx); ongoing interpretation belongs to [Maintenance](../skills-maintenance.mdx).
|
||||
|
||||
In the **illustrative Delivery workflow** from [Stage 01](../stage-01-skills-adoption.mdx), incomplete regression evidence is the improvement hypothesis. The workflow owner and independent Quality Engineering reviewer select contracts that can test it, then carry the same definitions into the baseline and pilot comparison. They can leave unrelated metrics unselected. This reference capability supports the whole journey; opening this page is not an execution gate.
|
||||
|
||||
## Metric definitions
|
||||
|
||||
Each contract is a prospective definition, not a rollout obligation. No live source or observed baseline is established. N and D refer to the numerator and denominator shown for that metric.
|
||||
|
||||
<details>
|
||||
<summary>Implementation status—not live telemetry</summary>
|
||||
|
||||
There are **16 contracts: 9 prototype calculations and 7 unimplemented metrics**. The prototype has no network collectors. None of these counts establishes live telemetry.
|
||||
|
||||
The nine calculations cover task success, selection precision and recall, change fail rate, deployment rework, escaped quality, policy effects, cost and the primary human-experience item. The seven omissions are supported bundle coverage, approved-workflow adoption, change lead time, deployment frequency, failed deployment recovery time, substantive-review coverage and workflow-specific business acceptance.
|
||||
|
||||
</details>
|
||||
|
||||
### Workflow effectiveness
|
||||
|
||||
**Is the work getting better?** Baseline relevant current-workflow outcomes even before standardized skills exist, then compare the same outcomes during adoption and maintenance. Use comparable task mix, acceptance rules, follow-up periods and source coverage. Before/after trends alone are not causal evidence of a skills benefit.
|
||||
|
||||
1. [Validated task success](./validated-task-success.mdx) — **Prototype calculation.** Independently accepted outcomes among matured workflow starts; failures, abandonment and unresolved outcomes remain in the denominator.
|
||||
2. [Change lead time](./change-lead-time.mdx) — **Unimplemented metric.** Delivery time for production changes in one service, not general task duration.
|
||||
3. [Deployment frequency](./deployment-frequency.mdx) — **Unimplemented metric.** Production delivery frequency for one service; frequency alone is not value.
|
||||
4. [Change fail rate](./change-fail-rate.mdx) — **Prototype calculation.** Production deployments causing failures; requires joined change/incident evidence.
|
||||
5. [Failed deployment recovery time](./failed-deployment-recovery-time.mdx) — **Unimplemented metric.** Recovery from failed production deployments; conditional on eligible incidents.
|
||||
6. [Deployment rework rate](./deployment-rework-rate.mdx) — **Prototype calculation.** Unplanned corrective production deployments, not all forms of task rework.
|
||||
7. [Changes with escaped quality issues](./changes-with-escaped-quality-issues.mdx) — **Prototype calculation.** Accepted changes with confirmed downstream issues after follow-up.
|
||||
8. [Confirmed policy effects](./confirmed-policy-effects.mdx) — **Prototype calculation.** Safety of supported workflow attempts; governed skill trials are a separate evaluation population, never pooled with live work.
|
||||
9. [Cost per accepted outcome](./cost-per-accepted-outcome.mdx) — **Prototype calculation.** Cost of the matured workflow cohort, including unsuccessful attempts and recorded review/rework effort. Missing cost buckets remain partial.
|
||||
10. [Verification confidence and cognitive load](./verification-confidence-and-cognitive-load.mdx) — **Prototype calculation.** Anonymous cohort experience: confidence, workload and usefulness separately, not measured time savings.
|
||||
11. [Workflow-specific business acceptance](./workflow-specific-business-acceptance.mdx) — **Unimplemented metric.** Acceptance against an agreed departmental rubric; requires a defined workflow and independent evidence.
|
||||
|
||||
Human effort is recorded as review/rework inputs where the cost contract supports it; the experience survey describes perception. Neither elapsed delivery time nor token counts establish effort saved. If the current workflow lacks the event semantics required by a contract (for example, governed attempts), record it as not applicable or unavailable with a reason; do not relabel unrelated records to manufacture a baseline.
|
||||
|
||||
### Skills effectiveness & health
|
||||
|
||||
**Are the skills fit for use and kept fit?** Qualify named skills and versions, observe supported use during adoption, and review or retire them in maintenance. Without applicable skills, bundles or enrolled use, skill-specific measures may be **N/A, not zero**. Once a population exists, missing observations are unknown, not evidence of non-use or good health.
|
||||
|
||||
**Fitness comes from [Quality's evaluation evidence](../skills-quality.mdx), not health proxies.** Compare named candidate and approved revisions against declared cases, independent artifact acceptance and mandatory safety checks. Retain regression results, failed trials and coverage limits. The five registry contracts below complement that report: selection tests relevance; support, use and review measures describe operating health. None replaces evidence that a skill produces useful, safe artifacts. Maintenance sends real failures and revision changes back to Quality for requalification.
|
||||
|
||||
1. [Skill selection precision](./skill-selection-precision.mdx) — **Prototype calculation.** Did the evaluated selection choose an applicable skill? Requires labeled qualification cases.
|
||||
2. [Skill selection recall](./skill-selection-recall.mdx) — **Prototype calculation.** Were expected skills selected? Requires the same labeled qualification population.
|
||||
3. [Supported bundle coverage](./supported-bundle-coverage.mdx) — **Unimplemented metric.** Are expected active installations on supported, non-revoked bundles/adapters?
|
||||
4. [Approved-workflow adoption](./approved-workflow-adoption.mdx) — **Unimplemented metric.** Is the enrolled cohort using approved skills in eligible workflows? Installation/loading is not use.
|
||||
5. [Skills within substantive review window](./skills-within-substantive-review-window.mdx) — **Unimplemented metric.** Do active approved revisions have current owners and substantive review evidence?
|
||||
|
||||
**Task-success population matters.** The canonical validated-task-success contract above measures workflow outcomes, not an evaluation benchmark. A named skill/version can be examined as a predeclared live-workflow slice under that same contract, without counting retries or multiple skills as extra tasks or attributing causality. Sandbox/evaluation cases remain excluded: a named skill/version evaluation must be reported separately with its own declared cases, acceptance evidence and limits. It is not an additional implemented calculation or a second conflicting task-success formula. The canonical page explains this boundary. Likewise, keep policy-effect evaluation trials separate from live attempts.
|
||||
|
||||
Use both tracks together to decide whether to improve, retain or retire a skill. Higher selection scores, wider adoption or current reviews cannot substitute for accepted work, safety, cost and human experience.
|
||||
|
||||
Read [Collection and safeguards](./collection-and-safeguards.mdx) for shared interpretation, event and privacy rules. [Run the synthetic measurement example](./synthetic-example.mdx) for reproducible arithmetic and limits.
|
||||
|
||||
**Next:** [Establish a relevant workflow baseline →](../baseline.mdx)
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
id: skill-selection-precision
|
||||
slug: /measurement/skill-selection-precision
|
||||
title: Skill selection precision
|
||||
description: Definition, collection evidence and limitations for skill selection precision.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Correct activations among activations on an independently labeled evaluation corpus.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | True-positive activations for the requested workflow |
|
||||
| Denominator | True-positive plus false-positive activations |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | All candidate/client labeled evaluation task-trials with known activation and relevance. |
|
||||
| Exclusions | Unlabeled/unknown activations excluded with coverage; no cherry-picked failed trials. |
|
||||
| Events and source | eval.selection; versioned labeled corpus and runner |
|
||||
| Owner / cadence | Data & AI / Each skill/client qualification |
|
||||
| Missing evidence | Unknown activation/relevance is unscorable; publish missing count and deny qualification if planned coverage incomplete. |
|
||||
| Gaming and limits | Choose easy labels or hide negative cases; freeze corpus and independently review labels. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Does not show execution success; precision depends on corpus prevalence. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
Use this labeled-case result in [Quality's candidate evaluation](../skills-quality.mdx). Selecting the right skill is only one input: independently test artifact fitness, safe execution and revision regression before the owning approver considers a bounded pilot. It is not the live Delivery workflow's accepted-task rate.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
id: skill-selection-recall
|
||||
slug: /measurement/skill-selection-recall
|
||||
title: Skill selection recall
|
||||
description: Definition, collection evidence and limitations for skill selection recall.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Relevant task-trials in which the intended skill activates.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | True-positive activations |
|
||||
| Denominator | True-positive plus false-negative task-trials |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Independently labeled relevant evaluation task-trials for a skill/client tuple. |
|
||||
| Exclusions | Irrelevant tasks; missing relevance or activation reported as unscorable, not negative. |
|
||||
| Events and source | eval.selection; versioned labeled corpus and runner |
|
||||
| Owner / cadence | Data & AI / Each skill/client qualification |
|
||||
| Missing evidence | Report evaluation coverage; null if no relevant labeled tasks. |
|
||||
| Gaming and limits | Overtrigger to maximize recall; always pair with precision and negative cases. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Loading the right skill is not adherence. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
Use this labeled-case result alongside precision in [Quality's candidate evaluation](../skills-quality.mdx). Finding expected skills does not establish useful artifacts or safe execution. Preserve missing-case coverage and revision-regression evidence before a bounded pilot; do not pool evaluation cases with live Delivery tasks.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
id: skills-within-substantive-review-window
|
||||
slug: /measurement/skills-within-substantive-review-window
|
||||
title: Skills within substantive review window
|
||||
description: Definition, collection evidence and limitations for skills within substantive review window.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Active approved skill revisions with an accountable owner and completed substantive review not past due.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct active approved skill revisions with current owner, review evidence and review_due_at >= as_of |
|
||||
| Denominator | All active approved skill revisions in catalog snapshot |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Approved revisions currently supported for use at as_of. |
|
||||
| Exclusions | Experimental and retired revisions; deprecated/revoked in-use counts reported independently, not hidden. |
|
||||
| Events and source | catalog.published; catalog.reviewed; catalog.deprecated; catalog.revoked; version inventory |
|
||||
| Owner / cadence | Data & AI / Monthly and each release |
|
||||
| Missing evidence | Missing owner/date/evidence outside numerator; show ownerless, deprecated-in-use and revoked-in-use absolute counts. |
|
||||
| Gaming and limits | Rubber-stamp review dates; require linked regression/security/usefulness evidence. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. A current review is not proof of effectiveness; consumer inventory may miss shadow copies. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
[Maintenance](../skills-maintenance.mdx) uses this coverage signal to find overdue or ownerless revisions. A current date is not proof of effectiveness: substantive review must consider [Quality's fitness and regression evidence](../skills-quality.mdx), supported-client changes and live-workflow outcomes. Gaps trigger review or requalification, not a favorable health assumption.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: supported-bundle-coverage
|
||||
slug: /measurement/supported-bundle-coverage
|
||||
title: Supported bundle coverage
|
||||
description: Definition, collection evidence and limitations for supported bundle coverage.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Inventoried active installations with verified effective approved, supported and nonrevoked bundle/adapter tuple.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Eligible installation_ids with valid inventory evidence within approved freshness window and matching support matrix |
|
||||
| Denominator | All expected active installation_ids in the managed pilot inventory |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Active installation inventory frozen for report, including invisible/offline entries until authoritative offboarding. |
|
||||
| Exclusions | Verified decommissioned installations and nonpilot assets; lack of telemetry alone never excludes. |
|
||||
| Events and source | inventory.observed; catalog.published; catalog.revoked; device inventory |
|
||||
| Owner / cadence | Platform & IT / Weekly and at revocation |
|
||||
| Missing evidence | Unknown/stale versions count outside numerator, inside denominator. Show inventory discovery coverage versus eligible device roster; if roster unknown metric is provisional. |
|
||||
| Gaming and limits | Remove silent devices or trust declared versions; reconcile managed inventory and separately label attestation trust. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Even verified file digests do not prove a private model followed the content. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,24 @@
|
||||
---
|
||||
id: synthetic-example
|
||||
slug: /measurement/synthetic-example
|
||||
title: Run the synthetic measurement example
|
||||
description: Reproduce the synthetic KPI calculations and understand their limits.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
{/* preserved:start */}
|
||||
**Executed synthetic example — not Eldorado results.** The bundled fixture produces 1 independently accepted task from 4 matured starts: 25% confirmed success. One unresolved task remains in that denominator; known-outcome coverage is 75%. Selection precision and recall are each 1 / 2 = 50%. Recorded synthetic compute cost is EUR 60 / 1 accepted outcome = EUR 60 per accepted outcome, a partial estimate: licenses, tooling, review and rework are missing. These deliberately small samples demonstrate arithmetic and missingness, not a baseline, target or ROI claim.
|
||||
|
||||
From the private documentation checkout, run `node scripts/ai-kpi.mjs` and `node --test scripts/ai-kpi.test.mjs`. The fixture `scripts/fixtures/ai-kpi-synthetic.json` is labeled synthetic; every result carries the same label and calculation version. This prototype has no network collectors and does not enable employee telemetry.
|
||||
|
||||
The executable covers validated success, selection precision/recall, change fail and rework rates, escaped quality, policy effects, cost and human experience. Other catalog metrics remain contracts rather than implemented collectors; output lists the omissions. Snapshot inputs are simplified, pre-reconciled records, not a production ingestion system. Conflicting duplicates reject the calculation rather than silently choosing a value.
|
||||
{/* preserved:end */}
|
||||
|
||||
Return to the [Skills Measurement index](./index.mdx) for every metric definition.
|
||||
|
||||
Use this fixture to check calculation and missing-evidence behavior before applying selected contracts in [Baseline](../baseline.mdx) or [Adoption](../skills-adoption.mdx). It is not the illustrative Delivery workflow's baseline and does not qualify a skill: [Quality](../skills-quality.mdx) requires independent, versioned artifact and safety evidence on declared evaluation cases.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,44 @@
|
||||
---
|
||||
id: validated-task-success
|
||||
slug: /measurement/validated-task-success
|
||||
title: Validated task success
|
||||
description: Definition, collection evidence and limitations for validated task success.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Confirmed independently accepted tasks as a share of all eligible initiated tasks in a matured start cohort; a conservative confirmed-success share, not observed failure rate.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Distinct matured task_ids with valid independent task.accepted evidence by as_of |
|
||||
| Denominator | All distinct eligible task_ids started in window with started_at + preregistered task_observation_hours <= as_of |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | Tasks in a preregistered workflow cohort, started in window; each counted once across retries, skills and clients. |
|
||||
| Exclusions | Cancelled before start, sandbox/evaluation tasks and out-of-scope workflows; never post-start failures/abandonments. |
|
||||
| Events and source | task.started; task.accepted; task.failed; task.abandoned; task.cancelled; work-management acceptance record |
|
||||
| Owner / cadence | Quality Engineering / Weekly pilot; monthly departmental outcome review |
|
||||
| Missing evidence | Unresolved/missing terminal outcomes remain in denominator with unknown count and known-outcome coverage; do not label them failed. Invalid/missing start excluded from calculation but flagged as orphan evidence. |
|
||||
| Gaming and limits | Split easy tasks or omit starts; reconcile starts to approved backlog and audit acceptance rubrics. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Maturation horizon is workflow-specific and must be approved; no automatic abandonment on timeout. |
|
||||
{/* contract:end */}
|
||||
|
||||
## Workflow outcomes versus skill/version evaluation
|
||||
|
||||
This contract belongs to **Workflow effectiveness**. Use the same matured-start population and independent acceptance rules before and after introducing skills; skills are not required for a workflow outcome to exist. Do not narrow the later denominator to successful skill invocations.
|
||||
|
||||
For **Skills effectiveness & health**, a predeclared slice of live workflow tasks using a named skill/version may reuse this contract unchanged. Keep the parent cohort visible, report exact versions and selection limits, and count each task once across retries, skills and clients. Overlapping skill slices must not be summed. This is descriptive evidence, not proof that the skill caused success.
|
||||
|
||||
A sandbox or qualification evaluation of a named skill/version is a different population and remains excluded by this contract. [Quality](../skills-quality.mdx) defines artifact-success and revision-regression evidence: declare cases, skill/version, client/model configuration, acceptance rubric and observed results separately; never combine those cases with live workflow starts or present their results as this prototype's workflow rate. This page does not introduce an implemented skill-evaluation metric or an alternative formula. No applicable skill means that skill-specific evaluation is N/A, not a zero workflow success rate.
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: verification-confidence-and-cognitive-load
|
||||
slug: /measurement/verification-confidence-and-cognitive-load
|
||||
title: Verification confidence and cognitive load
|
||||
description: Definition, collection evidence and limitations for verification confidence and cognitive load.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Prototype calculation — no live telemetry.** The synthetic example calculates this metric; it has no network collectors.
|
||||
|
||||
{/* contract:start */}
|
||||
Three separate anonymous 1–5 item distributions: confidence in verifying output, manageable workload, usefulness. Primary item: verification confidence mean; report full distributions and response rate.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Sum valid 1–5 verification-confidence responses, one per participant per survey wave |
|
||||
| Denominator | Count valid responses to that item |
|
||||
| Expression | N / D |
|
||||
| Aggregation | mean |
|
||||
| Unit | points (1–5) |
|
||||
| Eligible population | Invited eligible cohort at fixed survey wave; voluntary responses. |
|
||||
| Exclusions | Invalid/out-of-range answers and superseded duplicate submission; nonresponders stay in response-rate denominator. |
|
||||
| Events and source | survey.response; anonymous survey with single-use token and aggregate invitation count |
|
||||
| Owner / cadence | People & Administration Squad / After pilot workflow cycle; periodic follow-up |
|
||||
| Missing evidence | Report valid response count / invited count and item nonresponse; no imputation. Suppress people cohorts below five. |
|
||||
| Gaming and limits | Pressure to respond positively; no manager access to individual responses, avoid identifying free text. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Perception and selection bias; not measured time savings. No composite productivity index. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
id: workflow-specific-business-acceptance
|
||||
slug: /measurement/workflow-specific-business-acceptance
|
||||
title: Workflow-specific business acceptance
|
||||
description: Definition, collection evidence and limitations for workflow-specific business acceptance.
|
||||
---
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
|
||||
|
||||
**Unimplemented metric — no live telemetry.** This is a prospective contract, not an implemented calculation or collector.
|
||||
|
||||
{/* contract:start */}
|
||||
Independently accepted domain outcomes against a predeclared business rubric, separate from technical completion.
|
||||
|
||||
| Contract | Definition |
|
||||
| --- | --- |
|
||||
| Numerator | Eligible completed-observation task_ids meeting the department-specific outcome rubric |
|
||||
| Denominator | All eligible initiated workflow task_ids with matured business-outcome horizon |
|
||||
| Expression | N / D * 100 |
|
||||
| Aggregation | percent |
|
||||
| Unit | % |
|
||||
| Eligible population | One named departmental workflow and predeclared start cohort; never pool unlike rubrics. |
|
||||
| Exclusions | Cancelled-before-start and unrelated workflows; unsuccessful or abandoned eligible work remains. |
|
||||
| Events and source | task.started; business.accepted; departmental case/content/reconciliation/onboarding review record |
|
||||
| Owner / cadence | Product Management / Each pilot cycle with owning department |
|
||||
| Missing evidence | Unknown follow-up stays denominator with unresolved count; no claim actual business outcome changed without source evidence. |
|
||||
| Gaming and limits | Weaken rubric or count drafts as customer benefit; lock rubric and independently audit acceptance. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Domain owner signs acceptance: Operations service accuracy; Marketing claims/rights; Finance reconciliation accuracy; HR policy correctness; Product usability/value. Not revenue uplift. |
|
||||
{/* contract:end */}
|
||||
|
||||
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
|
||||
|
||||
Return to [Skills Measurement](./index.mdx).
|
||||
|
||||
</div>
|
||||
+43
-41
@@ -1,7 +1,7 @@
|
||||
---
|
||||
id: roadmap
|
||||
title: Roadmap
|
||||
description: Evidence-gated phases, no promised dates or budgets.
|
||||
description: Build proven skills in human and AI Agent work, starting with Delivery, as the foundation for the future autonomous SDLC.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
@@ -9,67 +9,69 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
## Two stages toward the long-term Target
|
||||
|
||||
## What must be true before widening the rollout?
|
||||
<ArchifyDiagram name="strategy-roadmap" title="Adopt skills → Future Autonomous Agent" story />
|
||||
|
||||
Advance by exit evidence, not promised dates or usage volume. Each stage can hold, narrow or stop; changed client, data or authority boundaries reopen earlier gates.
|
||||
**Humans direct, guide and review throughout.** Stage 1 standardizes skills in human + AI Agent work across the SDLC. Proven skills, measurements and working practices become the foundation for Stage 2: the future Autonomous Agent in [Target](./target-operating-model.mdx).
|
||||
|
||||
<ArchifyDiagram name="strategy-roadmap" title="Foundation, pilot, reliable distribution, coordination and departmental expansion have exit gates" story />
|
||||
This is the broad progression, not a month-by-month schedule. The [6 Months Target](./six-months-target.mdx) bounds the first contribution; the [6 Months Roadmap](./six-months-roadmap.mdx) owns the concrete action plan.
|
||||
|
||||
- **Start bounded:** named people, lawful data handling and a reproducible baseline precede the pilot.
|
||||
- **Prove recovery before coordination:** verified versions, revocation and human takeover are prerequisites.
|
||||
- **Expand by department:** accepted outcomes, guardrails, total cost and experience justify continuation; sensitive decisions remain human.
|
||||
Target operating model—not deployed autonomy, an agreed schedule or approved KPI thresholds. Stage 1 is useful in its own right; Stage 2 requires a separately justified change in authority, not graduation for using enough skills.
|
||||
|
||||
## Stage 1: Delivery first
|
||||
|
||||
<ArchifyDiagram name="strategy-roadmap-adoption" title="Delivery first → Other SDLC phases, order undecided" story />
|
||||
|
||||
Start with Delivery, then extend skills adoption to the remaining SDLC phases. Their order is not yet decided. **Delivery keeps improving as adoption expands.**
|
||||
|
||||
## Improve within each phase
|
||||
|
||||
<ArchifyDiagram name="strategy-roadmap-loop" title="Each phase: understand → baseline → topology → use → collect → reassess → repeat" story />
|
||||
|
||||
Repeat this loop within every phase—not as six global roadmap stages. Skills topology defines **what skills exist, how they relate, when they are used and how they work together**, including handoffs—not just a catalogue.
|
||||
|
||||
## Delivery in practice
|
||||
|
||||
**Understand the engineering path first:** codebase structure and existing principles → system-logic source → tests → builds and packaging → deployments. Inspect actual practices, tooling, controls and problems with the people doing the work, rather than assuming the documented process is the real one.
|
||||
|
||||
**Establish the comparison, then choose the intervention.** Context, coaching, better tests or deterministic automation may resolve the immediate bottleneck more effectively; do not force a skill where none is needed. Select relevant metrics/KPIs and a baseline for comparable work before changing it. [Measurement](./measurement/index.mdx) supplies optional definitions; [Baseline](./baseline.mdx) records the actual starting position or gaps. Connect skills to the engineering path, with clear triggers, dependencies and acceptance checks; [Quality](./skills-quality.mdx) qualifies the candidate before bounded real use.
|
||||
|
||||
**Use, collect, compare, repeat.** A human works with an AI Agent on real changes. Collect results, friction and feedback alongside quality, cost and verification effort. Compare with the baseline to understand the new current situation; retain, improve, stop or propose expansion. Changed revisions return to qualification; changed workflows need a fresh comparison.
|
||||
|
||||
Follow the **illustrative Delivery workflow** in [Stage 01](./stage-01-skills-adoption.mdx): prepare a bounded code change and regression tests, then hand the exact artifact to independent review. Its dependency diagram shows what passes between activities and who decides whether work can progress. Governance and Measurement support the whole loop; they are not one-time gates.
|
||||
|
||||
<details>
|
||||
<summary>Stage-by-stage entry evidence, work, exit gates and hold conditions</summary>
|
||||
<summary>Readiness questions behind the roadmap</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
These are readiness questions, not additional roadmap stages. Stage 01's topic pages define the recommended decisions and evidence within existing teams. Designate accountable people and agree workflow-specific acceptance criteria before evaluating; this strategy does not appoint approvers or approve thresholds.
|
||||
|
||||
### Foundation
|
||||
### Understand the current situation
|
||||
|
||||
**Entry evidence** — Strategy scope accepted for planning; existing teams identified.
|
||||
Sample representative repositories and changes. Retain repository revisions, tests and CI reliability, maintainability, technical debt and security findings. Trace ownership, review and release practices, handoffs, rework and bottlenecks. Keep baseline findings, a process map and prioritized gaps; hold selection if the sample cannot explain how work is delivered and accepted.
|
||||
|
||||
**Work** — Inventory actual client hosts/builds, provider/data terms, repositories, authority, owners and event availability; select low-risk workflows and metric definitions.
|
||||
### Prepare safe, measurable human + AI work
|
||||
|
||||
**Exit evidence and hold condition** — Named accountable people and independent reviewers, bounded pilot charter, forbidden actions, data/retention decision and reproducible baseline plan. Hold if accountability or lawful collection is unresolved.
|
||||
Inventory actual client hosts/builds, provider/data terms, authority and event availability. Confirm accountable people and independent reviewers, forbidden actions, data/retention decisions, recovery and a reproducible baseline. Hold if accountability, lawful collection or critical acceptance checks remain unresolved.
|
||||
|
||||
### Governed skills pilot
|
||||
Close critical gaps such as exposed secrets, unclear approval authority or unreliable acceptance checks. Broader refactoring and non-critical debt can run alongside the selected work. Stage 1 introduces no new privileged autonomous actions.
|
||||
|
||||
**Entry evidence** — Foundation evidence approved; no privileged autonomous effects.
|
||||
### Engineer and evaluate connected skills
|
||||
|
||||
**Work** — Build a small registry, immutable contract, client adapters, evaluations, coaching and synthetic measurement verification.
|
||||
Use a small registry, immutable skill contracts, qualified client adapters, evaluations and coaching. Verify the measurement calculations with synthetic fixtures before interpreting real outcomes. Require mandatory safety checks, independent task acceptance, reconciled source coverage and user feedback. Hold or narrow scope if quality or coverage is inadequate; usage alone does not justify expansion.
|
||||
|
||||
**Exit evidence and hold condition** — Qualified client/skill tuples, mandatory safety checks, independent task acceptance, reconciled coverage and user feedback. Hold or narrow scope if quality or data coverage is inadequate.
|
||||
### Extend adoption without stopping improvement
|
||||
|
||||
### Reliable distribution
|
||||
Prove canary updates, effective-version readback, version locking, exception expiry, stale/offline handling, rollback and revocation. Hold if effective versions or controls cannot be verified or the catalog cannot be supported.
|
||||
|
||||
**Entry evidence** — Pilot quality and usefulness support continuing.
|
||||
Use evidence to choose the next SDLC phase; no second or third phase is assigned here. Continue the improvement loop in Delivery and every phase already using skills.
|
||||
|
||||
**Work** — Canary updates, effective-version readback, version locking, exception expiry, stale/offline handling and rollback.
|
||||
### Prepare for the future Autonomous Agent
|
||||
|
||||
**Exit evidence and hold condition** — Tested revocation and recovery, no bypass of central privileged gates, owners can support the catalog. Hold if effective versions or controls cannot be verified.
|
||||
|
||||
### Logical SDLC coordination
|
||||
|
||||
**Entry evidence** — Distribution, authority and measurement evidence stable.
|
||||
|
||||
**Work** — Observe and assemble evidence first, then propose and route work within scoped identities and budgets.
|
||||
|
||||
**Exit evidence and hold condition** — Exact-artifact approvals, idempotency, duplicate/outage recovery, separation of duties, audit and kill-switch drills pass; humans can take over. No authority expansion based on usage alone.
|
||||
|
||||
### Departmental expansion
|
||||
|
||||
**Entry evidence** — Each department supplies a workflow owner, outcome, data boundary and capacity.
|
||||
|
||||
**Work** — Add Operations, Marketing, Finance & Accounting and HR & Administration workflows with domain-specific review; Product and Technology continue quality improvement.
|
||||
|
||||
**Exit evidence and hold condition** — Departmental accepted outcomes, guardrails, total cost and experience justify continuation; sensitive decisions stay human. Stop or roll back workflows without adequate evidence.
|
||||
|
||||
There are no invented launch dates, budgets, staffing commitments or guaranteed gains. Phase gates permit narrowing or stopping. Re-evaluate earlier phases when the underlying client, provider, data scope or authority changes.
|
||||
Stage 2 builds on proven skills, measurements and working practices—not permission inferred from adoption alone. [Beyond 6 Months](./stage-02-autonomous-agent.mdx) owns the separate authority/readiness decision. Recommended controls include exact-artifact approvals, idempotency, duplicate/outage recovery, separation of duties, audit and kill-switch drills. Prove human takeover; never infer permission from missing evidence. Keep sensitive decisions human. Changed client, provider, data or authority boundaries reopen the relevant checks.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Return to the strategy destination →](./index.mdx)
|
||||
**Next:** [6 Months Target →](./six-months-target.mdx)
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,136 @@
|
||||
---
|
||||
id: six-months-roadmap
|
||||
title: 6 Months Roadmap
|
||||
description: Proposed month-by-month work, capacity, dependencies and decisions for a solo AI Architect.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
## Six months, two investment decisions
|
||||
|
||||
<ArchifyDiagram name="strategy-six-months" title="Months 1–6: discover, test, compare and hand over; proposed, not commitments" story />
|
||||
|
||||
**Humans direct, guide and review throughout.** This is a proposed plan, not an agreed schedule or budget. The first decision funds one bounded experiment; the second retains, changes or stops it before any transfer. The [six-month strategy](./six-months-target.mdx) starts with existing uneven AI-assisted practice, not zero adoption. This is a bounded contribution toward the long-term [Target](./target-operating-model.mdx), not permission to deploy it. The broad [Roadmap](./roadmap.mdx) has no fixed timeline.
|
||||
|
||||
**Month 1 — Discover and earn trust.** I agree CTO expectations, access and a monthly decision meeting; meet team leads, pair with developers and reviewers across contrasting workflows, and trace recent changes. Output: current-work map, AI/tool/data constraints, evidence gaps and ranked bottlenecks. Dependency: willing access to real work. Decision: select a problem, or continue targeted discovery rather than prescribe skills.
|
||||
|
||||
**Month 2 — Agree one experiment.** I recruit one willing team and an independent reviewer, observe a prospective baseline and compare context, coaching, test/review feedback, deterministic automation and skills. Output: the [experiment packet](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example), effort cap, acceptance rules and stop date. Dependency: team lead agrees contributions; actual risk/approval owners clear the boundary. No partner, reliable checks or lawful evidence means no live pilot.
|
||||
|
||||
**Month 3 — Work beside the team.** I build and qualify the smallest intervention, pair on bounded changes and collect outcomes plus burden. Output: reproducible examples, failure cases and weekly evidence review. Dependency: independent qualification and explicit pilot permission, not tool installation. Stop unsafe work immediately; fix friction before asking others to adopt.
|
||||
|
||||
**Month 4 — Compare and choose.** I reconcile matured tasks, defects, review effort, costs and concurrent changes with the reviewer. Output: retain/change/hold/stop recommendation to the workflow owner and CTO. Dependency: comparable matured tasks and reconciled sources. Low task supply or missing follow-up means inconclusive, not success. Only an approved time-and-budget-bounded extension may continue; otherwise narrow or stop.
|
||||
|
||||
**Month 5 — Transfer selectively.** If value and burden are acceptable, I pair with a voluntary champion and backup and test a second willing team's fit. Output: a team-owned example, support/recovery instructions and a new-scope baseline. Dependency: team capacity and funded upkeep. If absent, improve the first workflow or retire it; no organization-wide training mandate.
|
||||
|
||||
**Month 6 — Handover and CTO evidence review.** I verify that the team can operate without daily architect help and present outcomes, limits, costs and stopped work. Output: an owned retained workflow or documented stop, plus a prioritized next-quarter proposal. Dependency: independent evidence and actual owner acceptance. The CTO decides the next investment, not an automatic autonomy phase.
|
||||
|
||||
## Delivery first, replication only if earned
|
||||
|
||||
|
||||
**Delivery keeps improving** whether transfer happens or not. The order of any other workflows is not yet decided. I bring concrete examples to skeptical teams, ask what creates extra work, and accept non-participation. A skeptic can help judge a demo without joining a pilot. If priorities conflict, I ask the CTO for a trade-off, not a compliance escalation.
|
||||
|
||||
## Keep one learning loop
|
||||
|
||||
|
||||
Repeat the learning loop, not a predetermined tool rollout. If skills are selected, their topology defines what skills exist, how they relate, when they are used and how they work together. Simpler context, coaching or deterministic fixes do not require a skills catalog.
|
||||
|
||||
## Solo capacity and influence
|
||||
|
||||
Proposed weekly allocation during pilots: two days hands-on pairing/building, one day evaluation/evidence, one day coaching and relationships, and one day sponsor decisions, support and contingency. One active live pilot at a time; a second team starts only after the first is supportable. This is a capacity envelope, not known company availability.
|
||||
|
||||
Ask a partner lead to agree a small pairing slot and independent review time explicitly; record actual effort, not assumed free team labor. Agree a short weekly team check-in and monthly CTO review of evidence, blocked dependencies, spend and the next choice. Seek specialist security/privacy advice only where the selected boundary requires it; preserve independent checks without appointing a committee.
|
||||
|
||||
Trace codebase structure and existing principles → system-logic source → tests → builds and packaging → deployments. Repair critical acceptance/data gaps before live use. Publish short reusable examples and offer office hours; don't become a permanent help desk for more than ten teams. Escalate support demand as an investment choice, never hide it in apparent savings.
|
||||
|
||||
Follow the **illustrative Delivery workflow** in [the experiment packet](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example). Its worked decision keep benefit, burden and safety connected. [Measurement](./measurement/index.mdx) supplies optional definitions; [Baseline](./baseline.mdx) records actual starting evidence. Governance and Measurement are supporting references, not one-time gates.
|
||||
|
||||
<details>
|
||||
<summary>Readiness questions behind the roadmap</summary>
|
||||
|
||||
These are readiness questions, not additional roadmap stages. Stage 01's topic pages define the recommended decisions and evidence within existing teams. Designate accountable people and agree workflow-specific acceptance criteria before evaluating; this strategy does not appoint approvers or approve thresholds.
|
||||
|
||||
### Understand the current situation
|
||||
|
||||
Sample representative repositories and changes. Retain repository revisions, tests and CI reliability, maintainability, technical debt and security findings. Trace ownership, review and release practices, handoffs, rework and bottlenecks. Keep baseline findings, a process map and prioritized gaps; hold selection if the sample cannot explain how work is delivered and accepted.
|
||||
|
||||
### Prepare safe, measurable human + AI work
|
||||
|
||||
Inventory actual client hosts/builds, provider/data terms, authority and event availability. Confirm accountable people and independent reviewers, forbidden actions, data/retention decisions, recovery and a reproducible baseline. Hold if accountability, lawful collection or critical acceptance checks remain unresolved.
|
||||
|
||||
Close critical gaps such as exposed secrets, unclear approval authority or unreliable acceptance checks. Broader refactoring and non-critical debt can run alongside the selected work. Stage 1 introduces no new privileged autonomous actions.
|
||||
|
||||
### If skills are the chosen intervention
|
||||
|
||||
Use a small registry, immutable skill contracts, qualified client adapters, evaluations and coaching. Verify the measurement calculations with synthetic fixtures before interpreting real outcomes. Require mandatory safety checks, independent task acceptance, reconciled source coverage and user feedback. Hold or narrow scope if quality or coverage is inadequate; usage alone does not justify expansion.
|
||||
|
||||
### Extend adoption without stopping improvement
|
||||
|
||||
Prove canary updates, effective-version readback, version locking, exception expiry, stale/offline handling, rollback and revocation. Hold if effective versions or controls cannot be verified or the catalog cannot be supported.
|
||||
|
||||
Use evidence to choose the next SDLC phase; no second or third phase is assigned here. Continue the improvement loop in Delivery and every phase already using skills.
|
||||
|
||||
### Contribute toward the long-term vision without granting authority
|
||||
|
||||
Beyond six months may mean deeper coaching, deterministic tooling or no expansion. If additional autonomous authority solves an evidenced problem, [Beyond 6 Months](./stage-02-autonomous-agent.mdx) requires a separate authority/readiness decision. Recommended controls include exact-artifact approvals, idempotency, duplicate/outage recovery, separation of duties, audit and kill-switch drills. Prove human takeover; never infer permission from missing evidence. Keep sensitive decisions human. Changed client, provider, data or authority boundaries reopen the relevant checks.
|
||||
|
||||
</details>
|
||||
|
||||
## EXP-01: a small, decision-ready example
|
||||
|
||||
**Entirely fictional teaching packet — no Eldorado results, approvals or universal targets.** Suppose current AI-assisted changes repeatedly return from review without regression evidence. Compare a repository test map plus review checklist with packaging the same guidance as a skill. Try the cheaper checklist first; only test the skill if repeated context loss remains. No new release authority or raw prompt collection is needed.
|
||||
|
||||
The proposed starting measures are **matured task acceptance**, **review/rework minutes** and **escaped defects with severity**. Tag review returns with a checked reason, including missing regression evidence, to test the claimed mechanism rather than infer it from acceptance alone. Record setup/upkeep and tool costs alongside them; critical policy effects stop the work regardless of averages. [Measurement](./measurement/index.mdx) explains feasible sources and misleading signals. The packet below shows how to decide even when the answer is “not enough evidence.”
|
||||
|
||||
<details>
|
||||
<summary>EXP-01 packet — scope, qualification, observations and decisions</summary>
|
||||
|
||||
### Freeze the question and capacity before trying it
|
||||
|
||||
Illustrative scope: small non-urgent bug fixes in one repository, one willing team and one qualified client/model configuration. Exclude migrations, secrets, personal data and production permissions. Trace intent → patch → regression tests → independent review → existing release route. Do not cherry-pick successful PRs; register every eligible task start and retain failures and abandoned work. Stratify by task complexity and reviewer availability; record concurrent CI/tool/model changes.
|
||||
|
||||
**Real-use blanks:** workflow owner `[name/consent]`; architect/author `[name]`; independent reviewer `[name]`; risk/data approver where needed `[name]`; participant agreement `[record]`; repository/client/model/revision `[immutable references]`; start/end/as-of `[dates]`; source links `[task, PR, CI, defect, effort and cost records]`; access/retention `[approved purpose and expiry]`. These blanks mean this example is not launch authorization.
|
||||
|
||||
Illustrative budget to negotiate: architect setup/context/evaluation 16 hours, independent qualification 4 hours, onboarding 2 participant-hours; four-week live pilot capped at 8 architect support hours and 8 additional participant/reviewer hours, with tool spend capped separately at EUR 100. These are effort caps, not estimated savings. Record actual one-off setup separately from recurring review, rework, support and upkeep. Expected supply is only 3 eligible starts per week: a feasibility signal, not power for a productivity claim. If the team cannot supply or support this, reduce scope or stop rather than add unpaid work.
|
||||
|
||||
Predeclare: task outcome follow-up 14 days from start; defect follow-up 14 days from acceptance, with later-discovered harm still reported. Plan 12 matured starts per period and show all pending tasks separately. That sample is a minimum for this descriptive feasibility decision, **not** sufficient precision for a causal benefit claim. Benefit hypothesis: fewer missing-evidence returns without increasing comparable review/rework effort. Illustrative guardrail: no increase above the baseline median for comparable work and no critical effect; all severity changes reviewed individually. Missing effort or defect linkage prevents retain/expand. Any genuine benefit/promotion claim needs an independently agreed uncertainty/precision rule and adequate sample before collection; if that is infeasible, stay feasibility-only.
|
||||
|
||||
### First-revision qualification and bounded permission
|
||||
|
||||
Fictional candidate `EXP-01/R1` is test-map/checklist guidance packaged as a skill, with one pinned client tuple and disposable repository revision. In real use replace these labels with immutable artifacts. Compare with the team's existing AI-assisted practice **without the candidate**, not “no AI.” With no prior approved skill, record approved-comparator regression **N/A: first revision**. Existing instructions remain inventoried so the comparator is honest.
|
||||
|
||||
Illustrative qualification ledger: representative fix produces the expected patch and regression tests, independently accepted; unrelated task correctly declines; injected repository instruction to bypass review is rejected; missing tests cause escalation rather than a false pass; removal/reload in a pinned clean environment restores declared current practice. These five case summaries are a tiny feasibility demonstration, not R2 qualification coverage. Record omitted cases and failures. A real reviewer must approve a risk-appropriate evaluation design, then inspect all executed results before any live pilot. A failed mandatory safety/authority check blocks it regardless of sample size.
|
||||
|
||||
Only the actual workflow approver, independent of the author, can authorize the exact candidate/client, enrolled cohort, four-week collection window, later follow-up and expiry. Security/data owner clears relevant boundaries. Record the permission separately from qualification. Disable/remove the candidate, invalidate/reload sessions and verify clean current-practice checks for recovery; there is no invented last-known-good skill. The [first-revision rule](./skills-quality.mdx) keeps independent acceptance mandatory.
|
||||
|
||||
### Illustrative observations, including the inconvenient rows
|
||||
|
||||
This compact ledger represents fictional task groups with the same declared eligibility. In real use retain one row per task and source links, not just this summary. Pending tasks do not enter the matured denominator; unresolved matured starts do.
|
||||
|
||||
| Record group | Matured starts | Accepted / failed / abandoned / unresolved | Review/rework observations | Defect follow-up |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| EXP-01 B01–B12: current AI-assisted practice | 12 | 8 / 2 / 1 / 1 | All 12 recorded; median 30 minutes | 8 accepted changes mature; one confirmed non-severe defect |
|
||||
| EXP-01 P01–P12: candidate, first review | 12 | 9 / 1 / 1 / 1 | Only 9 of 12 recorded; median 35 minutes for observed rows only | Only 6 of 9 accepted changes mature; three pending |
|
||||
| EXP-01 P13–P15: later starts | 0 yet | All three still within task horizon | Kept separate, not discarded | Not eligible yet |
|
||||
|
||||
The apparent 9 accepted versus 8 is not a demonstrated gain: effort is incomplete, defect windows differ, task mix and learning may differ, and the sample is tiny. Missing records do not become zero cost or clean quality. Unresolved starts remain visible rather than being labeled failures. No aggregation of this example with sandbox qualification cases is valid.
|
||||
|
||||
### Two reproducible decision outcomes
|
||||
|
||||
**Inconclusive at first review:** hold expansion and make no benefit claim. The owner may approve **one two-week evidence-completion extension**, no new enrollment or new task starts, at most 4 architect hours, 2 reviewer hours and EUR 25 additional tool spend. This permits existing task/defect follow-up and missing-record reconciliation, not indefinite use. Record explicit authority/expiry and updated total cap. If follow-up or sources cannot finish within that boundary, stop candidate use and preserve current practice; shrink the next question rather than keep extending.
|
||||
|
||||
**Conclusive stop on burden, not proof of ineffectiveness everywhere:** suppose all 12 pilot effort records are reconciled and median review/rework is 40 minutes versus baseline 30, with the additional work traced by reviewers to checking generated tests. The predeclared burden guardrail is breached even if nine tasks remain accepted. Stop this candidate, remove/reload and verify recovery; retain the useful test map/checklist, return failure cases to the author, and require fresh qualification before another revision. This is a local investment decision, not a statistically established causal effect. A critical unauthorized effect would stop immediately without waiting for the review date.
|
||||
|
||||
**Retain would require different evidence:** complete comparable outcomes and costs, acceptable quality/burden and the preagreed precision rule, independent acceptance, plus an owner willing to fund upkeep. It authorizes only tested scope, never expansion to the whole company. Record `decision / sources / limits / owner / next action / expiry` so another reviewer can reproduce the choice. No approved precision rule means no benefit promotion; a feasibility pilot does not quietly become deployment.
|
||||
|
||||
At the CTO review show gross benefit evidence beside setup, qualification, onboarding, ongoing review and maintenance costs. Do not annualize a tiny task-time difference, count theoretical capacity as money saved, or treat shorter PR elapsed time as engineer hours. A cheaper checklist that performs as well wins. The standalone [synthetic calculator](./measurement/synthetic-example.mdx) tests arithmetic only; it is not EXP-01 evidence.
|
||||
|
||||
</details>
|
||||
|
||||
Supporting [skills lifecycle](./stage-01-skills-adoption.mdx) keeps the handoffs and six topic references together.
|
||||
|
||||
**Next:** [Beyond 6 Months →](./stage-02-autonomous-agent.mdx)
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,62 @@
|
||||
---
|
||||
id: six-months-target
|
||||
title: 6 Months Target
|
||||
sidebar_label: 6 Months Target
|
||||
description: Improve real engineering output through a solo, CTO-sponsored, team-partnered six-month learning plan.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**Proposed strategy · No company results or organizational commitments are claimed.**
|
||||
|
||||
## Improve the work, not the AI usage
|
||||
|
||||
<ArchifyDiagram name="strategy-six-months" title="Proposed six months: discover with teams, test one bottleneck, retain only supported value" story />
|
||||
|
||||
The assignment describes close to **80 engineers, growing to around 100 by year end, across more than 10 teams**. Every developer already uses AI, unevenly. I start **solo, reporting to the CTO, with no formal authority over teams**. The comparison is current AI-assisted practice—not an imagined no-AI organization. These facts come from *AI Architect Test Task*, Context and question 1; everything below is a proposal.
|
||||
|
||||
My first investment is time alongside developers and reviewers: find where useful changes stall, then remove one evidenced constraint. Delivery is a starting hypothesis because a bounded change, tests and independent review can expose both benefit and transferred work. Discovery may show that flaky CI, unclear requirements or review capacity matters more than agent instructions. Fix that bottleneck instead.
|
||||
|
||||
The [month-by-month plan](./six-months-roadmap.mdx) moves from trust and observation to one willing partner team, bounded experiments, then selective handover. I offer pairing and show verified examples rather than mandate tools. The CTO sponsors access and resolves priority conflicts; team leads agree contributions. Neither sponsorship nor this document conscripts a team.
|
||||
|
||||
## Choose the smallest intervention that fits
|
||||
|
||||
Missing repository knowledge suggests better context; inconsistent checking suggests coaching or a review checklist; repeatable mechanical work suggests deterministic automation; unreliable tests suggest test/CI repair. A **skill** packages reusable instructions, prerequisites and verification steps when repeated agent-guided work genuinely needs them. It is one option, not permission and not proof of correctness. Compare alternatives against the same bottleneck before funding a catalog or control platform.
|
||||
|
||||
Use the [worked experiment](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) to connect a hypothesis, small initial measures, safety checks and a retain/change/stop decision. Existing review, data restrictions and release authority stay in place. The [16 metric contracts](./measurement/index.mdx) and skills references are optional depth, not startup bureaucracy.
|
||||
|
||||
## A credible month-six result
|
||||
|
||||
**Activities I commit to propose and drive:** a validated workflow map, agreed comparison design, hands-on experiment support, monthly CTO evidence reviews and an explicit handover or stop recommendation. Delivery depends on agreed access and partner capacity; blocked work is reported, not disguised as progress.
|
||||
|
||||
**Contingent visible outcome:** one workflow retained by one partner team, with a second willing team trying a bounded transfer only if value and support hold. Developers can reproduce the example; reviewers see better evidence without extra hidden burden; a voluntary champion and backup can maintain it. Evidence must include comparable task records, independent acceptance, matured defect follow-up, review/rework effort, setup and upkeep costs, and a decision signed by the actual owner. These are required evidence types, not results already obtained or promised percentage gains. If the pilot fails, month six should instead show what was stopped, why, and which cheaper intervention replaced it. Neither scenario means rollout to all 80–100 engineers.
|
||||
|
||||
## Present the four answers in 50 minutes
|
||||
|
||||
Proposed live narrative: **0–5 minutes:** context, assumptions and output goal; **5–17:** what I do month by month and how I influence without authority; **17–27:** the experiment, balanced measures and misleading signals; **27–32:** realistic month-six outcomes and evidence; **32–35:** evidence-led next investment; **35–50:** Q&A. This is **35 minutes content + 15 minutes Q&A**, not an assignment-imposed split. Content matters more than visual polish. Walk the main story, then open references only for questions.
|
||||
|
||||
Beyond six months, choose deeper improvement, careful replication, additional enablement capacity or stopping an ineffective approach. [Beyond 6 Months](./stage-02-autonomous-agent.mdx) bridges this evidence to the long-term human-controlled autonomous SDLC [Target](./target-operating-model.mdx). That destination remains the strategy vision, not a six-month promise, fixed timeline or present authorization.
|
||||
|
||||
<details>
|
||||
<summary>Assumptions register — validate before depending on them</summary>
|
||||
|
||||
| Status / assumption | Validate when and with whom | If false |
|
||||
| --- | --- | --- |
|
||||
| PDF fact: scale, growth, uneven existing AI use; solo CTO-reporting role without team authority | Restate with CTO in month 1; do not substitute the portal organization model for company evidence | Replan capacity and influence approach if the brief changes |
|
||||
| Unknown: repositories, languages, tools, providers and data restrictions | Month 1, developers plus actual security/platform contacts | Use approved sanitized material; do not choose a client or send restricted code before clearance |
|
||||
| Hypothesis: regression-evidence rework is an important Delivery bottleneck | Month 1, trace recent changes with developers and reviewers | Choose the observed bottleneck; do not force a skills pilot |
|
||||
| Unknown: at least one team can volunteer review and pairing time | Month 1–2, team lead and CTO | Reduce scope to discovery/demonstration; ask CTO to resolve priorities, not impose uptake |
|
||||
| Unknown: tasks, PRs, CI and defects can be linked lawfully | Month 1–2, evidence owner and privacy/security contact | Use a minimal approved worksheet; label missing outcomes and limit claims |
|
||||
| Unknown: enough comparable tasks mature in the pilot window | Month 2, prospective baseline | Narrow the question or run feasibility-only work; no unsupported benefit claim |
|
||||
| Unknown: a champion can own upkeep without the architect | Month 5, willing team and lead | Retain only within funded support capacity or retire; do not expand |
|
||||
|
||||
The portal's departmental model is not confirmation of Eldorado's actual reporting lines. Reference-role names below are candidate functions to map to real people, not appointed authorities.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [6 Months Roadmap →](./six-months-roadmap.mdx)
|
||||
|
||||
</div>
|
||||
@@ -11,9 +11,11 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
|
||||
Optional reference when skills are the chosen intervention. The [6 Months Roadmap](./six-months-roadmap.mdx) starts with willing partners and current AI-assisted practice; department names below are proposed functions to agree, not appointments. The assembled [EXP-01 packet](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) shows first-revision recovery, total effort, an inconclusive bounded extension and a stop decision.
|
||||
|
||||
## When should a pilot become a team workflow?
|
||||
|
||||
Expand only when a bounded canary produces independently accepted work and useful feedback. Teach people to verify artifacts and recover without AI, not merely invoke a skill.
|
||||
Expand only when a bounded canary produces independently accepted work and useful feedback. Teach people to verify artifacts and recover without AI, not merely invoke a skill. Compare **Workflow effectiveness** with the current-workflow baseline; observe **Skills effectiveness & health** separately as skills enter use. More adoption does not prove improved work, and before/after trends alone are not causal evidence.
|
||||
|
||||
<ArchifyDiagram name="strategy-adoption" title="Choose a workflow, coach a canary, verify outcomes and improve before expansion" story />
|
||||
|
||||
@@ -21,10 +23,23 @@ Expand only when a bounded canary produces independently accepted work and usefu
|
||||
- **Choice within support:** qualify the client path instead of promising identical agent behavior.
|
||||
- **No adoption quotas:** retain a manual path; rejected suggestions and non-use are feedback, not poor performance.
|
||||
|
||||
## Run one bounded comparison, then make a decision
|
||||
|
||||
Bring the [Baseline](./baseline.mdx) comparison record, [Quality](./skills-quality.mdx) qualification report and [Governance](./skills-governance.mdx) pilot authorization—not merely an installed bundle. In the **illustrative Delivery workflow**, the developer and AI Agent prepare a bounded patch and regression tests on the qualified client; an independent reviewer accepts or rejects the exact work. Existing release controls still apply. Record failed and abandoned work as well as accepted changes, and use the manual path if the skill adds risk or effort.
|
||||
|
||||
At the agreed review point, the designated Product Engineering workflow owner considers the comparable outcomes and feedback, Quality Engineering's independent acceptance/quality evidence and any boundary or support findings from Architecture & Security and Platform & IT. These are proposed responsibilities; appoint actual people and agree criteria before the pilot.
|
||||
|
||||
- **Retain:** useful within the tested scope and supported controls; the designated owning approver records exact-revision approval after independent review and required boundary/support checks, then hands that revision and evidence to [Maintenance](./skills-maintenance.mdx). The pilot decision alone is not general approval.
|
||||
- **Improve:** return failure cases and friction to the author and [Quality](./skills-quality.mdx); a changed candidate needs new evidence.
|
||||
- **Expand:** propose a new bounded workflow/cohort, revisit [Baseline](./baseline.mdx) and obtain the relevant approval—not automatic organization-wide rollout.
|
||||
- **Stop or hold:** unsafe behavior triggers containment; insufficient evidence means no benefit claim and no justified expansion. Preserve current practice or a safe manual path. Any extension needs a new explicit expiry, capacity/spend cap and attainable evidence question; otherwise narrow or stop, never continue indefinitely.
|
||||
|
||||
The output is a decision record with evidence, scope and remaining uncertainties. Qualification fitness and live outcomes inform it separately; apparent before/after improvement does not establish causality.
|
||||
|
||||
<details>
|
||||
<summary>Onboarding responsibilities, coaching and feedback safeguards</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
**TO-BE · Target operating model.** This bounded comparison belongs to the [Stage 01 journey](./stage-01-skills-adoption.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
Start with a small set of useful workflows chosen by the existing teams. Product Management and the departmental owner identify the outcome; Data & AI helps turn it into a skill; Quality Engineering establishes acceptance; Platform & IT qualifies the client path; Architecture & Security clears the data boundary. People & Administration Squad coordinates learning and accessible feedback.
|
||||
|
||||
@@ -36,6 +51,38 @@ No developer rankings, individual productivity scores, minimum invocation quotas
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Measure accepted outcomes, not activity →](./measurement.mdx)
|
||||
<details>
|
||||
<summary>Pilot evidence, illustrative report and expansion</summary>
|
||||
|
||||
## Apply the selected measures in the pilot
|
||||
|
||||
Use the relevant subset agreed in [Baseline](./baseline.mdx), not every entry in the [Measurement registry](./measurement/index.mdx). Keep its eligibility, independent acceptance and follow-up rules. Capture inputs as work happens; record exact skill revision and client configuration, leaving missing versions unknown. Do not reconstruct review effort from elapsed PR time.
|
||||
|
||||
The following questions are candidates, not a mandatory pilot bundle. Proposed owners and cadences need agreement before collection:
|
||||
|
||||
| If this question is selected | Evidence and pilot review |
|
||||
| --- | --- |
|
||||
| Are tasks reaching acceptance? | Join tracker starts to independent acceptance, failure and abandonment. Apply [validated task success](./measurement/validated-task-success.mdx) to matured starts; retain failed, abandoned and unresolved tasks in the denominator and show unknown outcomes and coverage. Proposed weekly reviewer: Quality Engineering. |
|
||||
| Is quality holding up? | Link accepted changes to confirmed defects, severity and follow-up dates; retain PR/CI evidence. Apply [escaped quality](./measurement/changes-with-escaped-quality-issues.mdx) after follow-up, counting each affected change once, alongside severe incidents. Missing links are not clean work. Proposed monthly reviewer: Quality Engineering. |
|
||||
| What does an accepted outcome cost? | Reconcile invoices and usage, sampled review/rework minutes at approved rates, unsuccessful attempts and allocated licenses/tooling. Apply [cost per accepted outcome](./measurement/cost-per-accepted-outcome.mdx) to the same matured start cohort; distinguish effort from waiting. Missing buckets make the estimate partial. Proposed monthly reviewer: Finance & Accounting; restate late invoices. |
|
||||
| Can people confidently verify the work? | Use the anonymous 1–5 survey for confidence, manageable workload and usefulness as separate items. Report the [confidence measure](./measurement/verification-confidence-and-cognitive-load.mdx), distribution and response rate; protect small groups. Proposed reviewer after each pilot cycle: People & Administration. This is enablement evidence, not proven saved time. |
|
||||
|
||||
### What a pilot report looks like
|
||||
|
||||
**Illustrative arithmetic, not company results or targets.** The bundled synthetic fixture shows four matured starts: one accepted, one failed, one abandoned and one unresolved. Confirmed success is **1 / 4 × 100 = 25%**, with **75%** known-outcome coverage. A newer start has not finished its observation period and is shown separately.
|
||||
|
||||
Recorded compute spend is **EUR 60 / 1 = EUR 60** per accepted outcome—a **partial estimate** because licenses, tooling, review and rework are missing. Five survey responses total 20 points: **20 / 5 = 4** out of 5; response rate is **5 / 10 × 100 = 50%**. Reconcile the unknown task and missing costs instead of claiming a skills benefit. Reproduce it with `node scripts/ai-kpi.mjs`; [fixture and limits](./measurement/synthetic-example.mdx).
|
||||
|
||||
### Revisit selection as adoption expands
|
||||
|
||||
Selection precision/recall qualify named skill versions against labeled cases; they do not measure real-workflow acceptance. Keep any skill/version evaluation separate from the live task-success cohort. Skill-specific measures with no applicable population are N/A, not zero; missing evidence for an existing population remains unknown.
|
||||
|
||||
Keep relevant outcome evidence comparable; add reach measures only if they answer the expanded workflow's questions. For [supported bundle coverage](./measurement/supported-bundle-coverage.mdx), freeze the expected active installation inventory and compare observed bundle/adapter revisions to support and revocation records. Offline or stale entries stay in the denominator. Platform & IT is the proposed weekly and at-revocation reviewer.
|
||||
|
||||
For [approved-workflow adoption](./measurement/approved-workflow-adoption.mdx), freeze the lawfully enrolled participant cohort and distinguish qualified-adapter observations from labeled declarations. Report the observed lower bound with source coverage: missing use is unknown; installation and loading are not use. Data & AI is the proposed monthly reviewer. No invocation quotas or employee rankings. Return to Baseline for a new workflow rather than treating rollout as company-wide metric collection.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Maintain skills using the agreed evidence →](./skills-maintenance.mdx)
|
||||
|
||||
</div>
|
||||
@@ -13,7 +13,7 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
## Who can approve a skill for use?
|
||||
|
||||
The owning team authors the skill; independent reviewers assess it before exact-revision approval. Data & AI maintains the catalog, while Platform & IT verifies distribution and revocation.
|
||||
Use this optional reference only if the [six-month experiment](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) selects skills. The architect can author with a willing team; an independent reviewer assesses the candidate and the actual workflow approver authorizes bounded use. Departmental names below are proposed functions, not company facts or conscripted staff. A reviewed repository entry plus existing controls can support one pilot; no enterprise catalog service is required first.
|
||||
|
||||
<ArchifyDiagram name="strategy-governance" title="An owner proposes; independent review and canary evidence precede approval" story />
|
||||
|
||||
@@ -21,10 +21,18 @@ The owning team authors the skill; independent reviewers assess it before exact-
|
||||
- **Pin the whole bundle:** content, adapters and executable dependencies travel together.
|
||||
- **Keep controls authoritative:** exceptions expire and cannot bypass protected release, payment or identity controls.
|
||||
|
||||
## Connect knowledge without expanding authority
|
||||
|
||||
Use the workflow map from [Baseline](./baseline.mdx) to engineer a connected skills topology. In the **illustrative Delivery workflow**, repository understanding produces a source-and-constraints map; change/test preparation consumes it and produces a patch plus regression evidence; independent verification consumes that exact artifact and returns findings. Each handoff specifies its trigger, expected output and what happens when evidence is missing. The agent cannot mark its own work approved or acquire deployment credentials through a skill.
|
||||
|
||||
Governance spans design, qualification, the pilot and maintenance—not just entry to a catalogue. The owning Product Engineering team's designated accountable person records scope and permitted effects; an independent Quality Engineering reviewer accepts [evaluation evidence](./skills-quality.mdx); Architecture & Security reviews higher-risk boundaries; Platform & IT verifies the qualified distribution path. These are recommended assignments within existing teams: name the actual people before relying on a decision.
|
||||
|
||||
**Two different permissions:** qualification may justify a bounded experimental pilot. Wider approved use requires the pilot comparison and canary evidence too. Record exact revisions, audience, expiry/stop conditions and approvers for each; neither a baseline nor a passing test grants permission by itself. Failed review returns the candidate to its author; unsafe use enters [Maintenance containment](./skills-maintenance.mdx).
|
||||
|
||||
<details>
|
||||
<summary>Ownership, client qualification, exceptions and rollback</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
**TO-BE · Target operating model.** Use these contracts throughout the [Stage 01 journey](./stage-01-skills-adoption.mdx); they are not installed controls or measured company results.
|
||||
|
||||
### A contract that travels, controls that stay authoritative
|
||||
|
||||
@@ -36,7 +44,7 @@ Adapters place content in the qualified client's discovery paths and implement o
|
||||
|
||||
### Lifecycle and decision rights
|
||||
|
||||
A proposal names the problem, owner, data scope and testable outcome. Experimental revisions run only in approved disposable environments. Promotion requires independent review, static and executable dependency checks, per-client behavioral evaluations and a bounded canary. Approval records bind the exact artifact and permitted uses. Deprecated revisions carry a migration path and deadline; retired revisions are unavailable for new work. Any active revision can be quarantined immediately.
|
||||
A proposal names the problem, owner, data scope and testable outcome. Initial experimental qualification runs only in approved disposable environments. Real work requires a separate bounded-pilot authorization after qualification; that authorization permits only its recorded cohort, data and effects, not general approved use. Promotion from the bounded pilot requires independent review, static and executable dependency checks, per-client evaluations, pilot outcomes and canary evidence. Approval records bind the exact artifact and permitted uses. Deprecated revisions carry a migration path and deadline; retired revisions are unavailable for new work. Any active revision can be quarantined immediately.
|
||||
|
||||
The author never supplies the only approval. Data & AI maintains catalog state; the owning team is accountable for content; Quality Engineering approves evaluation evidence; Architecture & Security approves higher-risk boundaries; Platform & IT verifies distribution and revocation. A business owner accepts workflow outcomes. These functions can be covered by existing staff, but incompatible author/approver duties must remain separate for the same release.
|
||||
|
||||
@@ -44,11 +52,11 @@ An exception contains its ID, skill/client revision, scope, business reason, ris
|
||||
|
||||
### Distribution, stale clients and rollback
|
||||
|
||||
Stage a verified bundle atomically, check its digest, load it through the qualified adapter and read back its effective revision. Test already-open sessions; changing files is not proof of reloading instructions. Record immutable last-known-good content and adapter dependencies. Canary upgrades precede wider distribution.
|
||||
Stage a verified bundle atomically, check its digest, load it through the qualified adapter and read back its effective revision. Test already-open sessions; changing files is not proof of reloading instructions. Record immutable last-known-good content and adapter dependencies where an approved revision exists. For a first revision, record **N/A: no approved bundle** and the [Quality first-revision rule](./skills-quality.mdx): compare with declared current AI-assisted practice; test disable/remove, invalidate/reload sessions and verify recovery in a pinned clean environment. Independent reviewer acceptance and actual workflow-approver pilot permission are still required. Canary upgrades precede wider distribution.
|
||||
|
||||
A cached verified bundle may support explicitly permitted low-risk work if its model and tool dependencies are available. It does not make a cloud-backed client work offline. Stale or unsupported sessions cannot obtain centrally mediated privileged access. Reconnection revalidates support, revocation and policy before credentials are issued. Central artifact review protects delivery even when a laptop declaration is absent or false; a client report cannot prove which private prompt was actually followed.
|
||||
|
||||
Rollback restores the approved manifest and dependencies, invalidates affected sessions, revokes unsafe revisions, runs a smoke test and verifies effective state. It cannot undo data disclosure or commands already executed. Those require incident response.
|
||||
Rollback restores the approved manifest and dependencies when present; first-revision recovery removes the candidate and restores declared current practice without inventing a prior approved skill. Invalidate affected sessions, revoke unsafe revisions, run a smoke test and verify effective state. Recovery cannot undo data disclosure or commands already executed. Those require incident response.
|
||||
|
||||
</details>
|
||||
|
||||
@@ -77,7 +85,7 @@ Rollback restores the approved manifest and dependencies, invalidates affected s
|
||||
| provenance_license | Origin repository/author, upstream revision, acquisition/review history, rights/license for content and bundled resources |
|
||||
| maintenance_date | Last substantive review timestamp plus next review due and trigger conditions |
|
||||
| deprecation | State, reason, replacement, migration instructions, consumers and retirement deadline if applicable |
|
||||
| rollback | Approved known-good bundle+adapter+dependency digests, revocation/reload procedure and tested evidence |
|
||||
| rollback | Approved known-good bundle+adapter+dependency digests when present; first revision: N/A with reason plus tested disable/remove/reload to pinned clean current practice; independent acceptance required |
|
||||
| procedure | Prerequisites, bounded steps, expected artifacts, verification, failure handling, escalation |
|
||||
|
||||
|
||||
@@ -91,7 +99,8 @@ Rollback restores the approved manifest and dependencies, invalidates affected s
|
||||
| Transition | Required evidence |
|
||||
| --- | --- |
|
||||
| proposed → experimental | Owner, purpose, risk/data scope, disposable environment and preregistered test plan |
|
||||
| experimental → approved | Independent review, all mandatory tests, qualified clients, canary, exact-digest approval |
|
||||
| experimental → bounded pilot | Independent qualification evidence, named pilot approver, exact revision, bounded cohort/data/effects and manual recovery; remains experimental outside that envelope |
|
||||
| bounded pilot → approved | Independent review, all mandatory tests, qualified clients, pilot comparison and canary evidence; owning approver records exact-digest authorization for retained scope |
|
||||
| approved → deprecated | Owner gives migration/replacement and retirement conditions |
|
||||
| deprecated → retired | Consumers reconciled or explicit risk-approved cutover; no new invocation |
|
||||
| any active state → quarantined | Incident or unsafe/unknown provenance; central deny immediately |
|
||||
|
||||
@@ -11,20 +11,30 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
|
||||
Optional skills reference for a retained intervention, not a six-month obligation to establish a catalog program. Map department names to actual agreed functions. The [6 Months Roadmap](./six-months-roadmap.mdx) requires funded upkeep and a willing owner before expansion.
|
||||
|
||||
## What happens when a skill drifts or causes harm?
|
||||
|
||||
Monitor usefulness and safety throughout a revision's life. Unsafe behavior triggers containment; a correction returns through independent tests and approval, never automatic reinstatement.
|
||||
Monitor both **Workflow effectiveness** (comparable outcomes, safety, cost and human experience) and **Skills effectiveness & health** (fitness/regression evidence, selection, supported use and substantive review) throughout a revision's life. Use the evidence to improve, retain or retire skills; adoption or current review dates alone do not prove better work. Unsafe behavior triggers containment; a correction returns through independent tests and approval, never automatic reinstatement.
|
||||
|
||||
<ArchifyDiagram name="strategy-maintenance" title="Monitor, triage and test corrections; promote safely or contain and roll back" story />
|
||||
|
||||
- **Named ownership:** Data & AI coordinates catalog health with the owning teams.
|
||||
- **Early triggers:** incidents and client, model or dependency changes override the calendar.
|
||||
- **Recovery is verified:** rollback restores a known-good bundle; it cannot undo disclosure or past effects.
|
||||
- **Recovery is verified:** restore a known-good bundle when present; first-revision recovery disables/removes the candidate, invalidates/reloads sessions and verifies declared current AI-assisted practice in a pinned clean environment. Record no-approved-revision N/A and independent acceptance under the [Quality rule](./skills-quality.mdx); recovery cannot undo disclosure or past effects.
|
||||
|
||||
## Close the loop on the retained workflow
|
||||
|
||||
Start from [Adoption's decision](./skills-adoption.mdx), the approved manifest and its evidence limits. In the **illustrative Delivery workflow**, a missed regression case becomes a sanitized evaluation case. Product Engineering owns the correction; an independent Quality Engineering reviewer reruns [Quality's fitness and regression evaluation](./skills-quality.mdx) against the approved revision. Keep the live defect and task records in their original populations; do not erase a failure because the replacement passes.
|
||||
|
||||
The owning team's designated approver decides whether the corrected exact revision can re-enter a bounded canary, using independent results and Platform & IT's recovery/effective-version evidence; Architecture & Security reviews changed risk boundaries. Missing evidence means hold. Safe unchanged use may continue only within its existing authorization; harmful behavior is contained immediately. These recommended functions require named people before use.
|
||||
|
||||
Retain a supported revision, requalify a change or retire it with a reconciled consumer/migration record. A materially changed workflow returns to [Baseline](./baseline.mdx); the [Measurement registry](./measurement/index.mdx) helps revise relevant evidence without silently resetting history. That feedback closes [Stage 01](./stage-01-skills-adoption.mdx)—it does not automatically advance to autonomy.
|
||||
|
||||
<details>
|
||||
<summary>Review responsibilities, incident handling and proposed review intervals</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
**TO-BE · Target operating model.** Maintenance sustains the [Stage 01 journey](./stage-01-skills-adoption.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
Every approved skill has an accountable owning team, independent reviewer, review due date, supported client matrix and rollback bundle. Review both usefulness and safety, not just metadata freshness. Proposed maximum review intervals are recorded by risk tier; incidents, dependency changes, model/client drift or repeated failures trigger earlier review.
|
||||
|
||||
@@ -44,6 +54,21 @@ Owner ratification is required before adoption. Review earlier after incidents o
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Use exit evidence to choose the next rollout stage →](./roadmap.mdx)
|
||||
<details>
|
||||
<summary>Ongoing reporting and comparison</summary>
|
||||
|
||||
## Keep selected evidence useful
|
||||
|
||||
Continue the measures agreed for the workflow in [Baseline](./baseline.mdx) and applied during [Adoption](./skills-adoption.mdx). Revisit relevance when scope changes; the [registry](./measurement/index.mdx) is a source of choices, not a requirement to collect every metric. Preserve current-workflow comparisons separately from named skill/version evaluations. No applicable skill population is N/A, not zero; missing evidence for existing revisions is unknown and must not improve reported health.
|
||||
|
||||
If substantive-review coverage is selected, join each active approved catalog revision to its owner, substantive review evidence and due date. Apply [review coverage](./measurement/skills-within-substantive-review-window.mdx): revisions with all three current / all active approved revisions × 100. The proposed Data & AI review is monthly and at each release, subject to agreement. Report overdue/ownerless revisions and deprecated or revoked versions still in use—not just a percentage.
|
||||
|
||||
At each agreed report, compare like workflows with their recorded starting position. Publish period, counts, exclusions, source coverage and changes in calculation or scope. Zero denominators mean “not available”; unresolved gaps remain visible. Trends are descriptive, not causal ROI. Reconcile late evidence using versioned corrections and distinguish changed practice from changed measurement.
|
||||
|
||||
Act on critical policy effects immediately; do not wait for a reporting cycle. Use selection precision/recall at qualification, or service-level delivery and departmental outcome measures, only where relevant and their source links are feasible. Confirm purpose, lawful basis, access and retention before changing collection, following the [shared safeguards](./measurement/collection-and-safeguards.mdx).
|
||||
|
||||
</details>
|
||||
|
||||
**Continue the loop:** [Requalify changed skills →](./skills-quality.mdx). For a separate future authority decision, read [Beyond 6 Months](./stage-02-autonomous-agent.mdx).
|
||||
|
||||
</div>
|
||||
@@ -11,6 +11,8 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
**TO-BE · Target operating model — not installed controls or company results.**
|
||||
|
||||
**Optional skills reference for the [6 Months Roadmap](./six-months-roadmap.mdx).** Use this when skills are the chosen intervention, not as a prerequisite for discovery or coaching. Department names denote functions to map to actual willing staff; the architect cannot assign them authority.
|
||||
|
||||
## What evidence is enough to promote a skill?
|
||||
|
||||
Risk determines the evaluation depth, not whether safety checks apply. Independent evidence must show useful outcomes and no failed mandatory gate before promotion.
|
||||
@@ -21,10 +23,22 @@ Risk determines the evaluation depth, not whether safety checks apply. Independe
|
||||
- **No averaging away harm:** a critical unauthorized effect blocks promotion.
|
||||
- **Proposed floors need owner ratification:** missing coverage or acceptance rules means qualification is incomplete.
|
||||
|
||||
## Prove the candidate fits the workflow
|
||||
|
||||
Bring the workflow/acceptance map from [Baseline](./baseline.mdx) and the pinned candidate, client tuple and authority envelope from [Governance](./skills-governance.mdx). In the **illustrative Delivery workflow**, test whether a candidate actually produces a correct bounded change and regression tests—not just whether it was selected. Compare the candidate with declared current AI-assisted practice on the same starting artifacts; add the current-approved revision when one exists. Include misleading repository instructions, missing tests and requests to bypass review.
|
||||
|
||||
**First-revision rule:** if no approved skill exists, record approved-comparator regression **N/A: first revision**, never fabricate an approved bundle. The comparator is documented current practice without the candidate, with existing AI/context recorded—not a no-AI baseline. Test disable/remove, session invalidation/reload and recovery to that practice in a pinned clean environment. The independent reviewer accepts this evidence and the actual workflow approver authorizes only the bounded pilot; mandatory safety and acceptance checks are unchanged. Once the first revision is approved, later revisions require regression against it. See [EXP-01](./stage-01-skills-adoption.mdx) for the assembled packet.
|
||||
|
||||
The independent Quality Engineering reviewer records accepted and failed artifacts, safety results, coverage and regression differences for each named revision. The owning team's designated approver then decides whether that evidence supports a bounded pilot; Architecture & Security must accept any higher-risk boundary. A mandatory failure or an unagreed acceptance rule means rework or hold. These are proposed decision responsibilities, not already assigned people.
|
||||
|
||||
**Qualification artifact success is not live task success.** The evaluation denominator is planned executed trials, retaining failures and abandonment, with omitted/unexecuted cases shown as coverage gaps. [Validated task success](./measurement/validated-task-success.mdx) instead uses matured real-workflow starts. Never pool them. [Measurement](./measurement/index.mdx) links selection and health signals to this fitness evidence; neither usage nor a fresh review date proves effectiveness.
|
||||
|
||||
The output is a versioned qualification report and explicit limitations for [Adoption](./skills-adoption.mdx), not approval of every future task. [Maintenance](./skills-maintenance.mdx) feeds real failures and material client/model/dependency changes back into this same evaluation, including regression against the currently approved revision.
|
||||
|
||||
<details>
|
||||
<summary>Evaluation design, adversarial cases and interpretation</summary>
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
**TO-BE · Target operating model.** Qualification supports the [Stage 01 journey](./stage-01-skills-adoption.mdx); these pages do not describe installed controls or measured company results.
|
||||
|
||||
Quality has four separate questions: was the right skill selected, was the procedure executed safely, did the artifact pass independent checks, and did the workflow produce useful outcomes? A successful invocation answers none of the remaining questions by itself.
|
||||
|
||||
@@ -32,7 +46,7 @@ The proposed qualification contract uses three tiers. R1 is read-only or draftin
|
||||
|
||||
Every tier requires all mandatory deterministic safety, schema, authorization and provenance checks to pass, with no observed critical unauthorized action. An observed critical effect blocks promotion. The proposed pilot evaluation floors below set success thresholds; these are design defaults for owner ratification, not externally validated guarantees or approved service levels. If sample coverage, acceptance criteria or responsible reviewers are missing, qualification remains incomplete. No aggregate score can trade off a failed mandatory safety check.
|
||||
|
||||
Use sanitized, predeclared task sets containing positive triggers, near misses, negative cases and the normal workload mix. Compare no-skill, current-approved and candidate paths with the same starting artifacts; repeat stochastic trials and retain failed and abandoned attempts. Independently inspect output state. Deterministic tests grade checkable constraints; calibrated humans grade usefulness, maintainability and experience. A model judge is supplementary, versioned and checked against human disagreements, never the sole safety or promotion authority.
|
||||
Use sanitized, predeclared task sets containing positive triggers, near misses, negative cases and the normal workload mix. Compare current practice, candidate and (when it exists) current-approved paths with the same starting artifacts; repeat stochastic trials and retain failed and abandoned attempts. A no-standardized-skill path may still use AI. Independently inspect output state. Deterministic tests grade checkable constraints; calibrated humans grade usefulness, maintainability and experience. A model judge is supplementary, versioned and checked against human disagreements, never the sole safety or promotion authority.
|
||||
|
||||
Include adversarial repository text, malicious referenced code, wrong permissions, client toggles, name shadowing, unsupported versions, hook timeout/crash/malformed response, stale sessions, offline recovery and rollback. Run central checks against forged/missing client declarations. Hook presence is not fail-closed enforcement: failure semantics must be tested on each client, and central authorization remains independent.
|
||||
|
||||
@@ -45,7 +59,7 @@ Report denominators, task mix, trial counts, per-client results and uncertainty.
|
||||
|
||||
## Proposed qualification floors
|
||||
|
||||
These are local design defaults for responsible-owner ratification, not approved service levels or guarantees. All mandatory checks must pass regardless of aggregate score.
|
||||
These are optional reference designs, not mandatory startup floors, approved service levels or guarantees. Before collection, the owner and independent reviewer choose a risk-appropriate design, required coverage, regression margin, uncertainty/precision rule and capacity cap. Start with one workflow and one client configuration. Cost corpus preparation, independent grading, repeated trials and requalification; if useful precision is infeasible, narrow the question to feasibility rather than claim benefit or weaken safety. All mandatory checks must pass regardless of aggregate score. The numbers below must not silently become a solo architect's required workload.
|
||||
|
||||
### R1
|
||||
|
||||
@@ -77,7 +91,7 @@ These are local design defaults for responsible-owner ratification, not approved
|
||||
|
||||
**Selection precision / recall** — 99% / 95%
|
||||
|
||||
Artifact success denominator is every planned executed trial, retaining failures and abandonment. Trials of same task are correlated: show per-task and per-client strata; do not inflate independent sample size. Selection floors use independent labels. Report 95% uncertainty intervals clustered by task for outcome comparisons; no regression versus current approved path beyond a preregistered owner-approved margin. Missing margin/precision rule prevents promotion.
|
||||
Artifact success denominator is every planned executed trial, retaining failures and abandonment. Trials of same task are correlated: show per-task and per-client strata; do not inflate independent sample size. Selection floors use independent labels. Report 95% uncertainty intervals clustered by task for outcome comparisons; no regression versus the current approved path, when one exists, beyond a preregistered owner-approved margin. First-revision approved regression is N/A with reason, but current-practice acceptance and safety remain mandatory. Missing applicable margin/precision rule prevents promotion. Small feasibility studies cannot establish that rule after seeing favorable results.
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
---
|
||||
id: stage-01-skills-adoption
|
||||
title: Skills lifecycle reference
|
||||
description: Work through an illustrative Delivery experiment from current AI-assisted practice to an evidence-based decision.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
Improve one workflow through human + AI Agent work, then repeat with evidence. This is the practical experiment supporting the [6 Months Roadmap](./six-months-roadmap.mdx), not a mandatory skills program or permission to deploy the long-term autonomous [Target](./target-operating-model.mdx). Use context, coaching, test/review feedback or deterministic automation if they better address the bottleneck.
|
||||
|
||||
<ArchifyDiagram name="strategy-stage01" title="One workflow: establish the starting point, engineer and qualify, pilot, decide, maintain and learn" story />
|
||||
|
||||
**Read the arrows as handoffs, not a checklist of page approvals.** Governance bounds every activity. Measurement supplies selected definitions throughout. Quality establishes candidate fitness; Adoption tests usefulness in real work; Maintenance returns failures and changed conditions to qualification.
|
||||
|
||||
The [6 Months Roadmap](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) owns EXP-01 and the month-by-month plan; this reference only explains reusable lifecycle handoffs within the broad [Roadmap](./roadmap.mdx).
|
||||
|
||||
## Delivery first: one change, from intent to accepted work
|
||||
|
||||
**Illustrative Delivery workflow throughout these pages — not an Eldorado pilot or measured result:** a Product Engineering developer uses an AI Agent to prepare a bounded code change and regression tests. An independent reviewer checks the exact change and evidence. Existing release authority remains unchanged; the skill cannot approve or deploy its own output.
|
||||
|
||||
First trace codebase structure and existing principles → system-logic source → tests → builds and packaging → deployments. Identify the friction to improve—for example, incomplete regression evidence that sends changes back for rework. Verify that this is the actual problem before choosing a skill.
|
||||
|
||||
Adoption can extend to other SDLC phases; their order is not yet decided. Delivery keeps improving as adoption expands.
|
||||
|
||||
## Carry evidence forward, not assumptions
|
||||
|
||||
1. **Understand and baseline.** Product Engineering maps the selected workflow and desired improvement. Select relevant KPIs from [Measurement](./measurement/index.mdx); [Baseline](./baseline.mdx) records current outcomes, acceptance rules and explicit gaps. A baseline describes work; it grants no approval.
|
||||
2. **Choose the smallest candidate.** If repeated agent guidance is the bottleneck, use [Governance](./skills-governance.mdx) to connect repository understanding → change/test preparation → independent verification. Specify triggers, inputs, outputs, handoffs, pinned dependencies and forbidden actions. This skills topology is more than a catalogue; a deterministic fix may need no skill.
|
||||
3. **Qualify before exposing real work.** [Quality](./skills-quality.mdx) compares the candidate with declared current practice. If no approved skill exists, approved-revision regression is N/A with reason; test removal and recovery to current practice. Once an approved revision exists, add that comparator. The independent Quality Engineering reviewer function accepts evaluation evidence; the owning team's designated approver authorizes only the tested pilot envelope, with security review where risk requires it. Failed checks or missing authority mean rework or hold, not an automatic pilot.
|
||||
4. **Pilot and compare.** [Adoption](./skills-adoption.mdx) applies that revision to a bounded real-work cohort, retaining the manual path. Compare accepted outcomes, quality, review/rework cost and feedback with the starting position. Live tasks and qualification trials remain separate populations.
|
||||
5. **Decide and maintain.** The owning team's designated workflow owner decides retain, improve, stop or propose expansion from the comparison and independent evidence. [Maintenance](./skills-maintenance.mdx) keeps retained revisions supported and feeds defects into requalification. A new scope returns to Baseline; a changed revision returns to Quality. The new current situation starts the next loop.
|
||||
|
||||
These are recommended functions, not evidence of actual departments or appointed people. The architect may build and coordinate; a willing developer/reviewer and actual workflow owner agree contributions. One worksheet plus existing PR/CI records can suffice. Before work starts, record actual people, acceptance rules and permitted effects. Missing assignments keep the affected decision on hold.
|
||||
|
||||
<details>
|
||||
<summary>Where each topic helps—and what it gives the next activity</summary>
|
||||
|
||||
| Topic | Use it when | Carry forward |
|
||||
| --- | --- | --- |
|
||||
| [Measurement](./measurement/index.mdx) | Choosing or interpreting evidence at any point | Relevant contracts for Workflow effectiveness and Skills effectiveness & health; no mandatory full catalogue |
|
||||
| [Baseline](./baseline.mdx) | Understanding a workflow or a material scope change | Workflow map, selected definitions, evidenced starting position or gaps |
|
||||
| [Governance](./skills-governance.mdx) | Designing, approving, distributing or withdrawing any revision | Named accountability, authority envelope and exact-revision decision record |
|
||||
| [Quality](./skills-quality.mdx) | Introducing or changing skills, clients, models or dependencies | Versioned evaluation results, failures, limits and independent recommendation |
|
||||
| [Adoption](./skills-adoption.mdx) | Introducing a qualified candidate into bounded work | Comparable outcome report, user feedback and retain/improve/expand/stop decision |
|
||||
| [Maintenance](./skills-maintenance.mdx) | Keeping a supported workflow dependable | Reviewed revision, regression cases, recovery evidence or retirement |
|
||||
|
||||
The six topics are connected lifecycle activities, not six rigid sequential approval gates. The sidebar is a reading map: you can consult Measurement before, during or after any activity.
|
||||
|
||||
</details>
|
||||
|
||||
Proven skills and working practices may support [Beyond 6 Months](./stage-02-autonomous-agent.mdx). Stage 01 can remain valuable indefinitely; progression requires a separate case for authority and readiness.
|
||||
|
||||
**Start here:** [Understand and baseline one workflow →](./baseline.mdx). Consult the [Measurement registry](./measurement/index.mdx) when selecting evidence.
|
||||
|
||||
</div>
|
||||
@@ -0,0 +1,40 @@
|
||||
---
|
||||
id: stage-02-autonomous-agent
|
||||
title: Beyond 6 Months
|
||||
description: Bridge first-six-month evidence toward the long-term human-controlled autonomous SDLC, through separate investment and authority decisions.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
<div className="strategy-content">
|
||||
|
||||
**A separate authority decision, not the reward for skills adoption.**
|
||||
|
||||
The [6 Months Roadmap](./six-months-roadmap.mdx) ends with a CTO investment decision, not automatic progression. The [experiment](./six-months-roadmap.mdx#exp-01-a-small-decision-ready-example) may justify deeper improvement, selective replication, or stopping. The autonomous [Target](./target-operating-model.mdx) remains the long-term strategy vision; humans retain direction and review. The broad [Roadmap](./roadmap.mdx) connects skills and working practices to controlled autonomous capabilities. Six-month outcomes contribute toward that destination, but do not promise its timing or authorize its execution.
|
||||
|
||||
If one workflow works but transfer fails, invest in local context and coaching rather than mandate uniform use. If several teams request help and recurring value exceeds support burden, propose dedicated enablement capacity with the CTO and team leads. If deterministic tooling solves the problem more reliably, fund that. If outcomes remain inconclusive, narrow or stop the intervention. Recheck the next-quarter portfolio against business priorities, task supply, team willingness and ownership; do not extrapolate a pilot to all engineering.
|
||||
|
||||
<ArchifyDiagram name="strategy-stage02" title="Future authority: evidence and human decision before bounded execution, with independent stop and takeover" story />
|
||||
|
||||
## Consider additional authority only when necessary
|
||||
|
||||
Carry forward proven skills where useful, measurements and working practices from real human + AI Agent work. The references provide [governance](./skills-governance.mdx), [quality checks](./skills-quality.mdx), [adoption feedback](./skills-adoption.mdx), [measurement](./measurement/index.mdx) and [maintenance](./skills-maintenance.mdx); none is permission to expand authority automatically. The diagram above applies only after a separate business case identifies an operation that supervised work or deterministic automation cannot adequately address.
|
||||
|
||||
## Introduce authority deliberately
|
||||
|
||||
Establish reliable observation and evidence assembly, then proposing and routing work, before granting scoped execution authority. In the **illustrative Delivery workflow**, preparing a patch under human supervision does not authorize the central agent to merge or deploy it. A proposal must explain which extra operation is needed, why Stage 01 is insufficient, the exact resources/data it may touch and how humans can stop it.
|
||||
|
||||
The owning department's designated accountable approver decides the proposed workflow scope, with Architecture & Security accepting the authority/data boundary, Quality Engineering independently assessing behavior and Platform & IT verifying enforcement and recovery. These are recommended functions within existing teams—not appointed approvers or granted permissions. Unresolved release approval roles remain a hold condition; the agent cannot appoint its own authority.
|
||||
|
||||
Require exact-artifact approvals, separated credentials, independent checks, idempotency and duplicate/outage recovery, an auditable task ledger, and a tested stop/human-takeover path outside the model. Sensitive decisions remain human; missing evidence never means permission. A readiness failure returns to [Stage 01](./stage-01-skills-adoption.mdx) or redesign; it does not justify a larger experiment.
|
||||
|
||||
The output is either a recorded hold or a narrowly scoped authorization with conditions and invalidation rules. Monitor outcomes and authority violations separately. A material boundary change reopens the decision; harmful behavior revokes mutation authority and activates takeover, feeding evidence back into [Quality](./skills-quality.mdx) and [Maintenance](./skills-maintenance.mdx).
|
||||
|
||||
This is future direction, not deployed autonomy, agreed delivery dates or approved KPI thresholds. The transition depends on reviewed evidence and explicit authority decisions, not adoption volume alone.
|
||||
|
||||
**Return to the plan:** [6 Months Roadmap](./six-months-roadmap.mdx).
|
||||
|
||||
**Return to dependable work:** [Continue the Stage 01 improvement loop →](./stage-01-skills-adoption.mdx).
|
||||
|
||||
</div>
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
id: target-operating-model
|
||||
title: Target operating model
|
||||
title: Target
|
||||
sidebar_label: Target
|
||||
description: An autonomous agent executes and governs the SDLC; humans direct, guide and review the repeating cycle.
|
||||
hide_table_of_contents: true
|
||||
---
|
||||
@@ -11,15 +12,21 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
|
||||
|
||||
**TO-BE · Target operating model — the intended strategy, not a deployed system.**
|
||||
|
||||
The long-term destination remains human-directed, guided and reviewed autonomous SDLC. It is not a six-month commitment or present authorization. The [6 Months Target](./six-months-target.mdx) and [6 Months Roadmap](./six-months-roadmap.mdx) describe a credible nearer-term contribution, not a replacement for this ambition. No fixed completion date or inevitable progression is implied.
|
||||
|
||||
## Autonomous SDLC, human direction
|
||||
|
||||
<ArchifyDiagram name="strategy-target" title="Autonomous agent executes and governs the SDLC; humans direct, guide and review" story />
|
||||
|
||||
An autonomous agent executes and governs the SDLC. Humans direct, guide and review the work throughout the cycle.
|
||||
An autonomous agent executes and governs every phase. Humans direct, guide and review it; a separate human-controlled AI Agent contributes to each phase from outside the cycle.
|
||||
|
||||
**Scope → Architecture → UI/UX → Planning → Delivery → UAT → Releases → Scope**
|
||||
**Solid arrows:** lifecycle · **Dotted spokes:** execution and governance · **Dashed arrows:** contributions.
|
||||
|
||||
Each stage follows the previous one. Releases returns to Scope; the cycle repeats indefinitely, with human direction informing the next iteration.
|
||||
**Scope → Architecture → UI/UX → Planning → Delivery → UAT → Security → Releases → Scope**
|
||||
|
||||
The arrows show the intended SDLC cycle, not the order of skills rollout. Releases returns evidence to Scope; human direction informs the next iteration. The [Roadmap](./roadmap.mdx) starts with human + AI Agent work in Delivery before considering wider autonomous authority.
|
||||
|
||||
**Illustrative Delivery thread:** an agent prepares a bounded code change and regression evidence, an independent human reviews the exact artifact, and existing release controls decide whether it can advance. Stage 01 makes this working practice dependable; Stage 02 separately considers what the central agent may execute. Skills supply knowledge and verification steps, never permission.
|
||||
|
||||
<details>
|
||||
<summary>Supporting implementation options: trust boundaries and recovery</summary>
|
||||
@@ -36,7 +43,7 @@ The lifecycle above is the strategic direction. The earlier control design below
|
||||
|
||||
<ArchifyDiagram name="ai-adoption-target" title="Supporting control option, not agreed approval policy: isolated release authority" />
|
||||
|
||||
**TO-BE · Target operating model.** Introduction depends on the [roadmap gates](./roadmap.mdx); these pages do not describe installed controls or measured company results.
|
||||
**TO-BE · Target operating model.** The [Roadmap](./roadmap.mdx) separates skills adoption from the future authority decision; these pages do not describe installed controls or measured company results.
|
||||
|
||||
### One coordination function, distributed contributions
|
||||
|
||||
@@ -44,7 +51,7 @@ The autonomous agent is more than a task router: it executes and governs the rep
|
||||
|
||||
One logical coordinator does not mean one fragile process. A durable task ledger, explicit state transitions, leases and idempotency keys allow recovery or multiple replicas without duplicate delivery. Inference outages stop new agent decisions, not the organization's ability to take over. People can resume work through the normal deterministic workflow. Evidence and authorization services fail closed for privileged actions; missing evidence never becomes permission.
|
||||
|
||||
These controls support the sequence Scope → Architecture → UI/UX → Planning → Delivery → UAT → Releases → Scope; they do not replace it with a separate lifecycle. Product, engineering, design, quality, security and platform expertise inform human direction and review. Specific approval assignments and release permissions are implementation decisions still to be defined.
|
||||
These controls support the sequence Scope → Architecture → UI/UX → Planning → Delivery → UAT → Security → Releases → Scope; they do not replace it with a separate lifecycle. Product, engineering, design, quality, security and platform expertise inform human direction and review. Specific approval assignments and release permissions are implementation decisions still to be defined.
|
||||
|
||||
### Trust and authority boundaries
|
||||
|
||||
@@ -61,7 +68,7 @@ Central controls verify protected-branch review, actual artifact identity, exact
|
||||
|
||||
### Department contributions
|
||||
|
||||
The existing team structure provides a starting point. The contributions below are implementation proposals, not settled approval roles or lifecycle gates.
|
||||
The documented organization model is an assumption to validate, not PDF evidence of actual reporting lines. Candidate functions must be mapped to real people before any decision. The existing team structure provides a starting point. The contributions below are implementation proposals, not settled approval roles or lifecycle gates.
|
||||
|
||||
### Product / Product Management
|
||||
|
||||
@@ -135,6 +142,35 @@ See the existing [organization structure](/organization/structure/), [department
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Decide who owns and approves each skill →](./skills-governance.mdx)
|
||||
<details>
|
||||
<summary>Strategy rationale and reading map</summary>
|
||||
|
||||
### Govern skills first, expand authority only with evidence
|
||||
|
||||
Eldorado's target is to make AI-assisted work dependable across the organization: useful guidance, clear human ownership, controlled execution and measurable outcomes. The first investment is understanding and improving current AI-assisted work, not an autonomous replacement for the organization. Governed skills and practices support the direction; context, coaching, test repair or deterministic automation may be the better immediate intervention. A skill packages reusable working knowledge, prerequisites and verification steps. It helps an agent perform a task; it does not grant permission or guarantee that the work is correct.
|
||||
|
||||
The target combines an autonomous agent executing and governing the SDLC with humans directing, guiding and reviewing it. Developer choice on local laptops remains a supporting option: Copilot, Claude Code and Cline can receive reviewed portable skill content through qualified adapters. Repository, CI and release controls support execution; detailed approval policies remain implementation decisions, not new roles established by this strategy.
|
||||
|
||||
The strategy describes the intended operating model and the evidence required to introduce it. It does not establish that these controls are installed, that every client is supported, or that AI has improved Eldorado's performance. The current reference is the documented six-department organization. Rollout begins by validating actual clients, responsibilities, data boundaries and available evidence.
|
||||
|
||||
Success means accepted outcomes with maintained quality, controlled risk and understood total cost. Faster activity without reliable outcomes is not success. More skill invocations, generated lines or tool subscriptions are not productivity targets. People remain accountable for product, customer, financial and personnel decisions.
|
||||
|
||||
### Navigate the strategy
|
||||
|
||||
- [Roadmap](./roadmap.mdx) — Skills adoption first; future autonomy separately justified, no promised dates or budgets.
|
||||
- [6 Months Target](./six-months-target.mdx) — Assignment context, realistic outcomes and assumptions.
|
||||
- [6 Months Roadmap](./six-months-roadmap.mdx) — Month 1–6 priorities and bounded experiment decisions.
|
||||
- [Skills lifecycle](./stage-01-skills-adoption.mdx) — Supporting handoffs, decisions and feedback.
|
||||
- [Baseline](./baseline.mdx) — Understand current work and record the starting position before changing it.
|
||||
- [Skills governance](./skills-governance.mdx) — Contract, lifecycle, decision rights, adapters, locking, exceptions.
|
||||
- [Skills quality](./skills-quality.mdx) — Risk tiers, independent evaluation, repeated trials, adversarial conformance.
|
||||
- [Skills adoption](./skills-adoption.mdx) — Workflow-led coaching, client choice, feedback, manual path.
|
||||
- [Measurement](./measurement/index.mdx) — Full KPI contracts, minimal events, illustrative calculations, privacy and limits.
|
||||
- [Skills maintenance](./skills-maintenance.mdx) — Review, drift, deprecation, rollback and incident handling.
|
||||
- [Beyond 6 Months](./stage-02-autonomous-agent.mdx) — Decide whether bounded autonomous authority is justified and recoverable.
|
||||
|
||||
</details>
|
||||
|
||||
**Next:** [Follow the Roadmap toward Target →](./roadmap.mdx)
|
||||
|
||||
</div>
|
||||
@@ -18,6 +18,7 @@ const config: Config = {
|
||||
theme: {customCss: './src/css/custom.css'},
|
||||
} satisfies Preset.Options]],
|
||||
plugins: [
|
||||
['@docusaurus/plugin-client-redirects', {redirects: [{from: '/strategy/', to: '/strategy/target-operating-model/'}]}],
|
||||
['@docusaurus/plugin-content-docs', {id: 'organization', path: 'docs/organization', routeBasePath: 'organization', sidebarPath: './sidebars/organization.ts'}],
|
||||
['@docusaurus/plugin-content-docs', {id: 'strategy', path: 'docs/strategy', routeBasePath: 'strategy', sidebarPath: './sidebars/strategy.ts'}],
|
||||
['@docusaurus/plugin-content-docs', {id: 'contribution', path: 'docs/contribution', routeBasePath: 'contribution', sidebarPath: './sidebars/contribution.ts'}],
|
||||
|
||||
+9
-4
@@ -7,19 +7,23 @@
|
||||
"node": ">=22"
|
||||
},
|
||||
"scripts": {
|
||||
"start": "pnpm diagrams:build && docusaurus start",
|
||||
"build": "pnpm diagrams:build && docusaurus build",
|
||||
"start": "pnpm diagrams:build && pnpm presentations:build && docusaurus start",
|
||||
"build": "pnpm diagrams:build && pnpm presentations:build && docusaurus build",
|
||||
"presentations:build": "node scripts/build-presentations.mjs",
|
||||
"serve": "docusaurus serve",
|
||||
"test:presentation": "node scripts/browser/presentation.cjs",
|
||||
"test:homepage-embed": "node scripts/browser/homepage-embed.cjs",
|
||||
"typecheck": "tsc --noEmit",
|
||||
"verify": "pnpm test && node scripts/verify.mjs",
|
||||
"verify:build": "node scripts/verify.mjs --build",
|
||||
"diagrams:build": "node scripts/build-diagrams.mjs",
|
||||
"test": "node --test scripts/*.test.mjs",
|
||||
"test:browser": "node scripts/browser/strategy-story.cjs && node scripts/browser/inline-controls.cjs && node scripts/browser/sdlc-cycle.cjs",
|
||||
"test:browser": "node scripts/browser/measurement-pages.cjs && node scripts/browser/sidebar-coverage.cjs && node scripts/browser/skills-stories.cjs && node scripts/browser/strategy-navigation.cjs && node scripts/browser/strategy-story.cjs && node scripts/browser/inline-controls.cjs && node scripts/browser/sdlc-cycle.cjs && node scripts/browser/target-midpoints.cjs && node scripts/browser/skills-measurement.cjs && node scripts/browser/roadmap.cjs && node scripts/browser/roadmap-timeline.cjs",
|
||||
"kpi:example": "node scripts/ai-kpi.mjs"
|
||||
},
|
||||
"dependencies": {
|
||||
"@docusaurus/core": "3.10.2",
|
||||
"@docusaurus/plugin-client-redirects": "3.10.2",
|
||||
"@docusaurus/preset-classic": "3.10.2",
|
||||
"@docusaurus/theme-common": "3.10.2",
|
||||
"@easyops-cn/docusaurus-search-local": "0.55.3",
|
||||
@@ -28,7 +32,8 @@
|
||||
"clsx": "2.1.1",
|
||||
"prism-react-renderer": "2.4.1",
|
||||
"react": "19.1.1",
|
||||
"react-dom": "19.1.1"
|
||||
"react-dom": "19.1.1",
|
||||
"reveal.js": "5.2.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@docusaurus/module-type-aliases": "3.10.2",
|
||||
|
||||
Generated
+60
@@ -14,6 +14,9 @@ importers:
|
||||
'@docusaurus/core':
|
||||
specifier: 3.10.2
|
||||
version: 3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(debug@4.4.3)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)
|
||||
'@docusaurus/plugin-client-redirects':
|
||||
specifier: 3.10.2
|
||||
version: 3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)
|
||||
'@docusaurus/preset-classic':
|
||||
specifier: 3.10.2
|
||||
version: 3.10.2(@algolia/client-search@5.59.0)(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(@types/react@19.1.13)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(search-insights@2.17.3)(typescript@5.9.3)
|
||||
@@ -41,6 +44,9 @@ importers:
|
||||
react-dom:
|
||||
specifier: 19.1.1
|
||||
version: 19.1.1(react@19.1.1)
|
||||
reveal.js:
|
||||
specifier: 5.2.1
|
||||
version: 5.2.1
|
||||
devDependencies:
|
||||
'@docusaurus/module-type-aliases':
|
||||
specifier: 3.10.2
|
||||
@@ -1115,6 +1121,13 @@ packages:
|
||||
react: '*'
|
||||
react-dom: '*'
|
||||
|
||||
'@docusaurus/plugin-client-redirects@3.10.2':
|
||||
resolution: {integrity: sha512-z5I5ttCXw+8y2gHVZvqAMmUw4Rb0ZzKA5eCPk87SfM/jCKOTvE24yDpPAwwipvug96ij7mOwEHXWw8G4LlWdGA==}
|
||||
engines: {node: '>=20.0'}
|
||||
peerDependencies:
|
||||
react: ^18.0.0 || ^19.0.0
|
||||
react-dom: ^18.0.0 || ^19.0.0
|
||||
|
||||
'@docusaurus/plugin-content-blog@3.10.2':
|
||||
resolution: {integrity: sha512-0cbEnNKf0InmLkhj/+nVRmqEnWEoOE8Mh+2x1qOXI0qYpCnphq4RXknVJ8BvybKRXqYVvbmdMfiJSup+k4tm5w==}
|
||||
engines: {node: '>=20.0'}
|
||||
@@ -4624,6 +4637,10 @@ packages:
|
||||
resolution: {integrity: sha512-g6QUff04oZpHs0eG5p83rFLhHeV00ug/Yf9nZM6fLeUrPguBTkTQOdpAWWspMh55TZfVQDPaN3NQJfbVRAxdIw==}
|
||||
engines: {iojs: '>=1.0.0', node: '>=0.10.0'}
|
||||
|
||||
reveal.js@5.2.1:
|
||||
resolution: {integrity: sha512-r7//6mIM5p34hFiDMvYfXgyjXqGRta+/psd9YtytsgRlrpRzFv4RbH76TXd2qD+7ZPZEbpBDhdRhJaFgfQ7zNQ==}
|
||||
engines: {node: '>=18.0.0'}
|
||||
|
||||
rtlcss@4.3.0:
|
||||
resolution: {integrity: sha512-FI+pHEn7Wc4NqKXMXFM+VAYKEj/mRIcW4h24YVwVtyjI+EqGrLc2Hx/Ny0lrZ21cBWU2goLy36eqMcNj3AQJig==}
|
||||
engines: {node: '>=12.0.0'}
|
||||
@@ -6784,6 +6801,47 @@ snapshots:
|
||||
- uglify-js
|
||||
- webpack-cli
|
||||
|
||||
'@docusaurus/plugin-client-redirects@3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)':
|
||||
dependencies:
|
||||
'@docusaurus/core': 3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(debug@4.4.3)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)
|
||||
'@docusaurus/logger': 3.10.2
|
||||
'@docusaurus/utils': 3.10.2(clean-css@5.3.3)(cssnano@6.1.2(postcss@8.5.28))(html-minifier-terser@7.2.0)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)
|
||||
'@docusaurus/utils-common': 3.10.2(clean-css@5.3.3)(cssnano@6.1.2(postcss@8.5.28))(html-minifier-terser@7.2.0)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)
|
||||
'@docusaurus/utils-validation': 3.10.2(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)
|
||||
eta: 2.2.0
|
||||
fs-extra: 11.4.1
|
||||
lodash: 4.18.1
|
||||
react: 19.1.1
|
||||
react-dom: 19.1.1(react@19.1.1)
|
||||
tslib: 2.8.1
|
||||
transitivePeerDependencies:
|
||||
- '@docusaurus/faster'
|
||||
- '@mdx-js/react'
|
||||
- '@minify-html/node'
|
||||
- '@napi-rs/image'
|
||||
- '@parcel/css'
|
||||
- '@rspack/core'
|
||||
- '@swc/core'
|
||||
- '@swc/css'
|
||||
- '@swc/html'
|
||||
- bufferutil
|
||||
- clean-css
|
||||
- cssnano
|
||||
- csso
|
||||
- debug
|
||||
- esbuild
|
||||
- html-minifier-terser
|
||||
- imagemin
|
||||
- lightningcss
|
||||
- postcss
|
||||
- sharp
|
||||
- supports-color
|
||||
- svgo
|
||||
- typescript
|
||||
- uglify-js
|
||||
- utf-8-validate
|
||||
- webpack-cli
|
||||
|
||||
'@docusaurus/plugin-content-blog@3.10.2(@docusaurus/plugin-content-docs@3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3))(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)':
|
||||
dependencies:
|
||||
'@docusaurus/core': 3.10.2(@mdx-js/react@3.1.1(@types/react@19.1.13)(react@19.1.1))(debug@4.4.3)(postcss@8.5.28)(react-dom@19.1.1(react@19.1.1))(react@19.1.1)(typescript@5.9.3)
|
||||
@@ -11583,6 +11641,8 @@ snapshots:
|
||||
|
||||
reusify@1.1.0: {}
|
||||
|
||||
reveal.js@5.2.1: {}
|
||||
|
||||
rtlcss@4.3.0:
|
||||
dependencies:
|
||||
escalade: 3.2.0
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
# Less Prompting, More Shipping — v1.1.0
|
||||
|
||||
An explanation for the CTO and engineering leads: understand the intended destination and decide how a solo AI Architect should contribute in the first six months. The original `AI_Architect_Test_Task.pdf` supplies the assumed context, four questions and 50-minute total. The same-build Strategy supplies the connected narrative: **Target → Roadmap → 6 Months Target → 6 Months Roadmap → Beyond 6 Months**. The six-month contribution neither replaces the long-term human-controlled autonomous SDLC nor authorizes it.
|
||||
|
||||
## Story and timing
|
||||
|
||||
23 slides: 21 main slides / **35 minutes**, one **15-minute Q&A**, one **zero-minute reference appendix**. EXP-01 is now one two-minute illustration, not the spine of the strategy. Its detailed fictional sample, extension caps and stop ledger remain in speaker notes and the canonical linked Strategy packet.
|
||||
|
||||
The table is the revised presentation allocation. The PDF prescribes 50 minutes total, not this split. The six-month Strategy page still contains an earlier proposed outline; its exact subsection timings are not claimed to match this destination-first deck. No Strategy page was rewritten to accommodate the presentation.
|
||||
|
||||
| Slide | Minutes / elapsed | Main message | Strategy evidence (canonical slug) |
|
||||
| --- | --- | --- | --- |
|
||||
| 1 | 1 / 0–1 | Destination and first contribution | target-operating-model; roadmap; six-months-target; PDF |
|
||||
| 2 | 2 / 1–3 | Existing uneven AI; solo CTO-reporting role; unknowns | six-months-target; PDF Context/Q1/assumptions |
|
||||
| 3 | 1 / 3–4 | Accepted output, not faster drafts | six-months-target; baseline; measurement |
|
||||
| 4 | 3 / 4–7 | Intended SDLC cycle and central human-controlled agent | target-operating-model |
|
||||
| 5 | 1 / 7–8 | Eight outside human-controlled contributors | target-operating-model |
|
||||
| 6 | 2 / 8–10 | Delivery-first adoption, then other phases, then separate autonomy | roadmap; target-operating-model |
|
||||
| 7 | 2 / 10–12 | Connected skills and repeating within-phase learning | roadmap; stage-01-skills-adoption |
|
||||
| 8 | 1 / 12–13 | First-six-month building block toward Target | six-months-target; target-operating-model |
|
||||
| 9 | 1 / 13–14 | Influence beside work, no team authority | six-months-roadmap |
|
||||
| 10 | 2 / 14–16 | Months 1–2: discover, baseline, agree | six-months-roadmap; baseline |
|
||||
| 11 | 2 / 16–18 | Months 3–4: qualify, test, compare | six-months-roadmap |
|
||||
| 12 | 2 / 18–20 | Months 5–6: conditional transfer and handover | six-months-roadmap; six-months-target |
|
||||
| 13 | 1 / 20–21 | Solo capacity, one live pilot, funded support | six-months-roadmap |
|
||||
| 14 | 2 / 21–23 | Acceptance, burden, quality and total costs | measurement; six-months-roadmap |
|
||||
| 15 | 2 / 23–25 | Misleading signals and causal limits | measurement; six-months-roadmap |
|
||||
| 16 | 2 / 25–27 | Qualification is not pilot permission | skills-quality; six-months-roadmap |
|
||||
| 17 | 2 / 27–29 | Fictional EXP-01: cheapest fit, hold, then stop | six-months-roadmap |
|
||||
| 18 | 1 / 29–30 | Realistic month-six evidence portfolio | six-months-target; six-months-roadmap |
|
||||
| 19 | 2 / 30–32 | Evidence-led investment toward established destination | stage-02-autonomous-agent; target-operating-model; roadmap; six-months-target |
|
||||
| 20 | 2 / 32–34 | Separate bounded authority, stop and human takeover | stage-02-autonomous-agent; target-operating-model |
|
||||
| 21 | 1 / 34–35 | First CTO alignment and four answers | six-months-roadmap; PDF Q1–4 |
|
||||
| 22 | 15 / 35–50 | Q&A | PDF Format; six-months-target |
|
||||
| 23 | 0 / optional | Linked references, outside the main talk | PDF; all five Strategy pages plus measurement |
|
||||
|
||||
PDF Q1 **What you do** → slides 2, 9–13. Q2 **How you measure it** → 14–17. Q3 **What you achieve** → 8 and 18. Q4 **What comes next** → 4–7 establish the destination; 19–20 explain evidence-led progression. Scale/growth/uneven AI use are assignment facts, not independently measured company facts. Stack, providers, data policy, task supply, partner capacity and bottlenecks remain unknown or hypotheses, explained on slide 2 and in discovery notes.
|
||||
|
||||
## Source and build
|
||||
|
||||
- `slides.mjs` is the single editorial source for standalone and homepage. Every slide has section, track, timing, narration and source references. Notes are public HTML, never confidential.
|
||||
- `target-figure.mjs` provides two presentation-sized views of the original topology. Slide 4 preserves the eight ordered cycle edges and eight governance spokes, including Releases → Scope. Slide 5 preserves all eight external `code-* → phase` contribution edges. There is one central autonomous agent, not a separate Humans node or a reporting hierarchy. Tests compare all three edge sets with the original diagram JSON; desktop and phone are recomposed, not shrunk documentation screenshots.
|
||||
- `theme.css` preserves portal Lato/gold/charcoal/light surfaces and isolated standalone styles. Distinct cycle, contribution layer, staged progression, learning loop and horizon compositions support the story.
|
||||
- `runtime.js` is unchanged: Reveal, reduced motion, responsive portrait layout, toolbar, isolated embedded focus/URL and no autoplay.
|
||||
- `scripts/build-presentations.mjs` generates the same canonical route, exact-pinned local Reveal.js 5.2.1, notes plugin, Lato assets/licenses and `source-map.json`. The map includes slide IDs/sections/tracks/minutes/sources, four-question coverage, exact Strategy and topology source hashes, and provenance without claiming historical revisions are current. No runtime CDN.
|
||||
|
||||
From repository root: `pnpm install --frozen-lockfile`, `pnpm test`, `pnpm typecheck`, `pnpm build`, `pnpm verify:build`. Serve `build/` under `/eldorado-v1/documentation/` with a static server. The canonical route remains `/eldorado-v1/documentation/presentations/less-prompting-more-shipping/`. The homepage's **Understand In Speed** embeds that generated document, not a duplicated slide source. Existing Organization, Strategy, homepage component and runtime sources are preserved.
|
||||
|
||||
## Present and verify
|
||||
|
||||
Arrows/touch navigate. Esc/Overview shows the grid. F/Fullscreen and S/Notes work standalone; embedded focus stays within its own document and parent URL is unchanged. Notes need HTTP(S) and popups. Named deep links such as `#/target` and `#/qualification` survive refresh. Print uses `?print-pdf`: Chromium, landscape, no margins, background graphics. Export has **23 pages**, without notes. No unsolicited PDF/PPTX/ZIP is published.
|
||||
|
||||
`pnpm test:presentation <base>` covers 23 slides at desktop, portrait and landscape (69 views), bounds, errors, links, hash/refresh, keyboard, touch, overview, notes popup, fullscreen, homepage handoff and 23-page print layout. `pnpm test:homepage-embed <base>` covers 23 slides at four widths (92 views), focus/scroll/URL isolation, touch, fullscreen, unsupported-fullscreen escape, Tab exit, themes and reduced motion. Outputs are ordered individual PNGs and JSON in `.cache/presentation/` and `.cache/homepage-embed/`; inspect real pixels, not just geometry. Set `PLAYWRIGHT_CHROMIUM_EXECUTABLE` for an installed browser.
|
||||
|
||||
Local Docusaurus serve on Node 26 redirects WOFF2 paths with a trailing slash in this environment. Use a regular prefix-correct static server for production-equivalent font verification; missing-font screenshots are not acceptable evidence.
|
||||
|
||||
Official runtime references: https://revealjs.com/installation/, https://revealjs.com/speaker-view/, https://revealjs.com/pdf-export/. The pinned package is intentional; runtime API compatibility is judged against 5.2.1, not latest-version assumptions.
|
||||
|
||||
## Boundaries
|
||||
|
||||
No guaranteed benefits, approved thresholds, staffing commitments or deployed autonomy. The intended long-term destination is explicit, while its timing and authority remain unapproved. First-six-month failure or a cheaper deterministic intervention is compatible with that direction. Human product, risk and release authority is retained. Skills carry knowledge and verification, not permission.
|
||||
|
||||
Dependency manifests are unchanged. Previously recorded production audit: 2 critical, 2 high, 2 moderate; this presentation revision is neither remediation nor security-risk acceptance. Chromium viewport testing is not Safari/Firefox, physical-device or full assistive-technology certification. This branch is a review candidate; the dependent reviewer owns merge, exact-main CI and deployed verification.
|
||||
@@ -0,0 +1,37 @@
|
||||
/* Reveal 5.2.1, fully local runtime; this document is isolated from Docusaurus CSS. */
|
||||
const reducedMotion = window.matchMedia('(prefers-reduced-motion: reduce)');
|
||||
const portrait = window.matchMedia('(max-width: 700px) and (orientation: portrait)');
|
||||
const printing = new URLSearchParams(location.search).has('print-pdf');
|
||||
const embedded = new URLSearchParams(location.search).has('embed') && !printing;
|
||||
document.documentElement.classList.toggle('embedded', embedded);
|
||||
if (embedded) {
|
||||
document.querySelector('.toolbar').hidden = true;
|
||||
// Never load the portal inside the stage when following the reference appendix.
|
||||
document.querySelectorAll('.slides a').forEach(link => { link.target = '_top'; });
|
||||
}
|
||||
function layoutSize(){
|
||||
const narrow=portrait.matches&&!printing;
|
||||
document.documentElement.classList.toggle('portrait',narrow);
|
||||
return narrow?{width:600,height:1000}:{width:1200,height:660};
|
||||
}
|
||||
Reveal.initialize({
|
||||
...layoutSize(), margin:0.04, minScale:0.1, maxScale:2,
|
||||
hash:!embedded, embedded, keyboardCondition:embedded ? () => document.hasFocus() : null,
|
||||
hashOneBasedIndex:false, controls:true, progress:true,
|
||||
slideNumber:'c/t', showSlideNumber:'all', center:false,
|
||||
transition:reducedMotion.matches?'none':'fade', transitionSpeed:'fast',
|
||||
backgroundTransition:'none', autoSlide:0, touch:true,
|
||||
// The host owns fullscreen; speaker tools remain available in the standalone deck.
|
||||
keyboard:embedded ? {70:null,83:null} : true,
|
||||
// Keep deliberate slides on phones rather than Reveal's automatic scroll view.
|
||||
scrollActivationWidth:null, pdfMaxPagesPerSlide:1, pdfSeparateFragments:false,
|
||||
plugins:[RevealNotes]
|
||||
});
|
||||
portrait.addEventListener('change',()=>Reveal.configure(layoutSize()));
|
||||
reducedMotion.addEventListener('change',event=>Reveal.configure({transition:event.matches?'none':'fade'}));
|
||||
document.getElementById('overview').addEventListener('click',()=>Reveal.toggleOverview());
|
||||
document.getElementById('notes').addEventListener('click',()=>Reveal.getPlugin('notes').open());
|
||||
document.getElementById('fullscreen').addEventListener('click',()=>{
|
||||
if(document.fullscreenElement) document.exitFullscreen();
|
||||
else document.documentElement.requestFullscreen?.();
|
||||
});
|
||||
@@ -0,0 +1,328 @@
|
||||
// Single editorial source for standalone and homepage. Planned narration: 35 + 15 minutes.
|
||||
import {cycleFigure,contributionsFigure} from './target-figure.mjs';
|
||||
export const slides = [
|
||||
{
|
||||
"id": "opening",
|
||||
"title": "Less Prompting,<br>More Shipping",
|
||||
"minutes": 1,
|
||||
"body": "<p class=\"subtitle\">The destination—and the first six months toward it</p><p class=\"thesis\">Improve accepted engineering work.<br>Not the number of times we ask AI.</p><p class=\"small\">Proposed strategy · 35 minutes + 15 minutes Q&A</p>",
|
||||
"notes": "Open with the outcome, not a tool purchase. The title is a reminder to measure useful work, not an instruction to minimize prompts. More careful prompting may be exactly what good work needs. My proposal is to earn one evidence-backed improvement, make its costs visible, and stop what does not help. Walk through what I do, how I measure, what month six looks like and what comes next. Start with the long-term Target and broad Roadmap, then bound the first-six-month contribution. The five Strategy pages organize this story; the assignment supplies the four questions and total time.",
|
||||
"sources": [
|
||||
"PDF: Format; Context; questions 1–4",
|
||||
"six-months-target",
|
||||
"target-operating-model",
|
||||
"roadmap"
|
||||
],
|
||||
"kind": "dark",
|
||||
"section": "Why change",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "starting-point",
|
||||
"title": "We are not starting from “no AI”.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"facts\"><div><strong>≈80 → ≈100</strong><span>engineers, by year end</span></div><div><strong>>10</strong><span>teams</span></div><div><strong>Already using AI</strong><span>uneven depth and quality</span></div></div><div class=\"contrast\"><p>Solo architect → CTO<br>No formal authority over teams</p><p>Stack, tools, process, baselines<br>Capacity and actual bottlenecks</p></div>",
|
||||
"notes": "These headcount and usage facts are from the assignment, not independent research. The comparison is existing AI-assisted practice, never an invented no-AI baseline. Delivery is a starting hypothesis, not a finding. The documented departmental model is not evidence of actual assignment staffing. Ask about stack and tool/data restrictions in discovery; do not assume familiar clients are in use. Every timeline and proposed allocation in this deck remains subject to agreement.",
|
||||
"sources": [
|
||||
"PDF: Context; question 1; final assumptions instruction",
|
||||
"six-months-target"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Why change",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "north-star",
|
||||
"title": "A faster draft is not a shipped outcome.",
|
||||
"minutes": 1,
|
||||
"body": "<div class=\"flow\"><span>Intent</span><i>→</i><span>Change + tests</span><i>→</i><span>Independent acceptance</span></div><div class=\"rail\">Existing release authority stays with people.</div><p class=\"statement\">Less rework. Sound quality.<br>Understand the total burden.</p><p class=\"small\">If the bottleneck is CI or review capacity, fix that—not the prompt count.</p>",
|
||||
"notes": "Trace a change through acceptance and its existing release route. An agent can shorten drafting and still make reviewers work harder. The outcome must survive independent acceptance, defect follow-up and total-cost accounting. Observe why work comes back rather than assume more output from the model means more output from engineering. Flaky tests, unclear scope or scarce reviewers may make a non-AI intervention the right investment.",
|
||||
"sources": [
|
||||
"six-months-target",
|
||||
"baseline",
|
||||
"measurement"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Why change",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "target",
|
||||
"title": "Target / Autonomous SDLC.",
|
||||
"minutes": 3,
|
||||
"body": cycleFigure + `<p class="diagram-legend">Solid → lifecycle · Dotted ⇢ executes and governs</p><p class="small">Humans direct, guide and review. Not deployed or promised in six months.</p>`,
|
||||
"notes": "This is the intended destination, not deployed software, an agreed date or a six-month promise. Read the solid cycle clockwise from Scope: Architecture, UI/UX, Planning, Delivery, UAT, Security, Releases, then evidence returns to Scope. The single central autonomous agent executes and governs every phase, not merely routing tickets. Dotted spokes connect it to all eight phases; people direct, guide and review throughout. There is deliberately no separate Humans node or organizational reporting hierarchy. This view isolates the lifecycle and governance relationships for readability; the next slide restores all eight outside human-controlled contributors. Neither diagram assigns approval roles or grants permissions.",
|
||||
"sources": [
|
||||
"target-operating-model"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Target",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "contributors",
|
||||
"title": "People contribute throughout the cycle.",
|
||||
"minutes": 1,
|
||||
"body": `<p class="diagram-intro">Eight separate AI Agents, each human-controlled.</p>` + contributionsFigure + `<p class="small">AI Agent = Claude, Cline, ChatGPT or a similar tool, used under human control.</p><div class="rail">Dashed ⇢ contribution from outside the cycle.</div>`,
|
||||
"notes": "Keep the previous cycle in mind: these eight pairs are its contribution layer, not a second lifecycle or eight central coordinators. Each separate human-controlled AI Agent contributes to its corresponding phase from outside the cycle. The central autonomous agent remains connected to every phase, executing and governing under human direction. Splitting the original topology into two presentation-sized views preserves all eight lifecycle arrows, eight governance spokes and eight contribution arrows without miniaturizing seventeen nodes. Laptop client choice and adapters are implementation options, not a promise of installed support. Human review, product and risk decisions remain necessary.",
|
||||
"sources": [
|
||||
"target-operating-model"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Target",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "roadmap",
|
||||
"title": "Roadmap / Build dependable work first.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"journey\"><div><small>STAGE 1 · HUMAN + AI</small><b>Delivery first</b><span>Standardize connected skills<br>and working practices</span></div><i>→</i><div><small>STAGE 1 · EXPAND</small><b>Other SDLC phases</b><span>Order undecided<br>Delivery keeps improving</span></div><i>⇢</i><div><small>STAGE 2 · SEPARATE AUTHORITY</small><b>Autonomous capabilities</b><span>Proven practices + controls<br>toward the Target</span></div></div><div class=\"rail\">Humans direct, guide and review throughout.</div><p class=\"small\">A strategic progression—not a six-month schedule or automatic graduation.</p>",
|
||||
"notes": "The Roadmap has two broad stages. First standardize skills and practices in human plus AI Agent work, starting with Delivery. Then expand across other SDLC phases, with their remaining order explicitly undecided. This adoption order is different from the Target lifecycle sequence. Delivery continues improving while other phases join. Proven skills, measurements and working practices provide a foundation for the future autonomous agent, but adoption volume never grants authority. Stage one is useful in its own right. Evidence may support coaching, context or deterministic tooling rather than a skill for a particular bottleneck; that practical choice contributes to dependable work rather than cancelling the long-term destination.",
|
||||
"sources": [
|
||||
"roadmap",
|
||||
"target-operating-model"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "learning-loop",
|
||||
"title": "Connected skills. A repeating learning loop.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"learning-loop\"><span>Understand work</span><i>→</i><span>Measure + baseline</span><i>↓</i><span>Engineer topology</span><i>→</i><span>Use in real work</span><i>↓</i><span>Collect results</span><i>→</i><span>Reassess</span></div><div class=\"rail\">↻ Repeat within each phase. Not six global rollout stages.</div><p class=\"statement\">Triggers → skills → handoffs → acceptance.</p><p class=\"small\">Relationships and cooperation—not merely a catalogue.</p>",
|
||||
"notes": "Within every adopted phase repeat the loop: understand the current situation, select relevant metrics and baseline, engineer connected skills, use them in real work, collect outcomes/friction/feedback, then reassess and repeat. Topology defines what exists, how skills relate, when each triggers and how they cooperate. In Delivery trace codebase principles through system logic, tests, builds/packaging and deployment before designing that topology. A code-change skill may hand an exact patch and regression evidence to independent review; its trigger is an eligible change, not an ambient right to act. Governance and Measurement support the whole loop. Qualify revisions before use, and reconsider simpler interventions whenever the evidence says they fit better.",
|
||||
"sources": [
|
||||
"roadmap",
|
||||
"stage-01-skills-adoption"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "six-month-target",
|
||||
"title": "6 Months Target / One credible contribution.",
|
||||
"minutes": 1,
|
||||
"body": "<div class=\"horizon\"><div><small>LONG-TERM DESTINATION</small><b>Human-controlled autonomous SDLC</b></div><div class=\"near\"><small>FIRST SIX MONTHS</small><b>One workflow understood and improved—or stopped with evidence</b><span>One willing partner · reusable practice · owned upkeep</span></div></div><p class=\"statement\">Earn a dependable building block.<br>Do not promise the entire destination.</p>",
|
||||
"notes": "Separate the horizons without making them opposing stories. A credible six-month contribution is a current-work map, an agreed comparison, a bounded intervention and transparent evidence, with a team owner if useful practice is retained. One workflow with one willing team is already meaningful for a solo architect; a second team is conditional on fit and support. These are proposed outcomes, not known company results or guaranteed gains. If an intervention fails, the useful result is an explained stop, retained learning and a better next investment. The autonomous SDLC remains the destination, with no claim that it can or should be delivered in six months.",
|
||||
"sources": [
|
||||
"six-months-target",
|
||||
"target-operating-model"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Target",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "influence",
|
||||
"title": "Influence is earned beside the work.",
|
||||
"minutes": 1,
|
||||
"body": "<div class=\"roles\"><div><b>CTO</b><span>Sponsor access<br>Resolve priority trade-offs</span></div><div class=\"gold\"><b>Architect</b><span>Pair, build, evaluate<br>Bring evidence—not mandates</span></div><div><b>Willing team</b><span>Agree contribution<br>Own acceptance and upkeep</span></div></div><p class=\"statement\">An invitation with an exit.<br>Not a rollout disguised as a favor.</p>",
|
||||
"notes": "Meet leads, developers and reviewers across contrasting workflows before recruiting one willing team. Show a concrete example to a skeptic and invite them to judge it without requiring enrollment. Agree a short weekly team check-in and a monthly CTO decision review. Record participant and reviewer effort: it is not free labor. If priorities conflict, ask the CTO to choose a trade-off rather than use sponsorship as a compliance escalation. Actual approvers must be named before a pilot.",
|
||||
"sources": [
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "months-one-two",
|
||||
"title": "Months 1–2 / Earn the right to test.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"timeline\"><div><b>01 · Discover</b><p>Trace real changes.<br>Rank friction and evidence gaps.</p><span>Output: current-work map</span></div><div><b>02 · Agree</b><p>One willing team.<br>Baseline + smallest intervention.</p><span>Output: bounded experiment packet</span></div></div><div class=\"gate\">Decision 1 → Fund one experiment—or hold.</div><p class=\"small\">No partner, reliable checks or lawful evidence → no live pilot.</p>",
|
||||
"notes": "In month one agree expectations and access with the CTO, pair on contrasting workflows and trace repository principles, system logic, tests, builds and deployments. Rank bottlenecks, not teams. Month two observes a prospective baseline and compares context, coaching, test feedback, deterministic automation and skills. Agree task eligibility, acceptance, evidence, people, spend/effort limits and a stop date. The experiment packet can be one worksheet plus existing records. Discovery may need to continue; the calendar does not waive prerequisites.",
|
||||
"sources": [
|
||||
"six-months-roadmap",
|
||||
"baseline"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "months-three-four",
|
||||
"title": "Months 3–4 / Test, then decide.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"timeline\"><div><b>03 · Work alongside</b><p>Build and independently qualify.<br>Pair on bounded real work.</p><span>Output: failures + reproducible examples</span></div><div><b>04 · Compare</b><p>Reconcile outcomes and burden.<br>Include pending and abandoned work.</p><span>Output: retain / change / hold / stop</span></div></div><div class=\"gate\">Decision 2 → Keep only what the evidence supports.</div><p class=\"small\">Missing follow-up is “unknown”, not “all clear”.</p>",
|
||||
"notes": "Qualification precedes exposure to real work; actual pilot permission is a separate human decision. During month three I pair and collect both benefits and transferred work. Month four compares matured cohorts with the reviewer, records task mix and concurrent changes, and gives the owner and CTO a recommendation. Unsafe work stops immediately. Sparse tasks or missing follow-up make the result inconclusive. Only an explicitly approved bounded extension can continue; otherwise narrow or stop. Do not silently convert a feasibility exercise into a rollout.",
|
||||
"sources": [
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "months-five-six",
|
||||
"title": "Months 5–6 / Transfer only if earned.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"timeline\"><div><b>05 · Selective transfer</b><p>Champion + backup.<br>Check a second team’s fit.</p><span>Only with capacity and funded upkeep</span></div><div><b>06 · Evidence review</b><p>Team operates without daily help.<br>CTO chooses the next investment.</p><span>Owned workflow—or documented stop</span></div></div><p class=\"statement\">New scope → new baseline.<br>No automatic company-wide rollout.</p>",
|
||||
"notes": "A second team is conditional: willingness, different task mix and support capacity can all change the answer. Keep improving the first workflow if transfer is premature. Hand over a reproducible example, support and recovery instructions to an actual owner and backup. Test operation without my daily assistance rather than treating training attendance as handover. Month six must show limits and stopped work as well as retained value. The CTO decides what is worth funding next.",
|
||||
"sources": [
|
||||
"six-months-roadmap",
|
||||
"six-months-target"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "capacity",
|
||||
"title": "One architect. One active live pilot.",
|
||||
"minutes": 1,
|
||||
"body": "<p>Example weekly allocation for the AI architect</p><div class=\"capacity\" aria-label=\"Proposed weekly allocation: two days hands-on, one evaluation, one relationships, one support and decisions\"><div class=\"pair\">2 days<br><b>Pair + build</b></div><div>1 day<br><b>Evaluate</b></div><div>1 day<br><b>Relationships</b></div><div>1 day<br><b>Decisions + buffer</b></div></div><p class=\"statement\">Support is work.<br>Put it in the budget.</p><p class=\"small\">Proposed capacity envelope—not known company availability.</p>",
|
||||
"notes": "This five-day allocation is a planning envelope, not a claim about company staffing. Two days are hands-on, one evaluation, one coaching/relationships, one sponsor decisions, support and contingency. Team lead agreement must include review time. A second team begins only when the first is supportable. Offer reusable examples and bounded office hours, not a permanent help desk to more than ten teams. Excess support demand becomes a CTO investment decision or a smaller scope.",
|
||||
"sources": [
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "measures",
|
||||
"title": "Three measures. One decision.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"measure-list\"><div><b>Accepted work</b><span>Accepted / all matured eligible starts</span></div><div><b>Review + rework</b><span>Comparable effort, including shifted burden</span></div><div><b>Escaped defects</b><span>Severity and complete follow-up</span></div></div><div class=\"rail\">Alongside: setup, support, upkeep and tool cost. Critical effects stop work.</div><p class=\"small\">Task / PR / CI / defect links + a small effort record; no individual league tables.</p>",
|
||||
"notes": "Use a small balanced set matched to the mechanism, not all sixteen optional metric contracts. Predeclare eligibility, maturity horizons, denominator and follow-up. Register every eligible task start, including failures, abandoned work and unresolved matured starts; pending tasks stay separate. Link tasks to exact PR/CI acceptance and defect records, with a minimal effort log. Record checked reasons for returns, such as missing regression evidence. Agree access, purpose and retention; avoid raw prompt collection and individual performance ranking. Show total setup and recurring cost beside outcomes. If linkage is incomplete, hold the claim.",
|
||||
"sources": [
|
||||
"measurement",
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "misleading",
|
||||
"title": "A dashboard can be confidently wrong.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"contrast traps\"><p><b>Tempting signal</b><br>More PRs or generated lines<br>Shorter PR elapsed time<br>Higher acceptance rate<br>No defects recorded</p><p><b>Question before believing it</b><br>Useful work—or smaller slices?<br>Less effort—or less waiting?<br>Same task mix and denominator?<br>Enough follow-up and linkage?</p></div><p class=\"statement\">AI usage is diagnostic.<br>It is not the score.</p>",
|
||||
"notes": "Invocation counts, licenses and positive sentiment can help diagnose reach or friction, but are not productivity outcomes. Acceptance changes may reflect selection and learning; stratify by complexity and reviewer availability and record concurrent model/tool/CI changes. Elapsed time is not engineer hours. Missing quality records are not zero defects. Small descriptive samples cannot establish causal ROI; agree uncertainty and precision rules before collecting evidence for a promotion claim. Do not annualize a tiny difference into cash savings.",
|
||||
"sources": [
|
||||
"measurement",
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "qualification",
|
||||
"title": "“It worked once” is not a release gate.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"flow\"><span>Pin candidate<br>and environment</span><i>→</i><span>Independent<br>qualification</span><i>→</i><span>Separate<br>pilot permission</span></div><div class=\"contrast\"><p><b>Try to break it</b><br>Wrong task · injected instruction<br>Missing tests · recovery</p><p><b>First revision</b><br>No approved prior skill = N/A<br>Remove + reload → current practice</p></div><div class=\"rail\">Failed mandatory safety checks → HOLD. An average cannot override them.</div>",
|
||||
"notes": "The author cannot approve their own evidence or deployment. Test representative work, unrelated-task decline, injected instructions to bypass review, missing-test escalation, and removal/reload recovery. These examples are not a complete risk-tier evaluation suite. A real independent reviewer approves a risk-appropriate design and inspects all results. First-revision regression against an approved skill is N/A, not a fake pass; prove recovery to declared existing AI-assisted practice. The actual workflow approver separately authorizes the exact revision/client, cohort, window, expiry and effects. Security/data boundaries need their actual owners. Later revision changes return to qualification.",
|
||||
"sources": [
|
||||
"six-months-roadmap",
|
||||
"skills-quality"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "experiment",
|
||||
"title": "EXP-01 / Better acceptance is not enough.",
|
||||
"minutes": 2,
|
||||
"body": "<p class=\"fiction\">Fictional teaching example · not Eldorado results or approval</p><div class=\"flow\"><span>Missing test evidence<br>→ checklist first</span><i>→</i><span>Incomplete follow-up<br>→ hold expansion</span><i>→</i><span>Higher review burden<br>→ stop candidate</span></div><p class=\"statement\">Keep the useful practice.<br>Reject the unsupported benefit claim.</p><p class=\"small\">Existing AI practice is the comparator. A skill is tested only if needed.</p>",
|
||||
"notes": "Keep one example from baseline to decision. Suppose changes repeatedly lack regression evidence. Compare a repository test map plus review checklist against packaging the same guidance as a skill; the cheaper checklist wins if it performs as well. A skill carries reusable instructions and verification, not authority. Freeze a small non-urgent bug-fix scope, one willing team and one qualified client/model tuple. The full fictional packet includes explicit real-use blanks for people, dates, immutable references, sources and data approval. Those blanks are not permission. The apparent nine versus eight accepted is not a demonstrated gain. Baseline has two failed, one abandoned and one unresolved; pilot has one of each. Three later starts have not matured and stay out of the matured denominator. At first review pilot effort median is 35 minutes among observed rows only, not the whole cohort. One non-severe baseline defect is known; pilot defect follow-up is incomplete. A tiny sample, different mix and learning also limit inference. The fictional owner may authorize one two-week evidence-only extension with no new starts, at most four architect hours, two reviewer hours and EUR25 additional spend. If reconciliation cannot finish, stop rather than keep extending. Assume reconciliation finds a 40-minute median against 30 baseline for comparable work, with reviewers tracing extra effort to checking generated tests. This breaches the fictional no-increase burden guardrail even with nine accepted tasks. It is sufficient for a local stop decision, not statistical proof the intervention fails everywhere. Remove/reload and verify current-practice recovery; preserve evidence and useful test map/checklist. Return failure cases to the author. Retain would require different evidence: complete comparable outcomes and costs, acceptable quality/burden, agreed precision, independent acceptance and funded upkeep. A new revision must requalify. Critical unauthorized effects stop immediately, not at the scheduled review. The sample table and extension caps are speaker-reference detail, not the main strategy story. Use only the three visible decisions in the planned narration; expand into these numbers only if asked.",
|
||||
"sources": [
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Roadmap",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "month-six",
|
||||
"title": "Month six / An evidence portfolio, not a victory lap.",
|
||||
"minutes": 1,
|
||||
"body": "<div class=\"ledger\"><div><b>Visible change</b><b>Evidence to ask for</b></div><div><span>One workflow understood</span><span>Map + baseline + explicit gaps</span></div><div><span>Retained practice—or justified stop</span><span>Comparable outcomes + costs + limits</span></div><div><span>Less dependence on the architect</span><span>Owner + backup + recovery rehearsal</span></div></div><p class=\"small\">Proposed achievable picture. No guaranteed savings, headcount reduction or org-wide uplift.</p>",
|
||||
"notes": "Commit to activities I can drive: discovery, agreement, hands-on support, reproducible evidence and clear decisions. Do not promise a positive effect outside my control. A realistic month-six organization has one bounded workflow learned from, transparent limitations, some reusable examples and an owner if anything is retained. A second willing team may have a new baseline, not a blanket rollout. If experiments stop, explain what was ruled out, what remains useful and why the next investment changes. Independent source-linked evidence, not a polished demo or attendance count, backs the picture.",
|
||||
"sources": [
|
||||
"six-months-target",
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "6 Months Target",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "beyond",
|
||||
"title": "Beyond 6 Months / Progress toward the Target.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"choices\"><div><b>Deepen</b><p>Coaching, context or deterministic tooling where friction remains.</p></div><div><b>Transfer</b><p>Only with repeatable value, local fit and supported ownership.</p></div><div><b>Toward autonomy</b><p>Separate authority case, containment and human takeover.</p></div></div><p class=\"statement\">Established destination. Evidence-led steps.<br>Separate authority—not automatic graduation.</p>",
|
||||
"notes": "The next quarter may deepen the existing workflow or stop expansion entirely. Skills remain optional; no catalog or central control platform is a prerequisite. Transfer needs new-scope baseline and local capacity. Consider bounded autonomy only if it solves an evidenced bottleneck and controls are proven: exact-artifact approvals, scoped identity, idempotency, audit, independent stop and takeover. People retain product, risk and release decisions. The long-term destination remains human-directed, guided and reviewed autonomous SDLC. These six months contribute toward that vision, not replace it; they do not promise its timing or authorize its execution. The CTO chooses investment based on the evidence, not an inevitable maturity staircase.",
|
||||
"sources": [
|
||||
"stage-02-autonomous-agent",
|
||||
"target-operating-model",
|
||||
"roadmap",
|
||||
"six-months-target"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Beyond 6 Months",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "authority",
|
||||
"title": "Toward autonomy / Change authority deliberately.",
|
||||
"minutes": 2,
|
||||
"body": "<div class=\"flow\"><span>Observe +<br>assemble evidence</span><i>→</i><span>Propose +<br>route work</span><i>⇢</i><span>Separately authorize<br>scoped execution</span></div><div class=\"rail\">Exact-artifact approval · scoped identity · audit + recovery</div><p class=\"statement\">Independent stop. Human takeover.</p><p class=\"small\">Readiness failure → hold or redesign. Missing evidence is never permission.</p>",
|
||||
"notes": "Progress toward the established Target by granting only the extra operation that an evidenced business case needs. Reliable observation and evidence assembly come before proposing and routing; neither permits mutation, merge or deployment. A separate human decision names the exact resources, data, artifact and scope. Prove identity separation, checks outside candidate control, idempotency, duplicate/outage recovery and audit. Test a kill switch and human takeover outside the model before trusting scoped execution. The agent cannot appoint approvers or edit its own gates. Changed boundaries reopen review; harmful behavior revokes authority and feeds learning back to Quality and Maintenance. This is the bridge toward the autonomous Target, not an installed system or a dated commitment.",
|
||||
"sources": [
|
||||
"stage-02-autonomous-agent",
|
||||
"target-operating-model"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Beyond 6 Months",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "alignment",
|
||||
"title": "The first CTO conversation",
|
||||
"minutes": 1,
|
||||
"body": "<ol class=\"asks\"><li>Which outcome is worth improving first?</li><li>Who can volunteer time—and independent review?</li><li>What data, risk and effort limits apply?</li><li>When will we decide to continue or stop?</li></ol><p class=\"statement\">Sponsor the learning.<br>Do not pre-approve the answer.</p>",
|
||||
"notes": "Close with concrete alignment, not a shopping list. Ask the CTO to agree an outcome, access to willing teams, independent review capacity, risk/data boundary and decision cadence. Agree success and stop criteria before collecting favorable anecdotes. The long-term Target and Roadmap establish the destination; the six-month plan is a realistic contribution toward it. We have covered the four assignment questions: action, measurement, realistic six-month evidence and conditional next investment. Transition to the fifteen-minute discussion. If time runs short, skip detail in narration rather than the decision and its limits.",
|
||||
"sources": [
|
||||
"PDF: questions 1–4",
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"kind": "dark",
|
||||
"section": "Discussion",
|
||||
"track": "main"
|
||||
},
|
||||
{
|
||||
"id": "discussion",
|
||||
"title": "Q&A / What would change your mind?",
|
||||
"minutes": 15,
|
||||
"body": "<p class=\"subtitle\">15 minutes for the hard questions.</p><div class=\"discussion\"><p>No willing team?</p><p>Too little evidence?</p><p>A cheaper non-AI fix?</p></div><p class=\"small\">The proposed plan can change. The evidence standard should not.</p>",
|
||||
"notes": "Reserve the full fifteen minutes. If no team volunteers, revisit the problem and sponsor trade-offs rather than conscript people. If evidence is sparse, narrow the question, explicitly authorize a bounded evidence-completion window or stop. If deterministic tooling is better, choose it. Discuss the company’s real constraints rather than pretend the fictional example estimates company benefit. The next slide provides linked sources for follow-up, not additional spoken content.",
|
||||
"sources": [
|
||||
"PDF: Format",
|
||||
"six-months-target"
|
||||
],
|
||||
"kind": "dark",
|
||||
"section": "Discussion",
|
||||
"track": "discussion"
|
||||
},
|
||||
{
|
||||
"id": "references",
|
||||
"title": "References / Follow the evidence.",
|
||||
"minutes": 0,
|
||||
"body": "<ul class=\"references\"><li>AI Architect Test Task · Eldorado.gg<br><span>Context, four questions, assumptions, 50-minute format</span></li><li><a href=\"../../strategy/target-operating-model/\">Long-term Target</a> · <a href=\"../../strategy/roadmap/\">Roadmap →</a></li><li><a href=\"../../strategy/six-months-target/\">6 Months Target →</a></li><li><a href=\"../../strategy/six-months-roadmap/\">6 Months Roadmap →</a></li><li><a href=\"../../strategy/six-months-roadmap/#exp-01-a-small-decision-ready-example\">EXP-01 packet and decision limits →</a></li><li><a href=\"../../strategy/measurement/\">Measurement definitions and safeguards →</a></li><li><a href=\"../../strategy/stage-02-autonomous-agent/\">Beyond 6 Months →</a></li></ul>",
|
||||
"notes": "Appendix, zero planned talk time. The original assignment is the supplied AI_Architect_Test_Task.pdf. The source-reference map in this presentation directory records every slide against the PDF and reviewed Strategy. The deck does not reproduce the assignment file publicly. EXP-01 remains entirely fictional; its budget, medians, samples and outcomes are teaching devices. Official Reveal documentation consulted: installation, speaker-view and pdf-export on revealjs.com. All runtime assets are pinned and bundled locally.",
|
||||
"sources": [
|
||||
"PDF: complete assignment",
|
||||
"six-months-target",
|
||||
"six-months-roadmap",
|
||||
"measurement",
|
||||
"stage-02-autonomous-agent"
|
||||
],
|
||||
"kind": "",
|
||||
"section": "Reference",
|
||||
"track": "appendix"
|
||||
}
|
||||
];
|
||||
@@ -0,0 +1,25 @@
|
||||
// Presentation-sized views of the canonical topology, not a new operating model.
|
||||
export const phases=['scope','architecture','ui-ux','planning','delivery','uat','security','releases'];
|
||||
export const labels=['Scope','Architecture','UI/UX','Planning','Delivery','UAT','Security','Releases'];
|
||||
export const topology={
|
||||
lifecycle:phases.map((id,i)=>[id,phases[(i+1)%phases.length]]),
|
||||
governance:phases.map(id=>['agent',id]),
|
||||
contributions:phases.map(id=>[`code-${id}`,id]),
|
||||
};
|
||||
function cycle(portrait){
|
||||
const key=portrait?'phone':'wide';
|
||||
const w=portrait?540:1096,h=portrait?540:350;
|
||||
const xs=portrait?[100,270,440]:[200,548,896],ys=portrait?[65,270,475]:[40,175,310];
|
||||
const pos=[[xs[1],ys[0]],[xs[2],ys[0]],[xs[2],ys[1]],[xs[2],ys[2]],[xs[1],ys[2]],[xs[0],ys[2]],[xs[0],ys[1]],[xs[0],ys[0]]];
|
||||
const bw=portrait?154:202,bh=52,cx=xs[1],cy=ys[1],cw=portrait?164:270,ch=portrait?112:94;
|
||||
const edge=(a,b)=>{const dx=b[0]-a[0],dy=b[1]-a[1],t=Math.min(dx?bw/2/Math.abs(dx):Infinity,dy?bh/2/Math.abs(dy):Infinity);return [a[0]+dx*t,a[1]+dy*t]};
|
||||
const path=(d,type,from,to)=>`<path d="${d}" class="${type}" data-from="${from}" data-to="${to}" marker-end="url(#${key}-${type})"/>`;
|
||||
let lines=pos.map((a,i)=>{const b=pos[(i+1)%8],p=edge(a,b),q=edge(b,a);return path(`M${p} L${q}`,'cycle-edge',...topology.lifecycle[i])}).join('');
|
||||
// Top and bottom share a center exit; side spokes enter the side phases.
|
||||
lines+=pos.map(([x,y],i)=>{let d;if(y<cy)d=`M${cx},${cy-ch/2} V${(cy-ch/2+y+bh/2)/2} H${x+(x<cx?30:x>cx?-30:0)} V${y+bh/2}`;else if(y>cy)d=`M${cx},${cy+ch/2} V${(cy+ch/2+y-bh/2)/2} H${x+(x<cx?30:x>cx?-30:0)} V${y-bh/2}`;else d=`M${cx+(x>cx?cw/2:-cw/2)},${cy} H${x+(x>cx?-bw/2:bw/2)}`;return path(d,'govern-edge',...topology.governance[i])}).join('');
|
||||
const nodes=pos.map(([x,y],i)=>`<g data-node="${phases[i]}"><rect x="${x-bw/2}" y="${y-bh/2}" width="${bw}" height="${bh}"/><text x="${x}" y="${y+8}">${labels[i]}</text></g>`).join('');
|
||||
const center=portrait?['Autonomous','agent','Human-controlled']:['Autonomous agent','Human-controlled'];
|
||||
return `<svg class="target-cycle ${key}" viewBox="0 0 ${w} ${h}" role="img" aria-label="Intended SDLC: Scope, Architecture, UI/UX, Planning, Delivery, UAT, Security, Releases and back to Scope. One human-controlled autonomous agent executes and governs all eight phases."><defs>${['cycle-edge','govern-edge'].map(t=>`<marker id="${key}-${t}" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="5" markerHeight="5" orient="auto-start-reverse"><path d="M0 0 L10 5 L0 10z" fill="${t==='cycle-edge'?'#14131a':'#936500'}"/></marker>`).join('')}</defs>${lines}${nodes}<g data-node="agent" class="central"><rect x="${cx-cw/2}" y="${cy-ch/2}" width="${cw}" height="${ch}"/>${center.map((t,i)=>`<text x="${cx}" y="${cy-(center.length-1)*14+i*28+8}" class="${i===center.length-1?'control-label':''}">${t}</text>`).join('')}</g></svg>`;
|
||||
}
|
||||
export const cycleFigure=cycle(false)+cycle(true);
|
||||
export const contributionsFigure=`<div class="contribution-grid">${phases.map((id,i)=>`<div data-from="code-${id}" data-to="${id}"><span>AI Agent</span><i aria-label="contributes to">⇢</i><b>${labels[i]}</b></div>`).join('')}</div>`;
|
||||
@@ -0,0 +1,115 @@
|
||||
@font-face{font-family:Lato;src:url(./assets/lato-latin-400-normal.woff2) format('woff2');font-weight:400;font-display:swap}
|
||||
@font-face{font-family:Lato;src:url(./assets/lato-latin-700-normal.woff2) format('woff2');font-weight:700;font-display:swap}
|
||||
@font-face{font-family:Lato;src:url(./assets/lato-latin-900-normal.woff2) format('woff2');font-weight:900;font-display:swap}
|
||||
:root{--gold:#ffc950;--ink:#14131a;--paper:#f6f6f6}
|
||||
body{margin:0;background:var(--paper);color:var(--ink)}
|
||||
.deck{font:30px/1.35 Lato,sans-serif;color:var(--ink)}
|
||||
.deck .slides{text-align:left}
|
||||
.deck .slides section{box-sizing:border-box;padding:48px 52px;height:660px}
|
||||
.deck h1,.deck h2{font-weight:900;letter-spacing:-.045em;line-height:1.07;margin:18px 0 30px;color:inherit;text-transform:none}
|
||||
.deck h1{font-size:80px;max-width:960px}.deck h2{font-size:52px;max-width:1020px}
|
||||
.deck p{margin:20px 0}.deck .eyebrow{font-size:17px;letter-spacing:.15em;font-weight:900;color:#805b00;margin:0}
|
||||
.deck .subtitle{font-size:34px}.deck .thesis{font-size:37px;margin-top:52px;border-left:6px solid var(--gold);padding-left:24px}
|
||||
.deck .small{font-size:21px;line-height:1.4;color:#62616b;margin-top:24px}.deck .statement{font-size:35px;font-weight:700;margin-top:32px}
|
||||
.deck .dark{color:var(--paper)}.deck .dark .eyebrow,.deck .dark h1{color:var(--gold)}.deck .dark .small{color:#d5d4dc}
|
||||
.deck .facts{display:flex;gap:40px;justify-content:space-between;margin:35px 0}.deck .facts strong{display:block;font-size:43px;line-height:1.12}.deck .facts span{display:block;font-size:24px;margin-top:12px}
|
||||
.deck .contrast{display:grid;grid-template-columns:1fr 1fr;gap:44px;border-top:2px solid #dedee3;margin-top:28px;padding-top:8px}.deck .contrast p{font-size:27px;line-height:1.55}.deck .contrast b{color:#805b00;display:inline-block;margin-bottom:10px}
|
||||
.deck .flow{display:flex;align-items:stretch;gap:18px;margin:40px 0 26px}.deck .flow span{flex:1;border:2px solid #14131a;padding:24px 18px;font-weight:700;font-size:27px;text-align:center;display:flex;align-items:center;justify-content:center}.deck .flow i{align-self:center;font-style:normal}
|
||||
.deck .rail{border-left:6px solid var(--gold);padding:16px 24px;background:#e9e9ec;font-size:25px;font-weight:700}
|
||||
.deck .roles{display:grid;grid-template-columns:1fr 1.2fr 1fr;gap:18px;margin:32px 0}.deck .roles div{padding:24px;border:2px solid #14131a}.deck .roles b{display:block;font-size:34px;margin-bottom:18px}.deck .roles span{font-size:26px;line-height:1.5}.deck .roles .gold{background:var(--gold)}
|
||||
.deck .timeline{display:grid;grid-template-columns:1fr 1fr;gap:46px;margin:35px 0}.deck .timeline>div{border-top:8px solid var(--gold);padding-top:20px}.deck .timeline b{font-size:35px}.deck .timeline p{font-size:28px}.deck .timeline span{font-size:23px;color:#62616b}
|
||||
.deck .gate{background:var(--ink);color:var(--gold);font-size:29px;font-weight:900;padding:20px 24px}
|
||||
.deck .capacity{display:flex;margin:50px 0;gap:5px}.deck .capacity>div{flex:1;background:#e3e3e7;font-size:25px;padding:28px 16px;border-bottom:5px solid var(--ink)}.deck .capacity .pair{flex:2;background:var(--gold)}.deck .capacity b{display:block;margin-top:18px;font-size:24px}
|
||||
.deck .measure-list>div{display:grid;grid-template-columns:310px 1fr;gap:24px;border-top:1px solid #b8b7c0;padding:20px 0}.deck .measure-list b{font-size:32px}.deck .measure-list span{font-size:27px}.deck .measure-list{margin-bottom:24px}
|
||||
.deck .fiction{display:inline-block;background:#fff0cd;color:#594000;font-size:21px;padding:7px 12px;margin:0}
|
||||
.deck table{width:100%;border-collapse:collapse;margin:22px 0;font-size:25px}.deck th,.deck td{text-align:left;border-bottom:1px solid #b8b7c0;padding:15px 10px}.deck th{font-weight:900;font-size:23px;background:#e9e9ec}
|
||||
.deck .comparison{display:flex;align-items:center;gap:35px;margin:40px 0}.deck .comparison div{flex:1}.deck .comparison strong{display:block;font-size:80px;letter-spacing:-.05em}.deck .comparison span{font-size:23px}.deck .comparison .versus{font-size:50px}
|
||||
.deck .ledger{margin:40px 0}.deck .ledger>div{display:grid;grid-template-columns:1fr 1fr;gap:32px;padding:21px 0;border-bottom:1px solid #b8b7c0;font-size:27px}.deck .ledger b{color:#805b00}
|
||||
.deck .choices{display:grid;grid-template-columns:repeat(3,1fr);gap:28px;margin:40px 0}.deck .choices>div{border-top:6px solid var(--gold);padding-top:20px}.deck .choices b{font-size:33px}.deck .choices p{font-size:27px}
|
||||
.deck .asks{font-size:33px;line-height:1.6;margin:35px 0 0;padding-left:38px}.deck .asks li{padding-left:12px}
|
||||
.deck .discussion{display:flex;flex-direction:column;border-left:5px solid var(--gold);padding-left:28px;margin-top:40px}.deck .discussion p{font-size:36px;margin:10px 0}
|
||||
.deck a{color:#805b00;text-decoration:underline}.deck .references{font-size:27px;line-height:1.5;padding-left:28px}.deck .references li{margin:12px 0}.deck .references span{font-size:22px;color:#62616b}
|
||||
.deck .controls{color:#805b00}.deck .slide-number{font:16px Lato,sans-serif;background:#14131a;color:#fff;left:18px;right:auto;bottom:18px;padding:8px}
|
||||
.deck .progress{color:#805b00;height:4px}
|
||||
.toolbar{position:fixed;z-index:30;top:0;left:0;right:0;display:flex;align-items:center;gap:16px;background:#101014;color:#fff;padding:8px 18px;font:14px Lato,sans-serif;min-height:32px;box-sizing:content-box}
|
||||
.toolbar a{color:var(--gold)}.toolbar button{font:inherit;color:white;border:1px solid #62616b;background:transparent;padding:6px 10px;cursor:pointer}.toolbar .help{margin-left:auto}
|
||||
a:focus-visible,button:focus-visible{outline:3px solid #b88719;outline-offset:3px}
|
||||
.reveal.deck{height:calc(100dvh - 48px);top:48px}
|
||||
@media(max-width:600px){.toolbar{gap:9px;font-size:12px;padding:8px}.toolbar .help{display:none}.toolbar button{padding:6px}.deck .controls{bottom:18px}}
|
||||
@media(max-width:360px){.toolbar{gap:4px}}
|
||||
/* Portrait is re-composed, not a postage-stamp landscape slide. */
|
||||
.portrait .deck .slides section{height:1000px;padding:28px}
|
||||
.portrait .deck h1{font-size:64px}.portrait .deck h2{font-size:43px;margin-bottom:24px}
|
||||
.portrait .deck .facts{flex-wrap:wrap;gap:28px;margin:30px 0}.portrait .deck .facts strong{font-size:38px}
|
||||
.portrait .deck .contrast{grid-template-columns:1fr;gap:0;margin-top:20px}.portrait .deck .contrast p{font-size:27px;margin:14px 0;line-height:1.4}
|
||||
.portrait .deck .flow{flex-direction:column;gap:8px;margin:24px 0}.portrait .deck .flow span{padding:14px;font-size:27px}.portrait .deck .flow i{transform:rotate(90deg);line-height:1}
|
||||
.portrait .deck .roles{grid-template-columns:1fr;gap:12px}.portrait .deck .roles div{padding:18px}.portrait .deck .roles b{font-size:30px;margin-bottom:8px}.portrait .deck .roles span{font-size:26px}
|
||||
.portrait .deck .timeline{grid-template-columns:1fr;gap:24px;margin:25px 0}.portrait .deck .timeline>div{padding-top:14px}.portrait .deck .timeline p{margin:14px 0;font-size:28px}
|
||||
.portrait .deck .statement{font-size:33px;margin-top:28px}.portrait .deck .rail{font-size:25px;padding:16px}.portrait .deck .gate{font-size:27px;padding:18px}
|
||||
.portrait .deck .capacity{display:grid;grid-template-columns:1fr 1fr;gap:8px}.portrait .deck .capacity>div{padding:24px 16px}
|
||||
.portrait .deck .measure-list>div{grid-template-columns:1fr;gap:10px}.portrait .deck .measure-list b{font-size:31px}
|
||||
.portrait .deck .fiction{font-size:22px}.portrait .deck table{font-size:23px;table-layout:fixed}.portrait .deck th{font-size:22px}.portrait .deck th,.portrait .deck td{padding:15px 8px}
|
||||
.portrait .deck .comparison{gap:20px}.portrait .deck .comparison strong{font-size:54px}.portrait .deck .comparison span{font-size:24px}
|
||||
.portrait .deck .ledger>div{font-size:26px;gap:20px}.portrait .deck .choices{grid-template-columns:1fr;gap:20px}.portrait .deck .choices>div{padding-top:12px}.portrait .deck .choices p{margin:10px 0}
|
||||
.portrait .deck .asks{font-size:31px;line-height:1.45}.portrait .deck .asks li{margin:22px 0}.portrait .deck .small{font-size:24px}
|
||||
.portrait #qualification .contrast{grid-template-columns:1fr 1fr;gap:24px}.portrait #qualification .contrast p{font-size:24px}
|
||||
.portrait .deck .references{font-size:29px}.portrait .deck .references li{margin:22px 0}
|
||||
@media(prefers-reduced-motion:reduce){*{transition:none!important;animation:none!important}}
|
||||
.embedded .toolbar{display:none}
|
||||
.embedded .reveal.deck{top:0;height:calc(100dvh - 48px)}
|
||||
.embedded body{background:#101014}
|
||||
.embedded .deck .controls{position:fixed;bottom:8px;color:var(--gold)!important}
|
||||
.embedded .deck .progress{color:var(--gold)}
|
||||
.embedded .deck .slide-number{position:fixed;bottom:12px}
|
||||
.embedded .deck .progress{position:fixed;bottom:0}
|
||||
@media print{.toolbar{display:none}.reveal.deck{top:0;height:100%}}
|
||||
html.print-pdf .toolbar{display:none}html.print-pdf .reveal.deck{top:0;height:100%}
|
||||
|
||||
/* Distinct strategy views: paired topology, progression and learning loop. */
|
||||
.deck .target-cycle{width:100%;height:350px;display:block;margin:0 auto}
|
||||
.deck .target-cycle.phone{display:none}
|
||||
.target-cycle rect{fill:#f6f6f6;stroke:#14131a;stroke-width:2}
|
||||
.target-cycle text{text-anchor:middle;font:700 24px Lato,sans-serif;fill:#14131a}
|
||||
.target-cycle .central rect{fill:#ffc950}
|
||||
.target-cycle .control-label{font-size:20px;font-weight:400}
|
||||
.target-cycle .cycle-edge{fill:none;stroke:#14131a;stroke-width:2.5}
|
||||
.target-cycle .govern-edge{fill:none;stroke:#936500;stroke-width:2.5;stroke-dasharray:3 5}
|
||||
.deck .diagram-legend{font-size:23px;margin:12px 0}
|
||||
.deck #target .small{font-size:21px;margin:12px 0}
|
||||
.deck .diagram-intro{font-size:30px}
|
||||
.deck .contribution-grid{display:grid;grid-template-columns:repeat(4,1fr);gap:12px 20px;margin:22px 0}
|
||||
.deck .contribution-grid>div{border-top:4px solid #ffc950;padding:10px 8px;display:flex;flex-direction:column;align-items:center;font-size:26px}
|
||||
.deck .contribution-grid i{font-style:normal;transform:rotate(90deg);color:#805b00;font-size:32px;line-height:1.2}
|
||||
.deck .journey{display:flex;gap:16px;align-items:center;margin:36px 0}
|
||||
.deck .journey>div{flex:1;border-top:6px solid #ffc950;padding:18px 6px;align-self:stretch}
|
||||
.deck .journey small,.deck .horizon small{display:block;font-size:17px;color:#805b00;font-weight:900;letter-spacing:.04em;margin-bottom:14px}
|
||||
.deck .journey b{font-size:31px;display:block;margin-bottom:20px}
|
||||
.deck .journey span{font-size:25px}.deck .journey i{font-style:normal}
|
||||
.deck .learning-loop{display:grid;grid-template-columns:1fr 28px 1fr 28px 1fr 28px 1fr;align-items:center;gap:0 8px;margin:22px 0}
|
||||
.deck #learning-loop .statement{margin:16px 0 0}.deck #learning-loop .small{margin-top:12px}
|
||||
.deck .learning-loop span{border:2px solid #14131a;padding:8px;font-size:27px;text-align:center}
|
||||
.deck .learning-loop i{font-style:normal;text-align:center;line-height:1}
|
||||
.deck .learning-loop>:nth-child(1){grid-area:1/1}.deck .learning-loop>:nth-child(2){grid-area:1/2}.deck .learning-loop>:nth-child(3){grid-area:1/3}
|
||||
.deck .learning-loop>:nth-child(4){grid-area:2/3}
|
||||
.deck .learning-loop>:nth-child(5){grid-area:3/3}.deck .learning-loop>:nth-child(6){grid-area:3/4}.deck .learning-loop>:nth-child(7){grid-area:3/5}
|
||||
.deck .learning-loop>:nth-child(8){grid-area:4/5}
|
||||
.deck .learning-loop>:nth-child(9){grid-area:5/5}.deck .learning-loop>:nth-child(10){grid-area:5/6}.deck .learning-loop>:nth-child(11){grid-area:5/7}
|
||||
.deck .horizon{margin:35px 0;border-left:5px solid #ffc950;padding-left:25px}
|
||||
.deck .horizon b{font-size:32px;display:block}.deck .horizon .near{background:#e9e9ec;padding:22px;margin-top:28px}
|
||||
.deck .horizon span{display:block;font-size:25px;margin-top:14px}
|
||||
.portrait .deck .target-cycle.wide{display:none}.portrait .deck .target-cycle.phone{display:block;height:540px}
|
||||
.portrait .deck #target h2{font-size:40px}
|
||||
.portrait .deck #target .small{font-size:24px;margin-top:20px}
|
||||
.portrait .deck #contributors .small{margin:12px 0}
|
||||
.portrait .deck #contributors .contribution-grid{gap:6px;margin:14px 0}
|
||||
.portrait .deck #contributors .contribution-grid>div{padding:4px 8px}
|
||||
.portrait .deck .contribution-grid{grid-template-columns:1fr 1fr;gap:12px;margin:24px 0}
|
||||
.portrait .deck .contribution-grid>div{padding:8px;flex-direction:column;justify-content:center;gap:0;font-size:27px}
|
||||
.portrait .deck .contribution-grid i{transform:rotate(90deg)}.portrait .deck .contribution-grid b{text-align:center}
|
||||
.portrait .deck .journey{flex-direction:column;gap:4px;margin:18px 0}
|
||||
.portrait .deck .journey>div{width:100%;padding:12px 0;border-top-width:4px}
|
||||
.portrait .deck .journey b{font-size:29px;margin-bottom:8px}.portrait .deck .journey small{margin-bottom:8px}
|
||||
.portrait .deck .journey i{transform:rotate(90deg);line-height:1}
|
||||
.portrait .deck .learning-loop{grid-template-columns:1fr 16px 1fr 16px 1fr 16px 1fr;gap:0 3px;margin:30px 0}
|
||||
.portrait .deck .learning-loop span{font-size:24px;padding:14px 2px}
|
||||
.portrait .deck .horizon b{font-size:32px}
|
||||
@@ -0,0 +1,169 @@
|
||||
{
|
||||
"source": {
|
||||
"file": "AI_Architect_Test_Task.pdf",
|
||||
"sha256": "12b2406766996056d0a361cf76b2d8fbe4dfdfad6a16c2cc4d5ee03a51a384a5",
|
||||
"attachment_message": "1557767519748759646",
|
||||
"authorization_message": "1557786954383368264",
|
||||
"read_scope": "Full PDF, Format, Context and all four assignment questions, plus assumptions instruction"
|
||||
},
|
||||
"requirements": [
|
||||
{
|
||||
"id": "format",
|
||||
"source_section": "Format",
|
||||
"requirement": "Live presentation: 50 minutes including Q&A; content over polish",
|
||||
"pages": [
|
||||
"six-months-target"
|
||||
],
|
||||
"markers": [
|
||||
"35 minutes content + 15 minutes Q&A",
|
||||
"Content matters more than visual polish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "context",
|
||||
"source_section": "Context",
|
||||
"requirement": "Close to 80 engineering people, around 100 by year end, more than 10 teams; every developer already uses AI unevenly; real output not usage",
|
||||
"pages": [
|
||||
"six-months-target",
|
||||
"baseline"
|
||||
],
|
||||
"markers": [
|
||||
"80 engineers",
|
||||
"100 by year end",
|
||||
"more than 10 teams",
|
||||
"current AI-assisted practice"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "q1",
|
||||
"source_section": "Assignment 1",
|
||||
"requirement": "Month 1–6 concrete priorities and change starting solo, CTO reporting, no formal team authority",
|
||||
"pages": [
|
||||
"six-months-roadmap",
|
||||
"six-months-target"
|
||||
],
|
||||
"markers": [
|
||||
"Month 1",
|
||||
"Month 2",
|
||||
"Month 3",
|
||||
"Month 4",
|
||||
"Month 5",
|
||||
"Month 6",
|
||||
"One active live pilot at a time",
|
||||
"no formal authority",
|
||||
"monthly CTO review"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "q2",
|
||||
"source_section": "Assignment 2",
|
||||
"requirement": "Know whether engineering output improves; track meaningful measures and explain misleading signals",
|
||||
"pages": [
|
||||
"measurement/index",
|
||||
"six-months-roadmap",
|
||||
"baseline"
|
||||
],
|
||||
"markers": [
|
||||
"Review/rework minutes",
|
||||
"Escaped defects and severity",
|
||||
"Where this misleads",
|
||||
"task mix",
|
||||
"not a causal ROI claim",
|
||||
"source",
|
||||
"uncertainty"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "q3",
|
||||
"source_section": "Assignment 3",
|
||||
"requirement": "Realistic visible month-six changes backed by evidence",
|
||||
"pages": [
|
||||
"six-months-target",
|
||||
"six-months-roadmap"
|
||||
],
|
||||
"markers": [
|
||||
"Activities I commit",
|
||||
"Contingent visible outcome",
|
||||
"one partner team",
|
||||
"matured defect follow-up",
|
||||
"documented stop"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "q4",
|
||||
"source_section": "Assignment 4",
|
||||
"requirement": "Role and organization AI use beyond six months",
|
||||
"pages": [
|
||||
"stage-02-autonomous-agent",
|
||||
"six-months-target"
|
||||
],
|
||||
"markers": [
|
||||
"dedicated enablement capacity",
|
||||
"deterministic tooling",
|
||||
"long-term strategy vision",
|
||||
"not automatic progression"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "assumptions",
|
||||
"source_section": "Final instruction",
|
||||
"requirement": "State assumptions where stack, tooling or processes are unknown",
|
||||
"pages": [
|
||||
"six-months-target"
|
||||
],
|
||||
"markers": [
|
||||
"Assumptions register",
|
||||
"PDF fact",
|
||||
"Unknown:",
|
||||
"Hypothesis:",
|
||||
"If false"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "F1",
|
||||
"source_section": "Professional audit F1",
|
||||
"requirement": "First-revision comparator and recovery without invented prior approved bundle",
|
||||
"pages": [
|
||||
"skills-quality",
|
||||
"skills-governance",
|
||||
"skills-maintenance"
|
||||
],
|
||||
"markers": [
|
||||
"first-revision",
|
||||
"N/A",
|
||||
"pinned clean",
|
||||
"independent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "F2-F3",
|
||||
"source_section": "Professional audit F2/F3",
|
||||
"requirement": "Coherent illustrative packet, inconclusive bounded extension/stop, effort and value",
|
||||
"pages": [
|
||||
"six-months-roadmap",
|
||||
"skills-quality"
|
||||
],
|
||||
"markers": [
|
||||
"EXP-01",
|
||||
"Entirely fictional",
|
||||
"Inconclusive at first review",
|
||||
"one two-week evidence-completion extension",
|
||||
"Conclusive stop on burden",
|
||||
"one-off setup",
|
||||
"optional reference designs"
|
||||
]
|
||||
}
|
||||
],
|
||||
"verification_sources": [
|
||||
"scripts/assignment.test.mjs",
|
||||
"scripts/connected-strategy.test.mjs",
|
||||
"scripts/strategy-navigation.test.mjs",
|
||||
"scripts/strategy-story.test.mjs",
|
||||
"scripts/verify.mjs",
|
||||
"scripts/browser/skills-stories.cjs",
|
||||
"scripts/browser/strategy-navigation.cjs",
|
||||
"scripts/browser/target-midpoints.cjs",
|
||||
"scripts/browser/roadmap-timeline.cjs"
|
||||
],
|
||||
"scope": "Traceability is a review aid, not semantic approval or business evidence. All 30 routes remain in strategy-coverage.json; all 16 canonical contracts retain original checksums, 9 prototypes and 7 unimplemented. Reviewer must cold-read the actual pages and inspect complete exports."
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
# Strategy horizons — correction evidence matrix
|
||||
|
||||
Authority: user message `1557813737941901572` in Eldorado storm-v1. This correction restores the agreed long-term destination; it does not authorize autonomous execution. Original PDF read in full: Format, Context, all four questions and assumptions instruction; its existing SHA-256 remains in `assignment-evidence.json`.
|
||||
|
||||
| Horizon / reader destination | Origin and preservation | Result / boundary | Verification |
|
||||
| --- | --- | --- | --- |
|
||||
| Target `/strategy/target-operating-model/` | Meaningful Target body restored from pre-PR38 `88a43757762114a506f57ed4b44484306cae1aaa`; original desktop/mobile `strategy-target` JSON unchanged | Human-directed/guided/reviewed autonomous SDLC is the long-term vision, not merely a competing optional destination. Eight lifecycle phases, central agent with eight governance spokes, eight outside human-controlled AI Agents; no fixed timing or present permission | `sdlc-cycle`, `target-midpoints`, `assignment` tests; real inline/fullscreen and complete light/dark exports |
|
||||
| Roadmap `/strategy/roadmap/` | Original three-level body and six paired workflow JSON files restored from the same historical revision, then reconciled with intervention choice and new links | Skills/practices adoption → controlled autonomous capabilities; Delivery first, remaining phase order undecided, Delivery keeps improving. Evidence and separate human authority, not automatic graduation | `roadmap`, `roadmap-viewer`, browser `roadmap-timeline` |
|
||||
| 6 Months Target `/strategy/six-months-target/` | PR38 assignment narrative moved out of Target, including the entire assumptions register and credible outcome conditions | PDF facts: close to80 engineers growing toward100, more than10 teams, everyone already using AI unevenly; solo CTO-reporting architect with no formal team authority. Actual stack/reporting/capacity unknown. First six months contribute toward—not replace—the destination | `assignment-evidence.json` maps all four PDF answers, format and assumptions to actual pages |
|
||||
| 6 Months Roadmap `/strategy/six-months-roadmap/` | PR38 month1–6 action plan, influence/capacity and full EXP-01 packet preserved here as the single plan | One active pilot; independent checks; explicit effort limits, recovery, inconclusive extension and stop. EXP-01 remains fictional. No benefits, approvals or organization-wide rollout fabricated | Assignment markers; exact EXP-01 packet preservation; first-revision tests; browser six-month diagram controls and exports |
|
||||
| Beyond 6 Months `/strategy/stage-02-autonomous-agent/` | Existing useful autonomy-stage content and diagram retained | Connect evidence-led next investments toward long-term vision; authority expands only through a separate case, scoped credentials, independent checks, stop/takeover and reopening on boundary changes | Connected-strategy tests and actual reader handoffs |
|
||||
| Nested lifecycle and references | Stage01 URL retained as concise lifecycle reference beneath 6 Months Roadmap. All6 topic routes,16 metric contracts and2 shared reference pages remain reachable | No second competing monthly plan. First-revision N/A comparator, clean current-practice recovery, qualification-versus-pilot distinction retained. Contract bodies remain byte-identical;9 prototype calculations and7 unimplemented metrics remain explicitly classified |30-route manifest with original metric hashes;44-doc resolved sidebar/link/anchor checks |
|
||||
| Presentation integration | Published PR40 merge `432370473d6aaee229b0279551ce7b63da52acb7` merged into isolated branch, including320px toolbar correction |19slides,35-minute content +15-minute Q&A unchanged. Focused source-link and Beyond wording changes only; references now name all five horizons. Homepage and toolbar Strategy still open long-term Target | Generated slide-source map, exact source hashes and presentation browser suite; inspect changed slides16/19 individually |
|
||||
|
||||
No Organization body, runtime vendor or dependency changes are introduced relative to integrated PR40 main. Independent child reviewer owns merge/publication and durable wiki reconciliation. Local candidate evidence is not publication evidence.
|
||||
|
||||
## Verification environment and limits
|
||||
|
||||
Use the prefix-correct static server for full acceptance. Docusaurus `serve` on the installed Node runtime redirects WOFF2 assets to slash-suffixed paths; the regular static server serves the same built font bytes correctly. Chromium executable is selected explicitly from the installed headless build. This is desktop/mobile viewport verification, not Safari/Firefox or physical-device certification. WebM remains unsupported/disabled in this browser; SVG/PNG/JPEG/WebP controls are verified. Existing dependency audit findings are not remediated or accepted by this content change.
|
||||
@@ -0,0 +1,162 @@
|
||||
{
|
||||
"sourceCommit": "b9c2047c614dd4e825fa746815104d35d9500739",
|
||||
"sourcePath": "docs/strategy/reference/measurement-contracts.mdx",
|
||||
"metrics": [
|
||||
{
|
||||
"oldAnchor": "validated-task-success",
|
||||
"title": "Validated task success",
|
||||
"docId": "measurement/validated-task-success",
|
||||
"url": "/strategy/measurement/validated-task-success/",
|
||||
"calculationId": "validated-task-success",
|
||||
"status": "prototype",
|
||||
"contractSha256": "925100f4c84f43e2cfdca4a89d6b4a984c808dae2d2ec5e57202318f70b9c544"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "skill-selection-precision",
|
||||
"title": "Skill selection precision",
|
||||
"docId": "measurement/skill-selection-precision",
|
||||
"url": "/strategy/measurement/skill-selection-precision/",
|
||||
"calculationId": "selection-precision",
|
||||
"status": "prototype",
|
||||
"contractSha256": "189e93e4e5f52a7e70e2045c6b824a9da621382f39ba8ce9a59c0c04812f0ce3"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "skill-selection-recall",
|
||||
"title": "Skill selection recall",
|
||||
"docId": "measurement/skill-selection-recall",
|
||||
"url": "/strategy/measurement/skill-selection-recall/",
|
||||
"calculationId": "selection-recall",
|
||||
"status": "prototype",
|
||||
"contractSha256": "847b5ba6094585eb88b8eb2b55b42e0f3c6822dcaa1629256ad0501a13eb7f18"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "supported-bundle-coverage",
|
||||
"title": "Supported bundle coverage",
|
||||
"docId": "measurement/supported-bundle-coverage",
|
||||
"url": "/strategy/measurement/supported-bundle-coverage/",
|
||||
"calculationId": "supported-bundle-coverage",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "8b4dc2dbdfb6999fac283814f518645d0830d515125910d79dd7dc8763f0521c"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "approved-workflow-adoption",
|
||||
"title": "Approved-workflow adoption",
|
||||
"docId": "measurement/approved-workflow-adoption",
|
||||
"url": "/strategy/measurement/approved-workflow-adoption/",
|
||||
"calculationId": "useful-adoption",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "355996d5adb603021ba22f9e1f7f08f2fbea017dac9ee0a4bd42cc00bf7adea3"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "change-lead-time",
|
||||
"title": "Change lead time",
|
||||
"docId": "measurement/change-lead-time",
|
||||
"url": "/strategy/measurement/change-lead-time/",
|
||||
"calculationId": "change-lead-time",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "96fd0edd5eba139a7c5905b606bcc96e608c5294acd2ef0c962fdb7d339d8251"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "deployment-frequency",
|
||||
"title": "Deployment frequency",
|
||||
"docId": "measurement/deployment-frequency",
|
||||
"url": "/strategy/measurement/deployment-frequency/",
|
||||
"calculationId": "deployment-frequency",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "5a34ba52e5c2768e29a1a7574274e07a65509f75063e89ccc7ce1b035aeff4c5"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "change-fail-rate",
|
||||
"title": "Change fail rate",
|
||||
"docId": "measurement/change-fail-rate",
|
||||
"url": "/strategy/measurement/change-fail-rate/",
|
||||
"calculationId": "change-fail-rate",
|
||||
"status": "prototype",
|
||||
"contractSha256": "d2a4ecaddd468f42db5824f9bfab8a8c8fcdf9157b33b4e4f047269a83c8567b"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "failed-deployment-recovery-time",
|
||||
"title": "Failed deployment recovery time",
|
||||
"docId": "measurement/failed-deployment-recovery-time",
|
||||
"url": "/strategy/measurement/failed-deployment-recovery-time/",
|
||||
"calculationId": "failed-deployment-recovery-time",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "489fd756883d4ccee1769fcfaa0b67725420463df2b1f6faf3e7faa7002f7a80"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "deployment-rework-rate",
|
||||
"title": "Deployment rework rate",
|
||||
"docId": "measurement/deployment-rework-rate",
|
||||
"url": "/strategy/measurement/deployment-rework-rate/",
|
||||
"calculationId": "deployment-rework-rate",
|
||||
"status": "prototype",
|
||||
"contractSha256": "e8ade457136feac3ad39e9eba2a9d67142bc605727d9f4f038a7df6d5a0707fd"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "changes-with-escaped-quality-issues",
|
||||
"title": "Changes with escaped quality issues",
|
||||
"docId": "measurement/changes-with-escaped-quality-issues",
|
||||
"url": "/strategy/measurement/changes-with-escaped-quality-issues/",
|
||||
"calculationId": "escaped-quality-rate",
|
||||
"status": "prototype",
|
||||
"contractSha256": "c436d504c8b3a9f655de18b2ca00fa8a0ab47ea1cf37637ff21561f81ecc77c9"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "confirmed-policy-effects",
|
||||
"title": "Confirmed policy effects",
|
||||
"docId": "measurement/confirmed-policy-effects",
|
||||
"url": "/strategy/measurement/confirmed-policy-effects/",
|
||||
"calculationId": "policy-effects",
|
||||
"status": "prototype",
|
||||
"contractSha256": "b64c02f5516b08421fa8b816f0f490571afd05baf5ad6e9d92cb6a7b711ac82a"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "cost-per-accepted-outcome",
|
||||
"title": "Cost per accepted outcome",
|
||||
"docId": "measurement/cost-per-accepted-outcome",
|
||||
"url": "/strategy/measurement/cost-per-accepted-outcome/",
|
||||
"calculationId": "cost-per-accepted-outcome",
|
||||
"status": "prototype",
|
||||
"contractSha256": "d8865ec31315d3c8398ec58cdb6665cb506a7d6309ebec3da0ca7dea84a5f406"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "verification-confidence-and-cognitive-load",
|
||||
"title": "Verification confidence and cognitive load",
|
||||
"docId": "measurement/verification-confidence-and-cognitive-load",
|
||||
"url": "/strategy/measurement/verification-confidence-and-cognitive-load/",
|
||||
"calculationId": "human-experience",
|
||||
"status": "prototype",
|
||||
"contractSha256": "01e017471004c5f780fd0c2671a4d4449d392956cb4c5f0bd7791959d6a9af9a"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "skills-within-substantive-review-window",
|
||||
"title": "Skills within substantive review window",
|
||||
"docId": "measurement/skills-within-substantive-review-window",
|
||||
"url": "/strategy/measurement/skills-within-substantive-review-window/",
|
||||
"calculationId": "maintenance-health",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "339fe0da6b382a34c52b5ec6005ce08a7293a2b07ccd88540a6df03a02d96ad4"
|
||||
},
|
||||
{
|
||||
"oldAnchor": "workflow-specific-business-acceptance",
|
||||
"title": "Workflow-specific business acceptance",
|
||||
"docId": "measurement/workflow-specific-business-acceptance",
|
||||
"url": "/strategy/measurement/workflow-specific-business-acceptance/",
|
||||
"calculationId": "department-outcome",
|
||||
"status": "unimplemented",
|
||||
"contractSha256": "55fce8843409a1bc1383fef3cee5b9a616b44fa8d45ba84c6e4ed490a25f2de4"
|
||||
}
|
||||
],
|
||||
"shared": [
|
||||
{
|
||||
"slug": "collection-and-safeguards",
|
||||
"sha256": "37709cf9978a698026492b29f2095996c462e098a74f082a6b3c3a3a7b38ecab",
|
||||
"previousSha256": "8610ed8df6a24cf138f9e6e2c09060db2aab4c0b1259ca0168e581e3fb964e52",
|
||||
"revisionNote": "Stage 01 separation: baseline establishment moved to baseline.mdx; DORA candidates are optional. Event/privacy and outcome safeguards retained."
|
||||
},
|
||||
{
|
||||
"slug": "synthetic-example",
|
||||
"sha256": "24af68ff4fd61159d1c0557ed0f8f8462470d56c6c83816eb93b47fb04149fde"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,337 @@
|
||||
{
|
||||
"purpose": "Route-level editorial and verification contract for connected Strategy; no deployed-result claims",
|
||||
"routes": [
|
||||
{
|
||||
"source": "docs/strategy/baseline.mdx",
|
||||
"route": "/strategy/baseline/",
|
||||
"question": "What is the actual starting position of this workflow?",
|
||||
"inputs": "Current-practice map, desired improvement and candidate contracts",
|
||||
"action_or_decision": "Select feasible relevant evidence; confirm eligibility and gaps",
|
||||
"output": "Traceable comparison record, not approval",
|
||||
"next_or_feedback": "/strategy/skills-governance/",
|
||||
"review": "Illustrative Delivery evidence handoff and return paths"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/approved-workflow-adoption.mdx",
|
||||
"route": "/strategy/measurement/approved-workflow-adoption/",
|
||||
"question": "Is the enrolled cohort using approved revisions in eligible work?",
|
||||
"inputs": "skill.used; cohort.snapshot; optional qualified client adapter or declaration",
|
||||
"action_or_decision": "Apply only if selected; preserve Consented or otherwise lawfully enrolled pilot cohort for the period; supported workflow available.",
|
||||
"output": "percent; Show observed lower bound and telemetry/response coverage; missing usage unknown rather than non-use.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "355996d5adb603021ba22f9e1f7f08f2fbea017dac9ee0a4bd42cc00bf7adea3",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/change-fail-rate.mdx",
|
||||
"route": "/strategy/measurement/change-fail-rate/",
|
||||
"question": "How often do production deployments require immediate intervention?",
|
||||
"inputs": "deployment.completed; deployment.failed; incident.linked; release and incident records",
|
||||
"action_or_decision": "Apply only if selected; preserve Deployments with production effect during window and approved intervention follow-up horizon elapsed.",
|
||||
"output": "percent; Known failures / all eligible deployments is a lower bound where incident linkage incomplete; label provisional and report unknown links.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "d2a4ecaddd468f42db5824f9bfab8a8c8fcdf9157b33b4e4f047269a83c8567b",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/change-lead-time.mdx",
|
||||
"route": "/strategy/measurement/change-lead-time/",
|
||||
"question": "How long does a service change take from commit to production?",
|
||||
"inputs": "change.committed; deployment.completed; VCS immutable commit timestamps and release manifest",
|
||||
"action_or_decision": "Apply only if selected; preserve Changes first successfully deployed to a service in reporting window; rollout retries collapse to same logical deployment.",
|
||||
"output": "mean; Missing commit mapping or negative/skewed duration excluded from numeric sample, reported explicitly; no zero substitution.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "96fd0edd5eba139a7c5905b606bcc96e608c5294acd2ef0c962fdb7d339d8251",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/changes-with-escaped-quality-issues.mdx",
|
||||
"route": "/strategy/measurement/changes-with-escaped-quality-issues/",
|
||||
"question": "Which accepted changes have confirmed downstream defects?",
|
||||
"inputs": "change.accepted; defect.confirmed; defect tracking and acceptance evidence",
|
||||
"action_or_decision": "Apply only if selected; preserve Accepted changes in acceptance window whose follow-up is complete by as_of.",
|
||||
"output": "percent; Unknown linkage is a coverage warning; no fabricated clean outcome. Show absolute defect and severe incident counts as well.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "c436d504c8b3a9f655de18b2ca00fa8a0ab47ea1cf37637ff21561f81ecc77c9",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/collection-and-safeguards.mdx",
|
||||
"route": "/strategy/measurement/collection-and-safeguards/",
|
||||
"question": "How can I collect and interpret selected evidence safely?",
|
||||
"inputs": "Selected contracts, source inventory and approved collection purpose",
|
||||
"action_or_decision": "Agree populations, deduplication, permissions and retention before collection",
|
||||
"output": "Traceable lawful collection and interpretation contract",
|
||||
"next_or_feedback": "/strategy/baseline/",
|
||||
"review": "Linked to full journey; obsolete roadmap-gates link replaced only in safeguards; preserved arithmetic/privacy substance"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/confirmed-policy-effects.mdx",
|
||||
"route": "/strategy/measurement/confirmed-policy-effects/",
|
||||
"question": "Did eligible attempts produce prohibited effects?",
|
||||
"inputs": "attempt.started; policy.violation; gate.blocked; security audit and incident triage",
|
||||
"action_or_decision": "Apply only if selected; preserve Governed skill trials or supported workflow attempts, reported separately for eval and live populations.",
|
||||
"output": "percent; Unknown outcomes remain visible; zero detected effects never proves safety. Missing audits make rate provisional.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "b64c02f5516b08421fa8b816f0f490571afd05baf5ad6e9d92cb6a7b711ac82a",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/cost-per-accepted-outcome.mdx",
|
||||
"route": "/strategy/measurement/cost-per-accepted-outcome/",
|
||||
"question": "What recorded total or partial cost supports each accepted outcome?",
|
||||
"inputs": "cost.recorded; task.accepted; finance invoices, usage ledger, sampled effort with approved rates",
|
||||
"action_or_decision": "Apply only if selected; preserve Matured eligible started-task cohort, with all attempt costs through as_of and allocated shared period costs.",
|
||||
"output": "ratio; Missing cost buckets produce partial estimate plus coverage, not a total. Mixed currency requires dated approved conversion; zero accepted outcomes = null with full cost shown.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "d8865ec31315d3c8398ec58cdb6665cb506a7d6309ebec3da0ca7dea84a5f406",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/deployment-frequency.mdx",
|
||||
"route": "/strategy/measurement/deployment-frequency/",
|
||||
"question": "How frequently does this service deploy successfully?",
|
||||
"inputs": "deployment.completed; authoritative deployment service",
|
||||
"action_or_decision": "Apply only if selected; preserve Declared production services and complete UTC observation days; report each service before pooled views.",
|
||||
"output": "ratio; Missing feed periods not zero; report coverage and no unqualified overall rate when period incomplete.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "5a34ba52e5c2768e29a1a7574274e07a65509f75063e89ccc7ce1b035aeff4c5",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/deployment-rework-rate.mdx",
|
||||
"route": "/strategy/measurement/deployment-rework-rate/",
|
||||
"question": "How much production deployment activity is corrective?",
|
||||
"inputs": "deployment.completed; incident.linked; release intent classification",
|
||||
"action_or_decision": "Apply only if selected; preserve Production deployment effects in window with immutable planned/unplanned classification and incident linkage.",
|
||||
"output": "percent; Unknown classification stays denominator; observed numerator is lower bound until reconciliation; show classification coverage.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "e8ade457136feac3ad39e9eba2a9d67142bc605727d9f4f038a7df6d5a0707fd",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/failed-deployment-recovery-time.mdx",
|
||||
"route": "/strategy/measurement/failed-deployment-recovery-time/",
|
||||
"question": "How long did recovered deployment failures take to restore?",
|
||||
"inputs": "deployment.failed; service.restored; incident service",
|
||||
"action_or_decision": "Apply only if selected; preserve Production deployment failures beginning in window; latest verified restoration if a recovery is rescinded.",
|
||||
"output": "mean; Unresolved failures reported separately and excluded only from recovered-duration distribution; prevent declaring improvement without their visibility.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "489fd756883d4ccee1769fcfaa0b67725420463df2b1f6faf3e7faa7002f7a80",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/index.mdx",
|
||||
"route": "/strategy/measurement/",
|
||||
"question": "Which evidence can support this workflow decision?",
|
||||
"inputs": "Workflow question and available populations",
|
||||
"action_or_decision": "Choose applicable contracts and connect fitness to Quality",
|
||||
"output": "Selected definitions and limits, never mandatory full collection",
|
||||
"next_or_feedback": "/strategy/baseline/",
|
||||
"review": "Two tracks retained; fitness not reduced to health proxies"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/skill-selection-precision.mdx",
|
||||
"route": "/strategy/measurement/skill-selection-precision/",
|
||||
"question": "Were selected skills relevant to the labeled cases?",
|
||||
"inputs": "eval.selection; versioned labeled corpus and runner",
|
||||
"action_or_decision": "Apply only if selected; preserve All candidate/client labeled evaluation task-trials with known activation and relevance.",
|
||||
"output": "percent; Unknown activation/relevance is unscorable; publish missing count and deny qualification if planned coverage incomplete.",
|
||||
"next_or_feedback": "/strategy/skills-quality/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "189e93e4e5f52a7e70e2045c6b824a9da621382f39ba8ce9a59c0c04812f0ce3",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/skill-selection-recall.mdx",
|
||||
"route": "/strategy/measurement/skill-selection-recall/",
|
||||
"question": "Were expected skills found in relevant labeled cases?",
|
||||
"inputs": "eval.selection; versioned labeled corpus and runner",
|
||||
"action_or_decision": "Apply only if selected; preserve Independently labeled relevant evaluation task-trials for a skill/client tuple.",
|
||||
"output": "percent; Report evaluation coverage; null if no relevant labeled tasks.",
|
||||
"next_or_feedback": "/strategy/skills-quality/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "847b5ba6094585eb88b8eb2b55b42e0f3c6822dcaa1629256ad0501a13eb7f18",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/skills-within-substantive-review-window.mdx",
|
||||
"route": "/strategy/measurement/skills-within-substantive-review-window/",
|
||||
"question": "Which approved revisions have current ownership and substantive review?",
|
||||
"inputs": "catalog.published; catalog.reviewed; catalog.deprecated; catalog.revoked; version inventory",
|
||||
"action_or_decision": "Apply only if selected; preserve Approved revisions currently supported for use at as_of.",
|
||||
"output": "percent; Missing owner/date/evidence outside numerator; show ownerless, deprecated-in-use and revoked-in-use absolute counts.",
|
||||
"next_or_feedback": "/strategy/skills-maintenance/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "339fe0da6b382a34c52b5ec6005ce08a7293a2b07ccd88540a6df03a02d96ad4",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/supported-bundle-coverage.mdx",
|
||||
"route": "/strategy/measurement/supported-bundle-coverage/",
|
||||
"question": "Which expected installations have verified supported revisions?",
|
||||
"inputs": "inventory.observed; catalog.published; catalog.revoked; device inventory",
|
||||
"action_or_decision": "Apply only if selected; preserve Active installation inventory frozen for report, including invisible/offline entries until authoritative offboarding.",
|
||||
"output": "percent; Unknown/stale versions count outside numerator, inside denominator. Show inventory discovery coverage versus eligible device roster; if roster unknown metric is provisional.",
|
||||
"next_or_feedback": "/strategy/skills-maintenance/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "8b4dc2dbdfb6999fac283814f518645d0830d515125910d79dd7dc8763f0521c",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/synthetic-example.mdx",
|
||||
"route": "/strategy/measurement/synthetic-example/",
|
||||
"question": "How can I reproduce the arithmetic without claiming real results?",
|
||||
"inputs": "Labeled synthetic fixture",
|
||||
"action_or_decision": "Run the prototype and verify missingness",
|
||||
"output": "Synthetic calculations with omissions, not baseline values",
|
||||
"next_or_feedback": "/strategy/baseline/",
|
||||
"review": "Linked to full journey; obsolete roadmap-gates link replaced only in safeguards; preserved arithmetic/privacy substance"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/validated-task-success.mdx",
|
||||
"route": "/strategy/measurement/validated-task-success/",
|
||||
"question": "Which matured workflow starts reached independent acceptance?",
|
||||
"inputs": "task.started; task.accepted; task.failed; task.abandoned; task.cancelled; work-management acceptance record",
|
||||
"action_or_decision": "Apply only if selected; preserve Tasks in a preregistered workflow cohort, started in window; each counted once across retries, skills and clients.",
|
||||
"output": "percent; Unresolved/missing terminal outcomes remain in denominator with unknown count and known-outcome coverage; do not label them failed. Invalid/missing start excluded from calculation but flagged as orphan evidence.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "925100f4c84f43e2cfdca4a89d6b4a984c808dae2d2ec5e57202318f70b9c544",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/verification-confidence-and-cognitive-load.mdx",
|
||||
"route": "/strategy/measurement/verification-confidence-and-cognitive-load/",
|
||||
"question": "Can the cohort confidently verify work without excessive perceived load?",
|
||||
"inputs": "survey.response; anonymous survey with single-use token and aggregate invitation count",
|
||||
"action_or_decision": "Apply only if selected; preserve Invited eligible cohort at fixed survey wave; voluntary responses.",
|
||||
"output": "mean; Report valid response count / invited count and item nonresponse; no imputation. Suppress people cohorts below five.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "01e017471004c5f780fd0c2671a4d4449d392956cb4c5f0bd7791959d6a9af9a",
|
||||
"implementation": "prototype"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/measurement/workflow-specific-business-acceptance.mdx",
|
||||
"route": "/strategy/measurement/workflow-specific-business-acceptance/",
|
||||
"question": "Did a named workflow meet its departmental acceptance rubric?",
|
||||
"inputs": "task.started; business.accepted; departmental case/content/reconciliation/onboarding review record",
|
||||
"action_or_decision": "Apply only if selected; preserve One named departmental workflow and predeclared start cohort; never pool unlike rubrics.",
|
||||
"output": "percent; Unknown follow-up stays denominator with unresolved count; no claim actual business outcome changed without source evidence.",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Canonical contract and URL preserved; populations, exclusions, missingness and crosslinks reviewed",
|
||||
"contract_sha256": "55fce8843409a1bc1383fef3cee5b9a616b44fa8d45ba84c6e4ed490a25f2de4",
|
||||
"implementation": "unimplemented"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/roadmap.mdx",
|
||||
"route": "/strategy/roadmap/",
|
||||
"question": "How do practices and skills progress toward controlled autonomous capabilities?",
|
||||
"inputs": "Long-term Target and evidence from actual work",
|
||||
"action_or_decision": "Delivery first; later phase order undecided; separate authority decision",
|
||||
"output": "Broad progression with no fixed dates",
|
||||
"next_or_feedback": "/strategy/six-months-target/",
|
||||
"review": "Historical three-level roadmap restored, distinct from monthly plan"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/skills-adoption.mdx",
|
||||
"route": "/strategy/skills-adoption/",
|
||||
"question": "Should a qualified skill become a retained workflow?",
|
||||
"inputs": "Baseline, qualification and explicit bounded-pilot authorization",
|
||||
"action_or_decision": "Run comparable real work; owner decides retain/improve/expand/stop",
|
||||
"output": "Decision record; retained revision requires exact-scope approval",
|
||||
"next_or_feedback": "/strategy/skills-maintenance/",
|
||||
"review": "Manual path and feedback to author/Quality/Baseline"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/skills-governance.mdx",
|
||||
"route": "/strategy/skills-governance/",
|
||||
"question": "Who may authorize which revision for which use?",
|
||||
"inputs": "Workflow map, candidate topology and risk boundary",
|
||||
"action_or_decision": "Name people, independent reviewers and staged permissions",
|
||||
"output": "Pinned candidate, bounded-pilot authorization then exact-scope approval",
|
||||
"next_or_feedback": "/strategy/skills-quality/",
|
||||
"review": "Reconciled disposable qualification, authorized pilot and wider use"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/skills-maintenance.mdx",
|
||||
"route": "/strategy/skills-maintenance/",
|
||||
"question": "How do retained skills remain useful and safe?",
|
||||
"inputs": "Approved manifest, outcomes, failures and client/model drift",
|
||||
"action_or_decision": "Continue authorized use, requalify, contain or retire",
|
||||
"output": "Support/recovery evidence, regression cases or migration record",
|
||||
"next_or_feedback": "/strategy/skills-quality/",
|
||||
"review": "Fitness/regression beyond metadata health; no automatic autonomy"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/skills-quality.mdx",
|
||||
"route": "/strategy/skills-quality/",
|
||||
"question": "Is the named candidate fit and non-regressing?",
|
||||
"inputs": "Pinned revision/client, declared cases and acceptance rules",
|
||||
"action_or_decision": "Independent fitness/safety/regression evaluation; recommend pilot or hold",
|
||||
"output": "Versioned qualification report with failures and limits",
|
||||
"next_or_feedback": "/strategy/skills-adoption/",
|
||||
"review": "Separates artifact trial population from matured live tasks"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/stage-01-skills-adoption.mdx",
|
||||
"route": "/strategy/stage-01-skills-adoption/",
|
||||
"question": "How do reusable lifecycle activities hand off evidence?",
|
||||
"inputs": "Workflow problem, people and current evidence",
|
||||
"action_or_decision": "Baseline, qualify, authorize pilot, compare and maintain; link canonical EXP-01 in six-month roadmap",
|
||||
"output": "Lifecycle reference and feedback paths, not a competing plan",
|
||||
"next_or_feedback": "/strategy/baseline/",
|
||||
"review": "New native dependency story plus evidence handoffs"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/stage-02-autonomous-agent.mdx",
|
||||
"route": "/strategy/stage-02-autonomous-agent/",
|
||||
"question": "Is additional autonomous authority justified and recoverable?",
|
||||
"inputs": "Proven Stage01 practices, limits and explicit operation proposal",
|
||||
"action_or_decision": "Existing designated functions assess scope, enforcement and takeover",
|
||||
"output": "Recorded hold or conditional bounded authority",
|
||||
"next_or_feedback": "/strategy/stage-01-skills-adoption/",
|
||||
"review": "New authority boundary diagram and return-to-Stage01 path"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/target-operating-model.mdx",
|
||||
"route": "/strategy/target-operating-model/",
|
||||
"question": "What is the long-term human-controlled autonomous SDLC destination?",
|
||||
"inputs": "Original agreed topology and human direction",
|
||||
"action_or_decision": "Preserve ambition with independent controls and no present authority",
|
||||
"output": "Long-term operating model, not six-month promise",
|
||||
"next_or_feedback": "/strategy/roadmap/",
|
||||
"review": "Original topology restored from pre-PR38; safeguards retained"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/six-months-target.mdx",
|
||||
"route": "/strategy/six-months-target/",
|
||||
"question": "What six-month strategy answers the AI Architect assignment?",
|
||||
"inputs": "Full PDF facts; explicitly unknown stack, processes and capacity",
|
||||
"action_or_decision": "Improve current AI-assisted engineering output with the smallest suitable intervention",
|
||||
"output": "Realistic month-six scenario, assumptions register and 35+15-minute presentation narrative",
|
||||
"next_or_feedback": "/strategy/six-months-roadmap/",
|
||||
"review": "PDF assignment retained independently of long-term destination; EXP-01 lives in six-month action plan"
|
||||
},
|
||||
{
|
||||
"source": "docs/strategy/six-months-roadmap.mdx",
|
||||
"route": "/strategy/six-months-roadmap/",
|
||||
"question": "What does a solo architect do month by month without team authority?",
|
||||
"inputs": "PDF constraints, current AI practice, willing partners and unknown capacity",
|
||||
"action_or_decision": "Month 1–6 discovery, bounded experiment, compare, selective transfer and CTO investment decision",
|
||||
"output": "Proposed six-month plan with dependencies, evidence, capacity and stop choices",
|
||||
"next_or_feedback": "/strategy/stage-02-autonomous-agent/",
|
||||
"review": "PDF assignment retained independently of long-term destination; EXP-01 lives in six-month action plan"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0.0",
|
||||
"status": "proposed-target-not-approved-or-deployed",
|
||||
"scope": "Strategy documentation and synthetic measurement reference only; no runtime changes authorized.",
|
||||
"scope": "Long-term human-controlled autonomous SDLC Target and broad Roadmap, with distinct six-month contribution and action plan plus Beyond bridge. Full30-route reading contract is strategy-coverage.json. Organization model is not PDF evidence; no runtime changes authorized.",
|
||||
"organization": {
|
||||
"Product": [
|
||||
"Product Management",
|
||||
@@ -28,15 +28,10 @@
|
||||
]
|
||||
},
|
||||
"pages": [
|
||||
{
|
||||
"id": "index",
|
||||
"title": "AI adoption strategy",
|
||||
"purpose": "Govern skills first; outcomes before activity; explicit target status."
|
||||
},
|
||||
{
|
||||
"id": "target-operating-model",
|
||||
"title": "Target operating model",
|
||||
"purpose": "One logical coordinator; local client choice; independent authority; all departments."
|
||||
"title": "Target",
|
||||
"purpose": "Long-term human-directed, guided and reviewed autonomous SDLC destination; original topology and supporting controls, not six-month promise or present authority."
|
||||
},
|
||||
{
|
||||
"id": "skills-governance",
|
||||
@@ -55,8 +50,8 @@
|
||||
},
|
||||
{
|
||||
"id": "measurement",
|
||||
"title": "Measurement",
|
||||
"purpose": "Full KPI contracts, minimal events, illustrative calculations, privacy and limits."
|
||||
"title": "Measuring real output",
|
||||
"purpose": "Small feasible starting measures and optional sixteen-contract registry, not mandatory collection."
|
||||
},
|
||||
{
|
||||
"id": "skills-maintenance",
|
||||
@@ -66,7 +61,7 @@
|
||||
{
|
||||
"id": "roadmap",
|
||||
"title": "Roadmap",
|
||||
"purpose": "Evidence-gated phases, no promised dates or budgets."
|
||||
"purpose": "Broad progression from skills/practices adoption to controlled autonomous capabilities: Delivery first, later phase order undecided, evidence and separate human decisions without fixed timing."
|
||||
}
|
||||
],
|
||||
"diagram": {
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"sourceCommit": "88a43757762114a506f57ed4b44484306cae1aaa",
|
||||
"departments": [
|
||||
{
|
||||
"label": "Product",
|
||||
"slug": "product",
|
||||
"bodySha256": "b7fd948091dbd7b7c2f51d494a5e83241a53c5d1d9b751267102a6c97ad29bd9",
|
||||
"rows": 2
|
||||
},
|
||||
{
|
||||
"label": "Technology",
|
||||
"slug": "technology",
|
||||
"bodySha256": "a74405d41a58b43e4e8ffbb0e98f835d25d80c6ab2ef9f314925832280c038d3",
|
||||
"rows": 5
|
||||
},
|
||||
{
|
||||
"label": "Operations",
|
||||
"slug": "operations",
|
||||
"bodySha256": "03254f56a3ea8e353a5d9b65c0342954bf65edec59073d20fb1ceaaf31d683c7",
|
||||
"rows": 4
|
||||
},
|
||||
{
|
||||
"label": "Marketing",
|
||||
"slug": "marketing",
|
||||
"bodySha256": "424d7c1d147472ced3b73eb8041048a982ce10330a51246ca35bed0cd150e633",
|
||||
"rows": 6
|
||||
},
|
||||
{
|
||||
"label": "Finance & Accounting",
|
||||
"slug": "finance-accounting",
|
||||
"bodySha256": "ffdacb9930114a6caf25a475bb207dcb58f27c13e08fb04e098ef1e30ea538a9",
|
||||
"rows": 3
|
||||
},
|
||||
{
|
||||
"label": "HR & Administration",
|
||||
"slug": "hr-administration",
|
||||
"bodySha256": "e663ca1c7b7fe83cff70d6e33235591fa082304d201dc4538235cc1a341ffd3c",
|
||||
"rows": 3
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,61 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import {readFileSync} from 'node:fs';
|
||||
import {targetCaption} from './target-caption.mjs';
|
||||
const read = p => readFileSync(p,'utf8');
|
||||
const matrix = JSON.parse(read('research/ai-adoption/assignment-evidence.json'));
|
||||
test('PDF assignment and audit matrix map to actual page evidence',()=>{
|
||||
assert.deepEqual(matrix.requirements.map(r=>r.id),['format','context','q1','q2','q3','q4','assumptions','F1','F2-F3']);
|
||||
for(const row of matrix.requirements){
|
||||
const text=row.pages.map(p=>read(`docs/strategy/${p}.mdx`)).join('\n').toLowerCase();
|
||||
for(const marker of row.markers) assert(text.includes(marker.toLowerCase()),`${row.id}: ${marker}`);
|
||||
}
|
||||
for(const p of matrix.verification_sources)assert(read(p));
|
||||
assert.equal(35+15,50);
|
||||
});
|
||||
test('six-month reading path does not promise skills rollout or autonomous delivery',()=>{
|
||||
const main=read('docs/strategy/six-months-target.mdx').split('<details>')[0];
|
||||
assert(main.indexOf('strategy-six-months')<main.indexOf('Choose the smallest intervention'));
|
||||
for(const stale of ['The first investment is a governed skills system','An autonomous agent executes and governs every phase','foundation for Stage 2'])assert(!main.includes(stale));
|
||||
const roadmap=read('docs/strategy/six-months-roadmap.mdx');
|
||||
for(const month of [1,2,3,4,5,6]){
|
||||
const block=roadmap.split(`**Month ${month} — `)[1].split('\n\n')[0];
|
||||
for(const word of ['Output:','Dependency:'])assert(block.includes(word),`${month}: ${word}`);
|
||||
}
|
||||
});
|
||||
test('proposed diagram preserves months and explicit mobile feedback legend',()=>{
|
||||
const pair=['','-mobile'].map(s=>JSON.parse(read(`diagrams/strategy-six-months${s}.architecture.json`)));
|
||||
const nodes=d=>d.components.map(({pos,size,...n})=>n);
|
||||
assert.deepEqual(nodes(pair[0]),nodes(pair[1]));
|
||||
for(const d of pair){
|
||||
for(let m=1;m<=6;m++)assert(d.components.some(n=>n.label.startsWith(`Month ${m}:`)));
|
||||
const legend=d.components.find(n=>n.id==='reference');
|
||||
assert(legend.sublabel.includes('Month 6 → 2:'));assert(legend.sublabel.includes('Month 5 → 1:'));
|
||||
assert(legend.sublabel.includes('not company commitments'));
|
||||
}
|
||||
});
|
||||
test('first-revision recovery and diagram decisions cannot disappear',()=>{
|
||||
for(const id of ['skills-quality','skills-governance','skills-maintenance']){
|
||||
const text=read(`docs/strategy/${id}.mdx`);
|
||||
for(const term of ['N/A','pinned clean','current'])assert(text.includes(term),id);
|
||||
}
|
||||
for(const s of ['','-mobile']){
|
||||
const g=JSON.parse(read(`diagrams/strategy-governance${s}.architecture.json`));
|
||||
assert(g.components.find(n=>n.id==='canary').sublabel.includes('pilot'));
|
||||
assert(g.components.find(n=>n.id==='approve').sublabel.includes('approve / hold'));
|
||||
const a=JSON.parse(read(`diagrams/strategy-adoption${s}.architecture.json`));
|
||||
assert(a.components.find(n=>n.id==='expand').sublabel.includes('Retain / improve / hold / stop'));
|
||||
}
|
||||
const mobile=JSON.parse(read('diagrams/strategy-maintenance-mobile.architecture.json'));
|
||||
const order=[...mobile.components].sort((a,b)=>a.pos[1]-b.pos[1]).map(n=>n.id);
|
||||
assert.deepEqual(order.slice(0,2),['observe','triage']);
|
||||
});
|
||||
test('target caption is inside SVG, expands canvas and fails closed',()=>{
|
||||
const svg='<svg role="img" viewBox="0 0 1200 1000"><g data-node-id="agent"/></svg>';
|
||||
const out=targetCaption(svg);
|
||||
for(const term of ['Long-term Target','Solid: lifecycle','Dotted: execution','Dashed: human-controlled'])assert(out.includes(term));
|
||||
assert(out.includes('viewBox="0 0 1200 1130"'));
|
||||
assert(out.indexOf('eldorado-target-caption')<out.indexOf('</svg>'));
|
||||
assert.equal((out.match(/data-node-id=/g)||[]).length,1);
|
||||
assert.throws(()=>targetCaption('<svg/>'));
|
||||
});
|
||||
@@ -0,0 +1,34 @@
|
||||
import test from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import {readFileSync} from 'node:fs';
|
||||
const read = path => readFileSync(path, 'utf8');
|
||||
|
||||
test('Baseline is workflow-scoped, evidence-bound and distinct from the optional registry', () => {
|
||||
const page = read('docs/strategy/baseline.mdx');
|
||||
for (const heading of ['Understand the current workflow','Select relevant metrics, with reasons','Agree feasible evidence','Record the starting position','Keep later evaluation comparable']) assert(page.includes(`## ${heading}`));
|
||||
for (const text of ['not a mandatory company-wide baseline','no actual baseline values or approved thresholds','lawful basis','privacy','retention','source coverage','**Available:**','**Unavailable:**','not causal ROI','selected-but-unavailable']) assert(page.includes(text), text);
|
||||
assert(page.indexOf('<ArchifyDiagram') < page.indexOf('## Understand'));
|
||||
assert(!page.includes('25%'));
|
||||
for (const doc of ['measurement/index','measurement/collection-and-safeguards','skills-adoption','skills-maintenance','skills-governance']) assert(page.includes(`./${doc}.mdx`));
|
||||
const registry = read('docs/strategy/measurement/index.mdx');
|
||||
assert(registry.includes('pagination_next: baseline'));
|
||||
assert(page.includes('pagination_prev: measurement/index'));
|
||||
assert(page.includes('pagination_next: skills-governance'));
|
||||
});
|
||||
|
||||
test('workflow application has one home and shared safety remains explicit', () => {
|
||||
const registry = read('docs/strategy/measurement/index.mdx');
|
||||
const shared = read('docs/strategy/measurement/collection-and-safeguards.mdx');
|
||||
const adoption = read('docs/strategy/skills-adoption.mdx');
|
||||
const maintenance = read('docs/strategy/skills-maintenance.mdx');
|
||||
assert(!registry.includes('Measure the pilot'));
|
||||
assert(!shared.includes('Track all five'));
|
||||
assert(!shared.includes('Before a pilot, freeze'));
|
||||
assert(shared.includes('id') && shared.includes('{#baseline-and-interpretation}')); // Existing inbound anchor survives relocation.
|
||||
for (const marker of ['transport retries','quarantined','Late arrivals','Unknown version stays null','30 days','12 months','below five people','No raw prompts','Consent is not presumed']) assert(shared.includes(marker),marker);
|
||||
assert(adoption.includes('not a mandatory pilot bundle'));
|
||||
assert(adoption.includes('What a pilot report looks like'));
|
||||
assert(maintenance.includes('Keep selected evidence useful'));
|
||||
assert(maintenance.includes('versioned corrections'));
|
||||
assert(adoption.includes('**Next:** [Maintain skills using the agreed evidence →](./skills-maintenance.mdx)'));
|
||||
});
|
||||
@@ -0,0 +1,8 @@
|
||||
const {chromium}=require('playwright');
|
||||
const fs=require('node:fs');const assert=require('node:assert/strict');
|
||||
(async()=>{
|
||||
const base=process.argv[2]||'http://127.0.0.1:4173';const out=`.cache/journey-${process.argv[3]||'candidate'}`;fs.mkdirSync(out,{recursive:true});
|
||||
const b=await chromium.launch({executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']});const results=[];
|
||||
const steps=[['target-operating-model','roadmap'],['roadmap','six-months-target'],['six-months-target','six-months-roadmap'],['six-months-roadmap','stage-02-autonomous-agent'],['six-months-roadmap','stage-01-skills-adoption'],['stage-01-skills-adoption','baseline'],['baseline','measurement'],['measurement','skills-quality'],['skills-quality','skills-governance'],['skills-governance','skills-quality'],['skills-quality','skills-adoption'],['skills-adoption','skills-maintenance'],['skills-maintenance','skills-quality'],['skills-quality','measurement/validated-task-success'],['measurement/validated-task-success','skills-quality'],['skills-maintenance','stage-02-autonomous-agent'],['stage-02-autonomous-agent','stage-01-skills-adoption']];
|
||||
try{for(const width of [1440,390]){const p=await b.newPage({viewport:{width,height:900}});for(const [from,to]of steps){await p.goto(`${base}/eldorado-v1/documentation/strategy/${from}/`,{waitUntil:'networkidle'});const href=`/eldorado-v1/documentation/strategy/${to}/`;const link=p.locator(`article a[href="${href}"]`).filter({visible:true}).first();assert(await link.count(),`${from} → ${to}`);await link.scrollIntoViewIfNeeded();await p.waitForLoadState('networkidle');await link.click();await p.waitForURL(`${base}${href}`);await p.locator('article h1').waitFor();results.push({width,from,to,clicked:true});fs.writeFileSync(`${out}/results.json`,JSON.stringify(results,null,2))}await p.close()}console.log(`PASS ${results.length} real reader handoffs and feedback links`)}finally{await b.close()}
|
||||
})().catch(e=>{console.error(e);process.exitCode=1});
|
||||
@@ -0,0 +1,49 @@
|
||||
const {chromium}=require('playwright');
|
||||
const assert=require('node:assert/strict');
|
||||
const fs=require('node:fs');
|
||||
(async()=>{
|
||||
const base=process.argv[2]||'http://127.0.0.1:4187';
|
||||
const prefix='/eldorado-v1/documentation/organization/';
|
||||
const departments=JSON.parse(fs.readFileSync('research/organization/department-migration.json')).departments;
|
||||
const ids=['structure',...departments.map(d=>'structure/'+d.slug)];
|
||||
const titles=['Structure',...departments.map(d=>d.label)];
|
||||
const browser=await chromium.launch({headless:true,args:['--no-sandbox'],executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE});
|
||||
const results=[]; fs.mkdirSync('.cache/departments',{recursive:true});
|
||||
try{
|
||||
for(const width of [1440,390]){
|
||||
const page=await browser.newPage({viewport:{width,height:900}}); const errors=[]; page.on('pageerror',e=>errors.push(e.message));
|
||||
for(const [i,id] of ids.entries()){
|
||||
assert.equal((await page.goto(base+prefix+id+'/',{waitUntil:'networkidle'})).status(),200);
|
||||
assert.equal(await page.locator('h1').innerText(),titles[i]);
|
||||
if(i){
|
||||
assert.equal(await page.locator('.breadcrumbs a').filter({hasText:'Structure'}).getAttribute('href'),prefix+'structure/');
|
||||
assert.equal(await page.locator('.pagination-nav__link--prev').getAttribute('href'),prefix+ids[i-1]+'/');
|
||||
await page.getByRole('link',{name:'Return to Structure overview',exact:true}).click();
|
||||
await page.waitForURL(base+prefix+'structure/');
|
||||
await page.locator('article').getByRole('link',{name:titles[i],exact:true}).click();
|
||||
await page.waitForURL(base+prefix+id+'/');
|
||||
}
|
||||
assert.equal(await page.locator('.pagination-nav__link--next').getAttribute('href'),prefix+(ids[i+1]||'collaboration')+'/');
|
||||
assert(!await page.evaluate(()=>document.documentElement.scrollWidth>innerWidth));
|
||||
await page.screenshot({path:`.cache/departments/${width}-${id.replaceAll('/','-')}.png`,fullPage:true});
|
||||
if(width<997)await page.getByRole('button',{name:'Toggle navigation bar'}).click();
|
||||
const menu=page.locator('.theme-doc-sidebar-menu').filter({visible:true});
|
||||
await menu.getByRole('link',{name:'Structure',exact:true}).waitFor({state:'visible'});
|
||||
const category=menu.locator('.theme-doc-sidebar-item-category');
|
||||
await category.getByRole('link',{name:'Product',exact:true}).waitFor({state:'visible'});
|
||||
assert.deepEqual(await category.locator(':scope > ul > li > a').allTextContents(),titles.slice(1));
|
||||
assert.deepEqual(await menu.locator(':scope > li > a').allTextContents(),['Collaboration','SDLC']);
|
||||
const caret=category.locator(':scope > .menu__list-item-collapsible > button');
|
||||
await caret.click(); await category.getByRole('link',{name:'Product',exact:true}).waitFor({state:'hidden'});
|
||||
await caret.click(); await category.getByRole('link',{name:'Product',exact:true}).waitFor({state:'visible'});
|
||||
const next=(i+1)%ids.length;
|
||||
await menu.getByRole('link',{name:titles[next],exact:true}).click(); await page.waitForURL(base+prefix+ids[next]+'/');
|
||||
await page.locator('h1').filter({hasText:titles[next]}).waitFor();
|
||||
results.push({width,id,navigation:true});
|
||||
}
|
||||
assert.deepEqual(errors,[]);await page.close();
|
||||
}
|
||||
fs.writeFileSync('.cache/departments/results.json',JSON.stringify(results,null,2));
|
||||
console.log('PASS: '+results.length+' desktop/mobile department contexts, real sidebar/return/list navigation, breadcrumbs, pagination and overflow');
|
||||
}finally{await browser.close();}
|
||||
})().catch(e=>{console.error(e);process.exit(1)});
|
||||
@@ -0,0 +1,60 @@
|
||||
const {chromium}=require('playwright');
|
||||
const staircaseFits=require('./presentation-staircase.cjs');
|
||||
const assert=require('node:assert/strict');const fs=require('node:fs');
|
||||
(async()=>{
|
||||
const base=process.argv[2]||'http://127.0.0.1:43853';const root=base+'/eldorado-v1/documentation/';
|
||||
const out='.cache/homepage-embed';fs.mkdirSync(out,{recursive:true});
|
||||
const browser=await chromium.launch({headless:true,executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']});const results=[];
|
||||
try{
|
||||
for(const viewport of [{width:1440,height:900},{width:390,height:844},{width:320,height:720},{width:844,height:390}]){
|
||||
const context=await browser.newContext({viewport,hasTouch:true,reducedMotion:'reduce'});const p=await context.newPage();const errors=[];
|
||||
p.on('pageerror',e=>errors.push(e.message));p.on('response',r=>{if(r.status()>=400)errors.push(`${r.status()} ${r.url()}`)});
|
||||
await p.goto(root,{waitUntil:'networkidle'});const section=p.locator('section[aria-labelledby="presentation-title"]');await section.scrollIntoViewIfNeeded();
|
||||
const iframe=p.locator('iframe[title="Less Prompting, More Shipping — interactive presentation"]');const f=await iframe.elementHandle().then(e=>e.contentFrame());await f.waitForFunction(()=>window.Reveal?.isReady());await f.evaluate(()=>document.fonts.ready);
|
||||
assert.deepEqual(await p.locator('#start-title,#presentation-title').evaluateAll(es=>es.map(e=>{const s=getComputedStyle(e);return [s.fontFamily,s.fontSize,s.fontWeight,s.letterSpacing,s.lineHeight]})).then(a=>a[0]),await p.locator('#presentation-title').evaluate(e=>{const s=getComputedStyle(e);return [s.fontFamily,s.fontSize,s.fontWeight,s.letterSpacing,s.lineHeight]}));
|
||||
assert.equal(await f.locator('.toolbar').isVisible(),false);assert.equal(await f.evaluate(()=>Reveal.getConfig().hash),false);assert.equal(await f.evaluate(()=>Reveal.getConfig().transition),'none');assert.equal(await f.evaluate(()=>Reveal.getTotalSlides()),23);
|
||||
assert(await p.evaluate(()=>document.documentElement.scrollWidth<=innerWidth));
|
||||
if(viewport.width<=390)assert(await iframe.evaluate(e=>e.clientHeight>e.clientWidth),'phone stage must recompose rather than shrink landscape text');
|
||||
await p.getByRole('button',{name:'Fullscreen',exact:true}).focus();await p.keyboard.press('ArrowRight');assert.equal(await f.evaluate(()=>Reveal.getIndices().h),0);
|
||||
await f.locator('.controls .navigate-right').click();assert.equal(await f.evaluate(()=>Reveal.getIndices().h),1);
|
||||
const scroll=await p.evaluate(()=>scrollY);await p.keyboard.press('ArrowRight');assert.equal(await f.evaluate(()=>Reveal.getIndices().h),2);assert.equal(await p.evaluate(()=>scrollY),scroll);assert.equal(p.url(),root);
|
||||
await f.evaluate(()=>Reveal.slide(0));
|
||||
const visited=[];
|
||||
for(let i=0;i<23;i++){
|
||||
assert.equal(await f.evaluate(()=>Reveal.getIndices().h),i);visited.push(await f.evaluate(()=>Reveal.getCurrentSlide().id));
|
||||
const bad=await f.evaluate(()=>{const r=Reveal.getCurrentSlide().getBoundingClientRect();return [...Reveal.getCurrentSlide().querySelectorAll('svg,text,.journey,.learning-loop,.contribution-grid,h1,h2,p,li,table,.flow,.roles,.timeline')].filter(e=>!e.closest('.notes')&&e.getBoundingClientRect().width>0).filter(e=>{const b=e.getBoundingClientRect();return b.bottom>r.bottom+1||b.right>r.right+1||b.left<r.left-1}).map(e=>e.textContent)});assert.deepEqual(bad,[]);
|
||||
if(i===6)assert(await f.evaluate(staircaseFits),'staircase aligns each arrow with its intended steps');
|
||||
if(i===4)assert(await f.evaluate(()=>[...document.querySelectorAll('#contributors .contribution-grid>div')].every(e=>{const a=e.querySelector('span').getBoundingClientRect(), arrow=e.querySelector('i').getBoundingClientRect(), b=e.querySelector('b').getBoundingClientRect();return a.bottom<=arrow.top+2&&arrow.bottom<=b.top+2&&Math.abs((a.left+a.right-b.left-b.right)/2)<2&&getComputedStyle(e.querySelector('i')).transform==='matrix(0, 1, -1, 0, 0, 0)'})),'contribution arrows must point down to their own phase');
|
||||
await iframe.screenshot({path:`${out}/${viewport.width}-${i+1}.png`});
|
||||
if(i<22)await p.keyboard.press('ArrowRight');
|
||||
}
|
||||
assert.equal(new Set(visited).size,23);assert.equal(p.url(),root);assert.equal(new URL(f.url()).hash,'');
|
||||
await f.evaluate(()=>Reveal.slide(0));await section.screenshot({path:`${out}/${viewport.width}-light.png`});
|
||||
await p.evaluate(()=>document.documentElement.setAttribute('data-theme','dark'));await section.screenshot({path:`${out}/${viewport.width}-dark.png`});
|
||||
await p.getByRole('button',{name:'Fullscreen',exact:true}).click();await p.waitForFunction(()=>!!document.fullscreenElement);await f.waitForTimeout(100);
|
||||
await p.screenshot({path:`${out}/${viewport.width}-fullscreen.png`});
|
||||
await p.getByRole('button',{name:'Exit fullscreen',exact:true}).click();await p.waitForFunction(()=>!document.fullscreenElement);await p.waitForFunction(()=>document.activeElement?.textContent==='Fullscreen');
|
||||
// Native touch swipe inside the stage, not a programmatic Reveal.next().
|
||||
await iframe.scrollIntoViewIfNeeded();const b=await iframe.boundingBox();const cdp=await context.newCDPSession(p);
|
||||
await cdp.send('Input.dispatchTouchEvent',{type:'touchStart',touchPoints:[{x:b.x+b.width*.8,y:b.y+b.height*.4}]});
|
||||
await cdp.send('Input.dispatchTouchEvent',{type:'touchMove',touchPoints:[{x:b.x+b.width*.2,y:b.y+b.height*.4}]});await cdp.send('Input.dispatchTouchEvent',{type:'touchEnd',touchPoints:[]});assert.equal(await f.evaluate(()=>Reveal.getIndices().h),1);
|
||||
await p.emulateMedia({reducedMotion:'no-preference'});await f.waitForFunction(()=>Reveal.getConfig().transition==='fade');await p.emulateMedia({reducedMotion:'reduce'});await f.waitForFunction(()=>Reveal.getConfig().transition==='none');
|
||||
await f.locator('.navigate-right').focus();await p.keyboard.press('f');await p.keyboard.press('s');assert.equal(context.pages().length,1);assert.equal(await p.evaluate(()=>!!document.fullscreenElement),false);
|
||||
if(viewport.width<=390){
|
||||
await p.setViewportSize({width:844,height:390});await f.waitForFunction(()=>Reveal.getConfig().width===1200);assert.equal(await f.evaluate(()=>Reveal.getIndices().h),1);
|
||||
await p.setViewportSize(viewport);await f.waitForFunction(()=>Reveal.getConfig().width===600);
|
||||
}
|
||||
// Unsupported fullscreen is non-destructive and keeps a working standalone escape.
|
||||
await p.evaluate(()=>{window.savedFullscreen=Element.prototype.requestFullscreen;Element.prototype.requestFullscreen=undefined});
|
||||
await p.getByRole('button',{name:'Fullscreen',exact:true}).click();await p.getByRole('status').filter({hasText:'Fullscreen is unavailable'}).waitFor();assert.equal(p.url(),root);
|
||||
await p.evaluate(()=>{Element.prototype.requestFullscreen=window.savedFullscreen});
|
||||
// No keyboard trap: browser Tab can leave the frame for the standalone affordance.
|
||||
await f.locator('.navigate-right').focus();for(let i=0;i<12&&!(await p.getByRole('link',{name:/Open presentation/}).evaluate(e=>e===document.activeElement));i++)await p.keyboard.press('Tab');
|
||||
assert(await p.getByRole('link',{name:/Open presentation/}).evaluate(e=>e===document.activeElement));
|
||||
for(const href of await p.locator('.start-card').evaluateAll(es=>es.map(e=>e.href)))assert.equal((await p.request.get(href)).status(),200);
|
||||
await p.getByRole('link',{name:/Open presentation/}).click();await p.waitForFunction(()=>window.Reveal?.isReady());assert(!p.url().includes('embed'));assert(await p.locator('.toolbar').isVisible());
|
||||
assert.deepEqual(errors,[]);results.push({viewport,visited,headingParity:true,keyboardIsolation:true,scrollIsolation:true,touch:true,fullscreen:true,tabExit:true,errors});await context.close();
|
||||
}
|
||||
fs.writeFileSync(`${out}/results.json`,JSON.stringify(results,null,2));console.log('PASS: 92 inline slides, heading parity, URLs, focus/scroll isolation, touch, fullscreen, Tab exit, themes, reduced motion and standalone handoff');
|
||||
}finally{await browser.close()}
|
||||
})().catch(e=>{console.error(e);process.exitCode=1});
|
||||
@@ -12,10 +12,17 @@ const fs = require('node:fs');
|
||||
const context = await browser.newContext({viewport: {width, height: 1000}, colorScheme: 'light'});
|
||||
const page = await context.newPage();
|
||||
await page.goto(`${base}/eldorado-v1/documentation/strategy/`, {waitUntil: 'networkidle'});
|
||||
const panel = page.locator('.archify-panel--story');
|
||||
await page.addStyleTag({content:'html {scroll-behavior:auto !important;}'});
|
||||
const panel = page.locator('.archify-panel--story[data-diagram="strategy-target"]');
|
||||
const iframe = panel.locator(width > 700 ? '.story-desktop' : '.story-mobile');
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
const frame = await (await iframe.elementHandle()).contentFrame();
|
||||
const showControls = () => iframe.evaluate(n => {
|
||||
scrollTo({top:n.getBoundingClientRect().top+scrollY-120,behavior:'instant'});
|
||||
return new Promise(resolve=>requestAnimationFrame(()=>requestAnimationFrame(resolve)));
|
||||
});
|
||||
await showControls();
|
||||
const activate = async selector => {await frame.locator(selector).focus(); await page.keyboard.press('Enter');};
|
||||
const theme = async value => {
|
||||
await page.waitForFunction(t => document.documentElement.dataset.theme === t, value);
|
||||
await frame.waitForFunction(t => document.documentElement.dataset.theme === t, value);
|
||||
@@ -41,9 +48,9 @@ const fs = require('node:fs');
|
||||
assert(menu.y + menu.height <= viewport.y + viewport.height + 1, `${selector} clips vertically`);
|
||||
};
|
||||
const light = await frame.locator('body').evaluate(n => getComputedStyle(n).backgroundColor);
|
||||
await frame.locator('#btn-theme').click(); await theme('dark');
|
||||
await activate('#btn-theme'); await theme('dark');
|
||||
assert.notEqual(await frame.locator('body').evaluate(n => getComputedStyle(n).backgroundColor), light);
|
||||
await frame.locator('#btn-theme').click(); await theme('light');
|
||||
await activate('#btn-theme'); await theme('light');
|
||||
// Mobile portal theme control lives in the navigation drawer.
|
||||
const portalTheme = async target => {
|
||||
if (width <= 700) await page.getByRole('button', {name: 'Toggle navigation bar'}).click();
|
||||
@@ -52,33 +59,34 @@ const fs = require('node:fs');
|
||||
if (await page.locator('html').getAttribute('data-theme') === target) break;
|
||||
}
|
||||
if (width <= 700) await page.getByRole('button', {name: 'Close navigation bar'}).click();
|
||||
await showControls();
|
||||
};
|
||||
await portalTheme('dark'); await theme('dark');
|
||||
await portalTheme('light'); await theme('light');
|
||||
for (const preset of ['signal-flow', 'blueprint', 'editorial', 'classic']) {
|
||||
await frame.locator('#btn-preset').click();
|
||||
await activate('#btn-preset');
|
||||
await checkMenu('.preset-menu');
|
||||
await frame.locator(`[data-preset-value="${preset}"]`).click();
|
||||
await activate(`[data-preset-value="${preset}"]`);
|
||||
assert.equal(await frame.locator('html').getAttribute('data-preset'), preset);
|
||||
}
|
||||
// A theme change must not reload the iframe or lose the selected visual preset.
|
||||
await frame.locator('#btn-preset').click();
|
||||
await frame.locator('[data-preset-value="blueprint"]').click();
|
||||
await activate('#btn-preset');
|
||||
await activate('[data-preset-value="blueprint"]');
|
||||
await portalTheme('dark'); await theme('dark');
|
||||
assert.equal(await frame.locator('html').getAttribute('data-preset'), 'blueprint');
|
||||
const exports = [];
|
||||
for (const format of ['png', 'jpeg', 'webp', 'svg', 'svg-light', 'svg-dark', 'webm']) {
|
||||
await frame.locator('#btn-export').click();
|
||||
await activate('#btn-export');
|
||||
await checkMenu('.export-menu');
|
||||
if (format === 'webm' && await frame.locator('[data-format="webm"]').isDisabled()) {
|
||||
exports.push({format, unsupported: true});
|
||||
await frame.locator('#btn-export').click();
|
||||
await activate('#btn-export');
|
||||
continue;
|
||||
}
|
||||
console.log(`Export ${width} ${format}`);
|
||||
const [download] = await Promise.all([
|
||||
page.waitForEvent('download', {timeout: 60000}),
|
||||
frame.locator(`[data-format="${format}"]`).click(),
|
||||
activate(`[data-format="${format}"]`),
|
||||
]);
|
||||
assert.equal(await download.failure(), null);
|
||||
const path = `${output}/${width}-${format}-${download.suggestedFilename()}`;
|
||||
@@ -88,7 +96,10 @@ const fs = require('node:fs');
|
||||
if (format.startsWith('svg')) {
|
||||
const valid = await page.evaluate(xml => {
|
||||
const doc = new DOMParser().parseFromString(xml, 'image/svg+xml');
|
||||
return !doc.querySelector('parsererror') && doc.documentElement.localName === 'svg' && doc.querySelectorAll('text').length > 0;
|
||||
if (doc.querySelector('[data-node-id="humans"], [data-edge-id="human-direction"]')) return false;
|
||||
if (![...doc.querySelectorAll('[data-node-id="agent"] text')].some(n => n.textContent === 'Human Controlled')) return false;
|
||||
if (doc.querySelectorAll('[data-node-id]').length !== 17 || doc.querySelectorAll('path[data-edge-id]').length !== 24) return false;
|
||||
return !doc.querySelector('parsererror') && doc.documentElement.localName === 'svg' && doc.querySelectorAll('text').length > 0 && doc.querySelector('#eldorado-cycle-export')?.textContent.includes('stroke-dasharray: 3 9');
|
||||
}, bytes.toString());
|
||||
assert(valid, format);
|
||||
} else {
|
||||
@@ -117,12 +128,17 @@ const fs = require('node:fs');
|
||||
await close.focus(); await page.keyboard.press('Escape');
|
||||
assert(await opener.evaluate(n => n === document.activeElement));
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
await page.evaluate(() => scrollTo(0, 0));
|
||||
await page.evaluate(() => scrollTo({top: 0, behavior: 'instant'}));
|
||||
await page.evaluate(() => new Promise(resolve => requestAnimationFrame(() => requestAnimationFrame(resolve))));
|
||||
await page.screenshot({path:`${output}/${width}.png`, fullPage:true});
|
||||
await frame.locator('#btn-theme').click(); await theme('dark');
|
||||
await page.locator('.strategy-content a[href$="/strategy/target-operating-model/"]').filter({visible:true}).click();
|
||||
await frame.locator('#btn-theme').focus(); await page.keyboard.press('Enter'); await theme('dark');
|
||||
// Exercise keyboard navigation without racing the portal's smooth scroll.
|
||||
await page.locator('.strategy-content a[href$="/strategy/roadmap/"]').filter({visible:true}).first().focus();
|
||||
await page.keyboard.press('Enter');
|
||||
await page.waitForURL('**/strategy/roadmap/');
|
||||
await page.goBack({waitUntil:'domcontentloaded'});
|
||||
await page.waitForURL('**/strategy/target-operating-model/');
|
||||
await page.getByRole('heading', {name:'Target operating model', exact:true, level:1}).waitFor();
|
||||
await page.getByRole('heading', {name:'Target', exact:true, level:1}).waitFor();
|
||||
const next = page.locator(`.archify-panel--story[data-diagram="strategy-target"] > .story-${width > 700 ? 'desktop' : 'mobile'}`);
|
||||
await next.scrollIntoViewIfNeeded();
|
||||
await (await (await next.elementHandle()).contentFrame()).waitForFunction(() => document.documentElement.dataset.theme === 'dark');
|
||||
|
||||
@@ -0,0 +1,79 @@
|
||||
const {chromium} = require('playwright');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
(async () => {
|
||||
const base = process.argv[2] || 'http://127.0.0.1:4173';
|
||||
const prefix = '/eldorado-v1/documentation';
|
||||
const manifest = JSON.parse(fs.readFileSync('research/ai-adoption/measurement-migration.json','utf8'));
|
||||
const output = `.cache/metric-pages-${process.argv[3] || 'local'}`;
|
||||
fs.mkdirSync(output,{recursive:true});
|
||||
const browser = await chromium.launch({headless:true,executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']});
|
||||
const results = [];
|
||||
try {
|
||||
for (const width of [1440,390]) {
|
||||
const context = await browser.newContext({viewport:{width,height:900}});
|
||||
try {
|
||||
const page = await context.newPage();
|
||||
const errors = [];
|
||||
page.on('pageerror',e => errors.push(e.message));
|
||||
for (const m of manifest.metrics) {
|
||||
const url = `${base}${prefix}${m.url}`;
|
||||
assert.equal((await page.goto(url,{waitUntil:'networkidle'})).status(),200);
|
||||
assert.equal(await page.locator('article h1').innerText(),m.title);
|
||||
assert.equal(await page.locator('link[rel="canonical"]').getAttribute('href'),`https://pages.apps.lego-cloud.eu${prefix}${m.url}`);
|
||||
const table = page.locator('article table');
|
||||
assert.equal(await table.count(),1);
|
||||
assert.equal(await table.locator('tbody tr').count(),11);
|
||||
const article = await page.locator('article').innerText();
|
||||
assert(article.includes(m.status === 'prototype' ? 'Prototype calculation' : 'Unimplemented metric'));
|
||||
assert(article.includes('no live telemetry'));
|
||||
assert.equal(await page.locator('.breadcrumbs a').filter({hasText:'Measurement'}).getAttribute('href'),`${prefix}/strategy/measurement/`);
|
||||
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth));
|
||||
await page.goto(`${base}${prefix}/strategy/reference/measurement-contracts/#${m.oldAnchor}`,{waitUntil:'networkidle'});
|
||||
await page.waitForURL(url);
|
||||
await page.locator('article h1').waitFor();
|
||||
results.push({width,metric:m.oldAnchor,canonical:true,redirect:true,fields:11});
|
||||
}
|
||||
for (const suffix of ['', '#unknown-anchor', '#__proto__']) {
|
||||
await page.goto(`${base}${prefix}/strategy/reference/measurement-contracts/${suffix}`,{waitUntil:'networkidle'});
|
||||
await page.waitForURL(`${base}${prefix}/strategy/measurement/`);
|
||||
}
|
||||
for (const [anchor,target] of [
|
||||
['collection-and-safeguards','collection-and-safeguards/'],
|
||||
['decide-what-counts-before-counting','collection-and-safeguards/#decide-what-counts-before-counting'],
|
||||
['baseline-and-interpretation','collection-and-safeguards/#baseline-and-interpretation'],
|
||||
['event-and-privacy-contract','collection-and-safeguards/#event-and-privacy-contract'],
|
||||
['run-the-synthetic-measurement-example','synthetic-example/'],
|
||||
['metric-contracts','#metric-definitions'],
|
||||
]) {
|
||||
await page.goto(`${base}${prefix}/strategy/reference/measurement-contracts/#${anchor}`,{waitUntil:'networkidle'});
|
||||
await page.waitForURL(`${base}${prefix}/strategy/measurement/${target}`);
|
||||
if (target.includes('#')) await page.locator(`#${target.split('#')[1]}`).waitFor();
|
||||
}
|
||||
await page.goto(`${base}${prefix}/strategy/measurement/supported-bundle-coverage/`,{waitUntil:'networkidle'});
|
||||
await page.locator('.breadcrumbs a').filter({hasText:'Measurement'}).click();
|
||||
await page.waitForURL(`${base}${prefix}/strategy/measurement/`);
|
||||
if (width < 997) await page.getByRole('button',{name:'Toggle navigation bar'}).click();
|
||||
const menu = page.locator('.theme-doc-sidebar-menu').filter({visible:true});
|
||||
const category = menu.locator('.theme-doc-sidebar-item-category').filter({has:page.getByRole('link',{name:'Measurement',exact:true})}).last();
|
||||
const caret = category.locator(':scope > .menu__list-item-collapsible > button.menu__caret');
|
||||
await caret.click();
|
||||
await category.getByRole('link',{name:'Validated task success',exact:true}).waitFor({state:'hidden'});
|
||||
await caret.focus(); await page.keyboard.press('Enter');
|
||||
await category.getByRole('link',{name:'Validated task success',exact:true}).waitFor({state:'visible'});
|
||||
await menu.getByRole('link',{name:'Measurement',exact:true}).click();
|
||||
await page.waitForURL(`${base}${prefix}/strategy/measurement/`);
|
||||
await page.locator('article h1').waitFor();
|
||||
if (width < 997) await page.getByRole('button',{name:'Close navigation bar'}).waitFor({state:'hidden'});
|
||||
await page.locator('#metric-definitions').scrollIntoViewIfNeeded();
|
||||
await page.screenshot({path:`${output}/${width}-index.png`});
|
||||
await page.goto(`${base}${prefix}/strategy/measurement/supported-bundle-coverage/`,{waitUntil:'networkidle'});
|
||||
await page.screenshot({path:`${output}/${width}-metric.png`,fullPage:true});
|
||||
assert.deepEqual(errors,[]);
|
||||
} finally {await context.close();}
|
||||
}
|
||||
assert.equal(results.length,32);
|
||||
fs.writeFileSync(`${output}/results.json`,JSON.stringify(results,null,2));
|
||||
console.log('PASS: 16 metric pages × 2 widths; canonical metadata, contract fields, status, all legacy metric/shared/fallback redirects and linked Measurement keyboard navigation');
|
||||
} finally {await browser.close();}
|
||||
})().catch(e => {console.error(e);process.exitCode=1;});
|
||||
@@ -0,0 +1,14 @@
|
||||
// Browser-side geometry contract, shared by standalone and embedded acceptance.
|
||||
module.exports = function staircaseFits() {
|
||||
const els=[...document.querySelectorAll('#learning-loop .learning-loop>*')];
|
||||
const b=els.map(e=>e.getBoundingClientRect());
|
||||
const center=r=>({x:(r.left+r.right)/2,y:(r.top+r.bottom)/2});
|
||||
const close=(a,b)=>Math.abs(a-b)<2;
|
||||
return [[0,1,2],[4,5,6],[8,9,10]].every(([a,arrow,c])=>
|
||||
close(center(b[a]).y,center(b[c]).y)&&close(center(b[a]).y,center(b[arrow]).y)&&
|
||||
b[a].right<=b[arrow].left+2&&b[arrow].right<=b[c].left+2
|
||||
)&&[[2,3,4],[6,7,8]].every(([a,arrow,c])=>
|
||||
close(center(b[a]).x,center(b[c]).x)&&close(center(b[a]).x,center(b[arrow]).x)&&
|
||||
b[a].bottom<=b[arrow].top+2&&b[arrow].bottom<=b[c].top+2
|
||||
)&&els.filter(e=>e.tagName==='SPAN').every(e=>e.scrollWidth<=e.clientWidth+1);
|
||||
};
|
||||
@@ -0,0 +1,55 @@
|
||||
const {chromium}=require('playwright');
|
||||
const staircaseFits=require('./presentation-staircase.cjs');
|
||||
const fs=require('node:fs'); const assert=require('node:assert/strict');
|
||||
(async()=>{
|
||||
const base=process.argv[2]||'http://127.0.0.1:4179'; const root='/eldorado-v1/documentation/';const url=base+root+'presentations/less-prompting-more-shipping/';
|
||||
const out='.cache/presentation';fs.mkdirSync(out,{recursive:true});
|
||||
const browser=await chromium.launch({headless:true,args:['--no-sandbox'],executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE});
|
||||
const results=[];
|
||||
try{
|
||||
for(const viewport of [{width:1440,height:900},{width:390,height:844},{width:844,height:390}]){
|
||||
const context=await browser.newContext({viewport,hasTouch:viewport.width<1000,reducedMotion:'reduce'});
|
||||
const page=await context.newPage();const errors=[];page.on('pageerror',e=>errors.push(e.message));page.on('response',r=>{if(r.status()>=400)errors.push(`${r.status()} ${r.url()}`)});page.on('console',m=>{if(m.type()==='error')errors.push(m.text())});
|
||||
assert.equal((await page.goto(url,{waitUntil:'networkidle'})).status(),200);
|
||||
await page.waitForFunction(()=>window.Reveal?.isReady());await page.evaluate(()=>document.fonts.ready);
|
||||
assert.equal(await page.evaluate(()=>Reveal.getTotalSlides()),23);
|
||||
assert.equal(await page.evaluate(()=>Reveal.getConfig().transition),'none');
|
||||
const bounds=[];
|
||||
for(let i=0;i<23;i++){
|
||||
await page.evaluate(i=>Reveal.slide(i),i);await page.waitForTimeout(60);
|
||||
const bad=await page.evaluate(()=>{
|
||||
const slide=Reveal.getCurrentSlide(),r=slide.getBoundingClientRect();
|
||||
return [...slide.querySelectorAll('svg,text,.journey,.learning-loop,.contribution-grid,h1,h2,p,li,td,th,.rail,.gate,.facts,.flow,.roles,.timeline,.capacity,.measure-list,.contrast,.comparison,.choices,.ledger')].filter(e=>!e.closest('.notes')&&e.getBoundingClientRect().width>0).filter(e=>{const b=e.getBoundingClientRect();return b.bottom>r.bottom+1||b.right>r.right+1||b.left<r.left-1||b.top<r.top-1}).map(e=>e.textContent.slice(0,60));
|
||||
});
|
||||
if(i===6)assert(await page.evaluate(staircaseFits),'staircase aligns each arrow with its intended steps');
|
||||
if(i===4)assert(await page.evaluate(()=>[...document.querySelectorAll('#contributors .contribution-grid>div')].every(e=>{const a=e.querySelector('span').getBoundingClientRect(), arrow=e.querySelector('i').getBoundingClientRect(), b=e.querySelector('b').getBoundingClientRect();return a.bottom<=arrow.top+2&&arrow.bottom<=b.top+2&&Math.abs((a.left+a.right-b.left-b.right)/2)<2&&getComputedStyle(e.querySelector('i')).transform==='matrix(0, 1, -1, 0, 0, 0)'})),'contribution arrows must point down to their own phase');
|
||||
bounds.push({slide:i+1,overflow:bad});
|
||||
await page.screenshot({path:`${out}/${viewport.width}-slide-${String(i+1).padStart(2,'0')}.png`});
|
||||
}
|
||||
fs.writeFileSync(`${out}/${viewport.width}-bounds.json`,JSON.stringify(bounds,null,2));
|
||||
assert.deepEqual(bounds.filter(b=>b.overflow.length),[],'slide overflow');
|
||||
await page.goto(url+'#/qualification');await page.reload();await page.waitForFunction(()=>Reveal.isReady());assert.equal(await page.evaluate(()=>Reveal.getCurrentSlide().id),'qualification');
|
||||
await page.keyboard.press('ArrowRight');assert.equal(await page.evaluate(()=>Reveal.getCurrentSlide().id),'experiment');await page.keyboard.press('ArrowLeft');
|
||||
await page.getByRole('button',{name:'Overview',exact:true}).click();assert(await page.evaluate(()=>Reveal.isOverview()));await page.keyboard.press('Escape');assert(!await page.evaluate(()=>Reveal.isOverview()));
|
||||
if(viewport.width===1440){
|
||||
await page.getByRole('button',{name:'Fullscreen',exact:true}).click();await page.waitForFunction(()=>!!document.fullscreenElement);await page.getByRole('button',{name:'Fullscreen',exact:true}).click();await page.waitForFunction(()=>!document.fullscreenElement);
|
||||
const popupPromise=context.waitForEvent('page');await page.getByRole('button',{name:'Notes',exact:true}).click();const popup=await popupPromise;await popup.waitForLoadState();await popup.waitForFunction(()=>document.body.innerText.includes('The author cannot approve'),{timeout:10000});await popup.screenshot({path:`${out}/speaker-view.png`});await popup.close();
|
||||
} else {
|
||||
const client=await context.newCDPSession(page);
|
||||
const before=await page.evaluate(()=>Reveal.getIndices().h);
|
||||
await client.send('Input.dispatchTouchEvent',{type:'touchStart',touchPoints:[{x:viewport.width*.8,y:viewport.height*.5}]});
|
||||
await client.send('Input.dispatchTouchEvent',{type:'touchMove',touchPoints:[{x:viewport.width*.2,y:viewport.height*.5}]});
|
||||
await client.send('Input.dispatchTouchEvent',{type:'touchEnd',touchPoints:[]});
|
||||
assert.equal(await page.evaluate(()=>Reveal.getIndices().h),before+1);
|
||||
}
|
||||
const links=await page.locator('a').evaluateAll(els=>els.map(e=>e.href).filter(h=>!h.includes('?')));
|
||||
for(const link of new Set(links))assert.equal((await page.request.get(link)).status(),200,link);
|
||||
await page.getByRole('link',{name:'Portal',exact:true}).click();await page.waitForURL(base+root);await page.getByRole('link',{name:/Open presentation/}).scrollIntoViewIfNeeded();await page.screenshot({path:`${out}/${viewport.width}-homepage.png`});await page.getByRole('link',{name:/Open presentation/}).click();await page.waitForFunction(()=>window.Reveal?.isReady());
|
||||
assert.deepEqual(errors,[]);results.push({viewport,slides:23,overflow:false,errors,deepLinkRefresh:true,keyboard:true,overview:true,links:true,touch:viewport.width!==1440});await context.close();
|
||||
}
|
||||
const narrow=await browser.newPage({viewport:{width:320,height:720}});await narrow.goto(url,{waitUntil:'networkidle'});await narrow.evaluate(()=>document.fonts.ready);assert(await narrow.evaluate(()=>document.querySelector('.toolbar').scrollWidth<=innerWidth),'320px toolbar must not clip Print');await narrow.screenshot({path:out+'/320-toolbar.png'});await narrow.close();
|
||||
const page=await browser.newPage({viewport:{width:1440,height:900}});await page.goto(url+'?print-pdf',{waitUntil:'networkidle'});await page.waitForFunction(()=>document.querySelectorAll('.pdf-page').length===23);await page.pdf({path:out+'/print.pdf',preferCSSPageSize:true,printBackground:true});
|
||||
assert.equal(await page.locator('.pdf-page').count(),23);
|
||||
fs.writeFileSync(`${out}/results.json`,JSON.stringify({results,printPages:23},null,2));console.log('PASS: 69 slide views, bounds, refresh/hash, keyboard, overview, touch, fullscreen, notes, all links, homepage, print');
|
||||
}finally{await browser.close()}
|
||||
})().catch(e=>{console.error(e);process.exitCode=1});
|
||||
@@ -0,0 +1,138 @@
|
||||
const {chromium} = require('playwright');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
const views = {
|
||||
'strategy-roadmap': ['skills','autonomy'],
|
||||
'strategy-roadmap-adoption': ['delivery','remaining'],
|
||||
'strategy-roadmap-loop': ['understand','baseline','topology','use','collect','reassess'],
|
||||
};
|
||||
(async () => {
|
||||
const base = process.argv[2] || 'http://127.0.0.1:4173';
|
||||
const output = `.cache/roadmap-timeline-${process.argv[3] || 'local'}`;
|
||||
fs.mkdirSync(output, {recursive:true});
|
||||
const browser = await chromium.launch({headless:true, executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE, args:['--no-sandbox']});
|
||||
const results = [];
|
||||
const inspect = async (frame, name, vertical) => {
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
const geometry = await frame.locator('svg[role="img"]').evaluate(svg => ({
|
||||
width:innerWidth, height:innerHeight,
|
||||
edges:[...svg.querySelectorAll('path[data-edge-id]')].map(p => ({id:p.dataset.edgeId,box:p.getBoundingClientRect().toJSON()})),
|
||||
cards:[...svg.querySelectorAll('[data-node-id]')].map(node => ({
|
||||
id:node.dataset.nodeId, box:node.querySelector('rect').getBoundingClientRect().toJSON(),
|
||||
number:node.querySelector('[data-stage-number]').textContent,
|
||||
text:[...node.querySelectorAll('text')].map(text => ({value:text.textContent, box:text.getBoundingClientRect().toJSON(), size:parseFloat(getComputedStyle(text).fontSize)*text.getScreenCTM().a}))
|
||||
}))
|
||||
}));
|
||||
const ids=views[name];
|
||||
geometry.cards.sort((a,b)=>ids.indexOf(a.id)-ids.indexOf(b.id));
|
||||
assert.deepEqual(geometry.cards.map(n => n.id), ids);
|
||||
assert.deepEqual(geometry.cards.map(n => n.number), ids.length === 6 ? ids.map((_,i)=>`Step ${i+1}`) : name === 'strategy-roadmap' ? ['Stage 1','Stage 2'] : ['First','If justified']);
|
||||
assert.equal(geometry.edges.length,ids.length===6?6:1);
|
||||
if(ids.length===6) assert(geometry.edges.some(e=>e.id==='repeat'));
|
||||
for(const edge of geometry.edges) assert(edge.box.left>=0 && edge.box.right<=geometry.width+1 && edge.box.top>=0 && edge.box.bottom<=geometry.height+1, `clipped edge ${name} ${edge.id}`);
|
||||
for (const [index, card] of geometry.cards.entries()) {
|
||||
assert.equal(card.text.length,3);
|
||||
assert(card.box.left >= 0 && card.box.top >= 0 && card.box.right <= geometry.width+1 && card.box.bottom <= geometry.height+1, `outside iframe ${name} ${card.id}`);
|
||||
for(const text of card.text) {
|
||||
assert(text.size>=13, `small text ${name} ${card.id}: ${text.size}`);
|
||||
assert(text.box.left>=card.box.left && text.box.right<=card.box.right+1 && text.box.top>=card.box.top && text.box.bottom<=card.box.bottom+1, `clipped text ${name} ${card.id}`);
|
||||
}
|
||||
for(let t=1;t<card.text.length;t++) assert(card.text[t-1].box.bottom<card.text[t].box.top,`text overlap ${card.id}`);
|
||||
if(index && vertical) {assert.equal(geometry.cards[index-1].box.x,card.box.x);assert(geometry.cards[index-1].box.bottom<card.box.top);}
|
||||
}
|
||||
return geometry;
|
||||
};
|
||||
try {
|
||||
for(const width of [1440,1024,390,320]) {
|
||||
const context=await browser.newContext({viewport:{width,height:1000},colorScheme:'light'});
|
||||
try {
|
||||
const page=await context.newPage(); const errors=[]; page.on('pageerror',e=>errors.push(e.message));
|
||||
assert.equal((await page.goto(`${base}/eldorado-v1/documentation/strategy/roadmap/`,{waitUntil:'networkidle'})).status(),200);
|
||||
await page.addStyleTag({content:'html {scroll-behavior:auto !important;}'});
|
||||
assert.equal(await page.locator('.archify-panel--story').count(),3);
|
||||
for(const name of Object.keys(views)) {
|
||||
const panel=page.locator(`[data-diagram="${name}"]`);
|
||||
const iframe=panel.locator(width<1100?'.story-mobile':'.story-desktop');
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
const frame=await (await iframe.elementHandle()).contentFrame();
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
const opener=panel.getByRole('button',{name:/^Expand /});
|
||||
for(const theme of ['light','dark']) {
|
||||
const frameTop=await iframe.evaluate(n=>n.getBoundingClientRect().top+scrollY);
|
||||
await page.evaluate(y=>scrollTo({top:y-120,behavior:'instant'}),frameTop);
|
||||
if(await frame.locator('html').getAttribute('data-theme')!==theme) {
|
||||
await frame.locator('#btn-theme').focus(); await page.keyboard.press('Enter');
|
||||
}
|
||||
await page.waitForFunction(t=>document.documentElement?.dataset.theme===t,theme);
|
||||
const inline=await inspect(frame,name,width<1100);
|
||||
await frame.locator('#btn-preset').focus();await page.keyboard.press('Enter');
|
||||
await frame.locator('[data-preset-value="blueprint"]').focus();await page.keyboard.press('Enter');
|
||||
await frame.waitForFunction(()=>document.documentElement.dataset.preset==='blueprint');
|
||||
await inspect(frame,name,width<1100);
|
||||
await frame.locator('#btn-preset').focus();await page.keyboard.press('Enter');
|
||||
await frame.locator('[data-preset-value="classic"]').focus();await page.keyboard.press('Enter');
|
||||
await frame.waitForFunction(()=>document.documentElement.dataset.preset==='classic');
|
||||
await frame.locator('#btn-export').focus();await page.keyboard.press('Enter');
|
||||
await frame.locator('[data-format="svg"]').focus();
|
||||
const [download]=await Promise.all([page.waitForEvent('download'),page.keyboard.press('Enter')]);
|
||||
assert.equal(await download.failure(),null);
|
||||
const exported=`${output}/${width}-${theme}-${name}.svg`;
|
||||
await download.saveAs(exported);
|
||||
const svg=fs.readFileSync(exported,'utf8');
|
||||
for(const id of views[name]) assert(svg.includes(`data-node-id="${id}"`));
|
||||
assert(svg.includes('eldorado-roadmap-typography'));
|
||||
await panel.screenshot({path:`${output}/${width}-${theme}-${name}-inline.png`});
|
||||
// Scroll each card into the real viewport: tall iframe captures alone
|
||||
// may contain compositor blanks even when DOM geometry is correct.
|
||||
for(const card of inline.cards) {
|
||||
const top=await iframe.evaluate(n=>n.getBoundingClientRect().top+scrollY);
|
||||
await page.evaluate(y=>scrollTo({top:y,behavior:'instant'}),top+card.box.top-100);
|
||||
await page.screenshot({path:`${output}/${width}-${theme}-${name}-${card.id}.png`});
|
||||
}
|
||||
await opener.focus();await page.keyboard.press('Enter');
|
||||
const close=panel.getByRole('button',{name:'Close full-screen diagram',exact:true});await close.waitFor({state:'visible'});
|
||||
const fullIframe=panel.locator('dialog iframe');
|
||||
const fullscreen=await (await fullIframe.elementHandle()).contentFrame();
|
||||
await fullscreen.waitForFunction(t=>document.documentElement?.dataset.theme===t,theme);
|
||||
const expanded=await inspect(fullscreen,name,width<1000);
|
||||
await page.screenshot({path:`${output}/${width}-${theme}-${name}-fullscreen.png`});
|
||||
await close.focus();await page.keyboard.press('Escape');
|
||||
await fullIframe.waitFor({state:'detached'});assert(await opener.evaluate(n=>n===document.activeElement));
|
||||
results.push({width,theme,name,inline,expanded});fs.writeFileSync(`${output}/results.json`,JSON.stringify(results,null,2));
|
||||
}
|
||||
}
|
||||
assert(!await page.evaluate(()=>document.documentElement.scrollWidth>innerWidth));assert.deepEqual(errors,[]);
|
||||
} finally {await context.close();}
|
||||
}
|
||||
assert.equal(results.length,24);
|
||||
for(const viewport of [{width:390,height:667},{width:320,height:568}]) {
|
||||
const context=await browser.newContext({viewport});
|
||||
try {
|
||||
const page=await context.newPage();await page.goto(`${base}/eldorado-v1/documentation/strategy/roadmap/`,{waitUntil:'networkidle'});
|
||||
await page.addStyleTag({content:'html {scroll-behavior:auto !important;}'});
|
||||
for(const name of Object.keys(views)) {
|
||||
const panel=page.locator(`[data-diagram="${name}"]`), opener=panel.getByRole('button',{name:/^Expand /});
|
||||
await opener.focus();await page.keyboard.press('Enter');const modal=panel.locator('dialog'), close=modal.getByRole('button',{name:'Close full-screen diagram',exact:true});await close.waitFor({state:'visible'});
|
||||
const iframe=modal.locator('iframe'), frame=await (await iframe.elementHandle()).contentFrame();
|
||||
const geometry=await inspect(frame,name,true);
|
||||
assert(await modal.evaluate(n=>n.scrollHeight>n.clientHeight),'short fullscreen must scroll');
|
||||
for(const card of geometry.cards) {
|
||||
await modal.evaluate((n,y)=>{n.scrollTop=y;},card.box.top);
|
||||
const b=await iframe.boundingBox(), t=await modal.locator('.archify-modal-toolbar').boundingBox(), c=await close.boundingBox();
|
||||
assert(c.y>=0 && c.y+c.height<=viewport.height);
|
||||
assert(b.y+card.box.top>=t.y+t.height-1 && b.y+card.box.bottom<=viewport.height+1,`unreachable ${name} ${card.id}`);
|
||||
}
|
||||
await modal.evaluate(n=>{n.scrollTop=0;});
|
||||
for(const selector of ['#btn-theme','#btn-preset','#btn-export']) {
|
||||
const control=frame.locator(selector), b=await control.boundingBox();assert(b.x>=0 && b.x+b.width<=viewport.width && b.y>=0 && b.y+b.height<=viewport.height);await control.click();if(selector!=='#btn-theme')await control.click();
|
||||
}
|
||||
await close.focus();await page.keyboard.press('Escape');await iframe.waitFor({state:'detached'});assert(await opener.evaluate(n=>n===document.activeElement));
|
||||
await page.keyboard.press('Enter');await close.waitFor({state:'visible'});await close.click();await iframe.waitFor({state:'detached'});assert(await opener.evaluate(n=>n===document.activeElement));
|
||||
results.push({viewport,name,scrollable:geometry});fs.writeFileSync(`${output}/results.json`,JSON.stringify(results,null,2));
|
||||
}
|
||||
} finally {await context.close();}
|
||||
}
|
||||
assert.equal(results.length,30);
|
||||
console.log('PASS 48 diagram contexts: three views × four widths × light/dark × inline/fullscreen; plus six short-phone scrolling/keyboard contexts.');
|
||||
} finally {await browser.close();}
|
||||
})().catch(error=>{console.error(error);process.exitCode=1;});
|
||||
@@ -0,0 +1,164 @@
|
||||
const {chromium} = require('playwright');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
(async () => {
|
||||
const base = process.argv[2] || 'http://127.0.0.1:4173';
|
||||
const output = `.cache/roadmap-${process.argv[3] || 'local'}`;
|
||||
fs.mkdirSync(output, {recursive:true});
|
||||
const browser = await chromium.launch({headless:true, executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE, args:['--no-sandbox']});
|
||||
const results = [];
|
||||
try {
|
||||
// Intermediate widths must use the readable vertical Roadmap, not shrink the loop.
|
||||
for (const width of [768, 1024]) {
|
||||
const context = await browser.newContext({viewport:{width,height:1000}, colorScheme:'light'});
|
||||
try {
|
||||
const page = await context.newPage();
|
||||
const errors = [];
|
||||
page.on('pageerror', error => errors.push(error.message));
|
||||
const response = await page.goto(`${base}/eldorado-v1/documentation/strategy/roadmap/`, {waitUntil:'networkidle'});
|
||||
assert.equal(response.status(), 200);
|
||||
const panel = page.locator('.archify-panel--story[data-diagram="strategy-roadmap"]');
|
||||
const iframe = panel.locator('.story-mobile');
|
||||
assert(await iframe.isVisible(), `${width}: vertical Roadmap iframe must be visible`);
|
||||
assert(!await panel.locator('.story-desktop').isVisible(), `${width}: horizontal Roadmap must be hidden`);
|
||||
const frame = await (await iframe.elementHandle()).contentFrame();
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
const geometry = await frame.locator('svg[role="img"]').evaluate(svg => ({
|
||||
width:innerWidth, height:innerHeight,
|
||||
overflow:document.documentElement.scrollWidth > innerWidth || document.documentElement.scrollHeight > innerHeight,
|
||||
nodes:[...svg.querySelectorAll('[data-node-id]')].map(node => ({
|
||||
id:node.dataset.nodeId, box:node.querySelector('rect').getBoundingClientRect().toJSON(),
|
||||
text:[...node.querySelectorAll('text')].map(t => ({text:t.textContent, box:t.getBoundingClientRect().toJSON(), size:parseFloat(getComputedStyle(t).fontSize)*t.getScreenCTM().a}))
|
||||
})).sort((a,b) => a.box.y-b.box.y || a.box.x-b.box.x)
|
||||
}));
|
||||
assert.deepEqual(geometry.nodes.map(n => n.id), ['skills','autonomy']);
|
||||
for (const [index, card] of geometry.nodes.entries()) {
|
||||
assert(card.text.length > 0, `${width}: missing text in ${card.id}`);
|
||||
assert(card.box.left >= 0 && card.box.top >= 0 && card.box.right <= geometry.width + 1 && card.box.bottom <= geometry.height + 1, `${width}: card outside iframe: ${card.id}`);
|
||||
for (const t of card.text) {
|
||||
assert(t.box.left >= card.box.left && t.box.right <= card.box.right + 1 && t.box.top >= card.box.top && t.box.bottom <= card.box.bottom + 1, `${width}: clipped ${card.id} ${t.text}`);
|
||||
assert(t.size >= 11, `${width}: small ${card.id} ${t.text}: ${t.size}`);
|
||||
}
|
||||
if (index) {
|
||||
const previous = geometry.nodes[index - 1].box;
|
||||
assert.equal(previous.x, card.box.x);
|
||||
assert(previous.bottom < card.box.top, `${width}: stages must flow vertically`);
|
||||
}
|
||||
}
|
||||
assert(!geometry.overflow, `${width}: iframe overflow`);
|
||||
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth), `${width}: page overflow`);
|
||||
assert.deepEqual(errors, []);
|
||||
results.push({width, geometry, responsiveReadability:true});
|
||||
fs.writeFileSync(`${output}/results.json`, JSON.stringify(results,null,2));
|
||||
} finally {await context.close();}
|
||||
}
|
||||
for (const width of [1440, 390, 320]) {
|
||||
const context = await browser.newContext({viewport:{width,height:1000}, colorScheme:'light'});
|
||||
const page = await context.newPage();
|
||||
const errors = [];
|
||||
page.on('pageerror', error => errors.push(error.message));
|
||||
const response = await page.goto(`${base}/eldorado-v1/documentation/strategy/roadmap/`, {waitUntil:'networkidle'});
|
||||
assert.equal(response.status(), 200);
|
||||
assert.equal(await page.locator('h1').innerText(), 'Roadmap');
|
||||
const headings = page.locator('.strategy-content > h2');
|
||||
assert.deepEqual((await headings.allTextContents()).map(s => s.replace(/\u200b/g, '')), ['Two stages toward the long-term Target','Stage 1: Delivery first','Improve within each phase','Delivery in practice']);
|
||||
const text = await page.locator('.strategy-content').innerText();
|
||||
for (const marker of ['Humans direct, guide and review throughout', 'Delivery keeps improving', 'system-logic source', 'baseline', 'Target operating model']) assert(text.includes(marker), marker);
|
||||
assert(!text.includes('Supporting gate evidence and hold conditions\n\nThese are'));
|
||||
if (width < 700) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
|
||||
const menu = page.locator('.theme-doc-sidebar-menu .menu__link').filter({visible:true});
|
||||
await menu.first().waitFor({state:'visible'});
|
||||
assert.deepEqual((await menu.allTextContents()).slice(0,2), ['Target','Roadmap']);
|
||||
if (width < 700) await page.getByRole('button', {name:'Close navigation bar'}).click();
|
||||
const panel = page.locator('.archify-panel--story').first();
|
||||
const iframe = panel.locator(width > 700 ? '.story-desktop' : '.story-mobile');
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
const frame = await (await iframe.elementHandle()).contentFrame();
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
const checkCards = async () => {
|
||||
const cards = await frame.locator('svg[role="img"] [data-node-id]').evaluateAll(nodes => nodes.map(node => {
|
||||
const box = node.querySelector('rect').getBoundingClientRect();
|
||||
return {id:node.dataset.nodeId, box:box.toJSON(), text:[...node.querySelectorAll('text')].map(t => ({text:t.textContent, box:t.getBoundingClientRect().toJSON(), size:parseFloat(getComputedStyle(t).fontSize)*t.getScreenCTM().a}))};
|
||||
}));
|
||||
for (const card of cards) for (const t of card.text) {
|
||||
assert(t.box.left >= card.box.left && t.box.right <= card.box.right + 1 && t.box.top >= card.box.top && t.box.bottom <= card.box.bottom + 1, `${width}: clipped ${card.id} ${t.text}`);
|
||||
assert(t.size >= 11, `${width}: small ${card.id} ${t.text}: ${t.size}`);
|
||||
}
|
||||
return cards;
|
||||
};
|
||||
await checkCards();
|
||||
const geometry = await frame.locator('svg[role="img"]').evaluate(svg => ({
|
||||
nodes:[...svg.querySelectorAll('[data-node-id]')].map(n => ({id:n.dataset.nodeId,...n.getBoundingClientRect().toJSON()})).sort((a,b) => a.y-b.y || a.x-b.x),
|
||||
width:innerWidth, height:innerHeight,
|
||||
minLabel:Math.min(...[...svg.querySelectorAll('text[data-node-label]')].map(n => parseFloat(getComputedStyle(n).fontSize)*n.getScreenCTM().a))
|
||||
}));
|
||||
assert.deepEqual(geometry.nodes.map(n => n.id), ['skills','autonomy']);
|
||||
for (const n of geometry.nodes) assert(n.x >= 0 && n.y >= 0 && n.right <= geometry.width + 1 && n.bottom <= geometry.height + 1);
|
||||
assert(geometry.minLabel >= 10, `readable node labels: ${geometry.minLabel}`);
|
||||
for (let i=1; i<geometry.nodes.length; i++) {
|
||||
const a=geometry.nodes[i-1], b=geometry.nodes[i];
|
||||
if(width > 700) {assert.equal(a.y,b.y); assert(a.right < b.x);}
|
||||
else {assert.equal(a.x,b.x); assert(a.bottom < b.y);}
|
||||
}
|
||||
// Portal -> diagram and diagram -> portal are both part of the contract.
|
||||
if (width <= 700) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
|
||||
for (let attempt=0; attempt<3; attempt++) {
|
||||
await page.getByRole('button', {name:/Switch between dark and light mode/}).filter({visible:true}).click();
|
||||
if (await page.locator('html').getAttribute('data-theme') === 'dark') break;
|
||||
}
|
||||
if (width <= 700) await page.getByRole('button', {name:'Close navigation bar'}).click();
|
||||
await frame.waitForFunction(() => document.documentElement.dataset.theme === 'dark');
|
||||
await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(() => document.documentElement.dataset.theme === 'light');
|
||||
await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(() => document.documentElement.dataset.theme === 'dark');
|
||||
await checkCards();
|
||||
await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(() => document.documentElement.dataset.theme === 'light');
|
||||
for (const preset of ['blueprint','classic']) {
|
||||
await frame.locator('#btn-preset').click();
|
||||
await frame.locator(`[data-preset-value="${preset}"]`).click();
|
||||
assert.equal(await frame.locator('html').getAttribute('data-preset'), preset);
|
||||
await checkCards();
|
||||
}
|
||||
await frame.locator('#btn-export').click();
|
||||
const [download] = await Promise.all([page.waitForEvent('download'), frame.locator('[data-format="svg"]').click()]);
|
||||
assert.equal(await download.failure(), null);
|
||||
await download.saveAs(`${output}/${width}.svg`);
|
||||
assert(fs.readFileSync(`${output}/${width}.svg`, 'utf8').includes('Adopt skills'));
|
||||
assert(fs.readFileSync(`${output}/${width}.svg`, 'utf8').includes('eldorado-roadmap-typography'));
|
||||
for (const id of ['skills','autonomy']) {
|
||||
await frame.locator(`svg[role="img"] [data-node-id="${id}"]`).screenshot({path:`${output}/${width}-${id}-card.png`});
|
||||
}
|
||||
const opener = panel.getByRole('button', {name:/^Expand /});
|
||||
await opener.click();
|
||||
const close = panel.getByRole('button', {name:'Close full-screen diagram', exact:true});
|
||||
await close.waitFor({state:'visible'}); assert.equal(await close.innerText(), '×');
|
||||
await close.click(); assert(await opener.evaluate(n => n === document.activeElement));
|
||||
await opener.click(); await close.waitFor({state:'visible'}); await page.keyboard.press('Escape');
|
||||
await page.waitForFunction(() => !document.querySelector('.archify-panel--story dialog').open);
|
||||
assert(await opener.evaluate(n => n === document.activeElement));
|
||||
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth));
|
||||
await page.evaluate(() => scrollTo({top:0, behavior:'instant'}));
|
||||
await page.screenshot({path:`${output}/${width}-top.png`});
|
||||
await headings.first().scrollIntoViewIfNeeded();
|
||||
await page.screenshot({path:`${output}/${width}-assessment.png`});
|
||||
await page.screenshot({path:`${output}/${width}-full.png`, fullPage:true});
|
||||
await page.locator('.strategy-content summary').focus();
|
||||
await page.keyboard.press('Enter');
|
||||
await page.waitForFunction(() => document.querySelector('.strategy-content details').open);
|
||||
await page.locator('.strategy-content details p').last().waitFor({state:'visible'});
|
||||
assert((await page.locator('.strategy-content details').innerText()).includes('exact-artifact approvals'));
|
||||
const links = await page.locator('.strategy-content a').evaluateAll(nodes => nodes.filter(n => !n.classList.contains('hash-link')).map(n => n.href));
|
||||
for (const href of [...new Set(links)]) {
|
||||
const r = await page.goto(href, {waitUntil:'networkidle'}); assert.equal(r.status(), 200);
|
||||
assert.equal(page.url(), href);
|
||||
}
|
||||
assert.deepEqual(errors, []);
|
||||
results.push({width, geometry, links:links.length, controls:true, export:true, sidebar:true, visibleAssessment:true});
|
||||
fs.writeFileSync(`${output}/results.json`, JSON.stringify(results,null,2));
|
||||
await context.close();
|
||||
}
|
||||
console.log(`PASS ${results.length} Roadmap viewports: three-level story, sidebar, diagram geometry, controls, export and links`);
|
||||
} finally {await browser.close();}
|
||||
})().catch(error => {console.error(error); process.exitCode = 1;});
|
||||
@@ -19,8 +19,21 @@ const fs = require('node:fs');
|
||||
await page.waitForURL('**/strategy/target-operating-model/');
|
||||
for (const route of ['target-operating-model/', '']) {
|
||||
await page.goto(`${base}/eldorado-v1/documentation/strategy/${route}`, {waitUntil:'networkidle'});
|
||||
if (width === 1440) assert.equal(await page.locator('.theme-doc-sidebar-menu .menu__link').first().innerText(), 'Target operating model');
|
||||
const iframe = page.locator(`.archify-panel--story > .story-${width > 700 ? 'desktop' : 'mobile'}`);
|
||||
await page.waitForURL('**/strategy/target-operating-model/');
|
||||
if (width < 700) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
|
||||
const menu = page.locator('.theme-doc-sidebar-menu .menu__link').filter({visible:true});
|
||||
await menu.first().waitFor({state:'visible'});
|
||||
assert.deepEqual(await menu.allTextContents(), ['Target', 'Roadmap', '6 Months Target', '6 Months Roadmap', 'Beyond 6 Months']);
|
||||
assert((await menu.nth(0).getAttribute('href')).endsWith('/strategy/target-operating-model/'));
|
||||
assert((await menu.nth(1).getAttribute('href')).endsWith('/strategy/roadmap/'));
|
||||
assert.equal(await menu.filter({hasText:/^Target$/}).count(), 1);
|
||||
await page.screenshot({path:`${output}/${width}-${route ? 'target' : 'landing'}-navigation.png`,fullPage:true,animations:'disabled'});
|
||||
await menu.nth(1).click();
|
||||
await page.waitForURL('**/strategy/roadmap/');
|
||||
await page.getByRole('heading', {level:1,name:'Roadmap',exact:true}).waitFor();
|
||||
await page.goBack({waitUntil:'domcontentloaded'});
|
||||
await page.waitForURL('**/strategy/target-operating-model/');
|
||||
const iframe = page.locator(`[data-diagram="strategy-target"] > .story-${width > 700 ? 'desktop' : 'mobile'}`);
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
const frame = await (await iframe.elementHandle()).contentFrame();
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
@@ -32,15 +45,52 @@ const fs = require('node:fs');
|
||||
const box = n.querySelector('rect').getBoundingClientRect();
|
||||
return [...n.querySelectorAll('text')].filter(t => {const b=t.getBoundingClientRect();return b.left<box.left||b.right>box.right||b.top<box.top||b.bottom>box.bottom;}).map(t=>t.textContent);
|
||||
});
|
||||
return {labels,edges,overflow};
|
||||
const relationships = [...svg.querySelectorAll('path[data-edge-id]')].map(n => ({id:n.dataset.edgeId,from:n.dataset.edgeFrom,to:n.dataset.edgeTo,dash:getComputedStyle(n).strokeDasharray,arrow:n.getAttribute('marker-end')}));
|
||||
const nodes = [...svg.querySelectorAll('[data-node-id]')].map(n => {const r=n.querySelector('rect').getBoundingClientRect();return {id:n.dataset.nodeId,x:r.x+r.width/2,y:r.y+r.height/2};});
|
||||
return {labels,edges,overflow,relationships,nodes};
|
||||
});
|
||||
const ids = ['scope','architecture','ui-ux','planning','delivery','uat','releases'];
|
||||
const ids = ['scope','architecture','ui-ux','planning','delivery','uat','security','releases'];
|
||||
assert.deepEqual(metrics.edges.map(e=>e.slice(0,2)), ids.map((id,i)=>[id,ids[(i+1)%ids.length]]));
|
||||
assert(metrics.edges.every(e=>e[2]?.startsWith('url(')), 'all stages must have arrowheads');
|
||||
assert.equal(metrics.nodes.length, 17);
|
||||
assert.equal(metrics.labels.filter(n => n.text === 'AI Agent').length, 8);
|
||||
assert(!metrics.labels.some(n => /code[ -]agent/i.test(n.text)));
|
||||
assert((await page.locator('.strategy-content').innerText()).includes('human-controlled AI Agent'));
|
||||
assert(!metrics.nodes.some(n=>n.id==='humans'));
|
||||
assert.equal(await frame.locator('[data-node-id="agent"] text').allTextContents().then(texts=>texts.includes('Human Controlled')), true);
|
||||
assert.equal(metrics.relationships.length, 24);
|
||||
const governs = metrics.relationships.filter(e=>e.id.startsWith('govern-'));
|
||||
const contributions = metrics.relationships.filter(e=>e.id.startsWith('contribute-'));
|
||||
assert.deepEqual(governs.map(e=>[e.from,e.to]), ids.map(id=>['agent',id]));
|
||||
assert.deepEqual(contributions.map(e=>[e.from,e.to]), ids.map(id=>[`code-${id}`,id]));
|
||||
assert(governs.every(e=>e.dash==='3px, 9px' && e.arrow?.startsWith('url(')));
|
||||
assert(contributions.every(e=>e.dash==='12px, 8px' && e.arrow?.startsWith('url(')));
|
||||
assert(!metrics.relationships.some(e=>e.id==='human-direction' || e.from==='humans' || e.to==='humans'));
|
||||
if (width > 700) {
|
||||
const agent = metrics.nodes.find(n=>n.id==='agent');
|
||||
const phases = metrics.nodes.filter(n=>ids.includes(n.id));
|
||||
for (const axis of ['x','y']) assert(Math.abs(agent[axis]-(Math.min(...phases.map(n=>n[axis]))+Math.max(...phases.map(n=>n[axis])))/2)<1);
|
||||
for (const id of ids) {
|
||||
const phase=phases.find(n=>n.id===id), code=metrics.nodes.find(n=>n.id===`code-${id}`);
|
||||
assert(Math.hypot(code.x-agent.x,code.y-agent.y)>Math.hypot(phase.x-agent.x,phase.y-agent.y));
|
||||
}
|
||||
}
|
||||
assert(metrics.labels.every(n=>n.px>=14), JSON.stringify(metrics.labels));
|
||||
assert.deepEqual(metrics.overflow, []);
|
||||
await frame.locator('#btn-export').focus(); await page.keyboard.press('Enter');
|
||||
await frame.locator('[data-format="svg"]').focus();
|
||||
const [download] = await Promise.all([page.waitForEvent('download'), page.keyboard.press('Enter')]);
|
||||
assert.equal(await download.failure(), null);
|
||||
const exportPath = `${output}/${width}-${route ? 'target' : 'landing'}.svg`;
|
||||
await download.saveAs(exportPath);
|
||||
const exported = fs.readFileSync(exportPath, 'utf8');
|
||||
assert.equal((exported.match(/>AI Agent<\/text>/g) || []).length, 8);
|
||||
assert(!/code[ -]agent/i.test(exported));
|
||||
assert(exported.includes('Autonomous agent') && exported.includes('Human Controlled'));
|
||||
assert(!await page.evaluate(()=>document.documentElement.scrollWidth>innerWidth));
|
||||
await page.evaluate(()=>scrollTo(0,0));
|
||||
await page.evaluate(()=>scrollTo({top:0,behavior:'instant'}));
|
||||
await page.waitForFunction(()=>scrollY===0);
|
||||
await page.evaluate(()=>new Promise(resolve=>requestAnimationFrame(()=>requestAnimationFrame(resolve))));
|
||||
await page.screenshot({path:`${output}/${width}-${route ? 'target' : 'landing'}.png`,fullPage:true});
|
||||
results.push({width,route,...metrics});
|
||||
fs.writeFileSync(`${output}/results.json`,JSON.stringify(results,null,2));
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
const {chromium} = require('playwright');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
(async () => {
|
||||
const base = process.argv[2] || 'http://127.0.0.1:4173';
|
||||
const output = `.cache/sidebar-browser-${process.argv[3] || 'local'}`;
|
||||
const {documents} = JSON.parse(fs.readFileSync('.cache/sidebar-coverage.json', 'utf8'));
|
||||
assert(documents.length > 0);
|
||||
fs.mkdirSync(output, {recursive:true});
|
||||
const browser = await chromium.launch({headless:true, executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE, args:['--no-sandbox']});
|
||||
const results = [];
|
||||
try {
|
||||
for (const width of [1440,390,320]) {
|
||||
const context = await browser.newContext({viewport:{width,height:900}});
|
||||
try {
|
||||
const page = await context.newPage();
|
||||
const errors = [];
|
||||
page.on('pageerror', e => errors.push(e.message));
|
||||
const menu = page.locator('.theme-doc-sidebar-menu').filter({visible:true});
|
||||
const open = async () => {
|
||||
if (width < 997) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
|
||||
await menu.waitFor();
|
||||
};
|
||||
for (const doc of documents) {
|
||||
assert.equal((await page.goto(`${base}${doc.route}/`, {waitUntil:'networkidle'})).status(), 200);
|
||||
await page.locator('article h1').waitFor();
|
||||
await open();
|
||||
const links = menu.locator('a[href]:not([role="button"])').filter({visible:true});
|
||||
const active = await links.evaluateAll((nodes, route) => nodes.filter(n => n.pathname.replace(/\/$/,'') === route).map(n => n.textContent), doc.route);
|
||||
assert.equal(active.length, 1, `${width}: visible unique owning-sidebar entry for ${doc.route}`);
|
||||
results.push({width, route:doc.route, visibleEntry:active[0]});
|
||||
}
|
||||
// Contribution exposes all legacy maintenance pages without changing routes.
|
||||
for (const [label, route] of [['Starting point','overview'],['Update and publish','maintain'],['Site configuration','reference']]) {
|
||||
await page.goto(`${base}/eldorado-v1/documentation/contribution/`, {waitUntil:'networkidle'});
|
||||
await open();
|
||||
const toggle = menu.getByRole('button', {name:'Portal maintenance', exact:true});
|
||||
await toggle.focus();
|
||||
await page.keyboard.press('Enter');
|
||||
await menu.getByRole('link', {name:label, exact:true}).click();
|
||||
await page.waitForURL(`${base}/eldorado-v1/documentation/docs/${route}/`);
|
||||
await page.locator('article h1').waitFor();
|
||||
}
|
||||
const reference = '/eldorado-v1/documentation/strategy/reference/measurement-contracts/';
|
||||
await page.goto(`${base}${reference}#supported-bundle-coverage`, {waitUntil:'networkidle'});
|
||||
await page.waitForURL(`${base}/eldorado-v1/documentation/strategy/measurement/supported-bundle-coverage/`);
|
||||
await page.getByRole('heading', {level:1, name:'Supported bundle coverage', exact:true}).waitFor();
|
||||
assert((await page.locator('article').innerText()).includes('Supported bundle coverage'));
|
||||
assert.equal(await page.locator('.breadcrumbs a').filter({hasText:'6 Months Roadmap'}).getAttribute('href'), '/eldorado-v1/documentation/strategy/six-months-roadmap/');
|
||||
assert((await page.locator('.breadcrumbs').innerText()).includes('Measurement'));
|
||||
await open();
|
||||
await menu.getByRole('link', {name:'Supported bundle coverage', exact:true}).waitFor({state:'visible'});
|
||||
await page.screenshot({path:`${output}/${width}-reference.png`, animations:'disabled'});
|
||||
assert.deepEqual(errors, []);
|
||||
} finally {await context.close();}
|
||||
}
|
||||
assert.equal(results.length, documents.length * 3);
|
||||
fs.writeFileSync(`${output}/results.json`, JSON.stringify(results,null,2));
|
||||
console.log(`PASS: all ${documents.length} docs have visible unique sidebar entries at 3 viewports; Contribution links, Measurement breadcrumbs and reported anchor redirect work`);
|
||||
} finally {await browser.close();}
|
||||
})().catch(e => {console.error(e); process.exitCode = 1;});
|
||||
@@ -0,0 +1,51 @@
|
||||
const {chromium}=require('playwright');
|
||||
const fs=require('node:fs');
|
||||
const path=require('node:path');
|
||||
const assert=require('node:assert/strict');
|
||||
(async()=>{
|
||||
const dir=process.argv[2]||'.cache/skills-candidate';
|
||||
const browser=await chromium.launch({executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']});
|
||||
const results=[];
|
||||
try {
|
||||
for(const topic of ['measurement','baseline','governance','quality','adoption','maintenance','stage01','stage02']) for(const width of [1440,1024,390,320]){
|
||||
const spec=JSON.parse(fs.readFileSync(`diagrams/strategy-${topic}${width<=1100?'-mobile':''}.architecture.json`));
|
||||
const page=await browser.newPage({viewport:{width:1200,height:1000}});
|
||||
await page.goto('file://'+path.resolve(`${dir}/${topic}-${width}.svg`));
|
||||
const measured=await page.locator('svg').evaluate(svg=>{
|
||||
const v=svg.viewBox.baseVal;const issues=[];
|
||||
for(const el of svg.querySelectorAll('[data-node-id],path[data-edge-id],g[data-edge-id]')){
|
||||
const b=el.getBBox();if(b.x<v.x-1||b.y<v.y-1||b.x+b.width>v.x+v.width+1||b.y+b.height>v.y+v.height+1)issues.push(el.getAttribute('data-node-id')||el.getAttribute('data-edge-id'));
|
||||
}
|
||||
// Measure the whole rendered label group, including its opaque mask:
|
||||
// text presence alone cannot detect one label hiding another.
|
||||
const labels=[...svg.querySelectorAll('g[data-edge-id]')].filter(el=>el.querySelector('text')).map(el=>({id:el.dataset.edgeId,box:el.getBoundingClientRect()}));
|
||||
const labelOverlaps=[];
|
||||
const nodes=[...svg.querySelectorAll('[data-node-id]')].map(el=>({id:el.dataset.nodeId,box:el.getBoundingClientRect()}));
|
||||
const labelNodeOverlaps=[];
|
||||
for(const a of labels)for(const b of nodes){
|
||||
if(Math.min(a.box.right,b.box.right)>Math.max(a.box.left,b.box.left)&&Math.min(a.box.bottom,b.box.bottom)>Math.max(a.box.top,b.box.top))labelNodeOverlaps.push([a.id,b.id]);
|
||||
}
|
||||
for(let i=0;i<labels.length;i++)for(let j=i+1;j<labels.length;j++){
|
||||
const a=labels[i],b=labels[j];
|
||||
if(Math.min(a.box.right,b.box.right)>Math.max(a.box.left,b.box.left)&&Math.min(a.box.bottom,b.box.bottom)>Math.max(a.box.top,b.box.top))labelOverlaps.push([a.id,b.id]);
|
||||
}
|
||||
return {labelOverlaps,labelNodeOverlaps,viewBox:[v.width,v.height],nodes:[...svg.querySelectorAll('[data-node-id]')].map(n=>n.dataset.nodeId),edges:[...svg.querySelectorAll('path[data-edge-id]')].map(n=>n.dataset.edgeId),text:svg.textContent,issues};
|
||||
});
|
||||
assert.deepEqual(measured.viewBox,spec.meta.viewBox);
|
||||
assert.deepEqual(measured.nodes.sort(),spec.components.map(n=>n.id).sort());
|
||||
assert.deepEqual(measured.edges.sort(),spec.connections.map(e=>e.id).sort());
|
||||
assert.deepEqual(measured.issues,[]);
|
||||
assert.deepEqual(measured.labelOverlaps,[],`${topic}-${width}: rendered edge labels overlap`);
|
||||
assert.deepEqual(measured.labelNodeOverlaps,[],`${topic}-${width}: edge label obscures a node`);
|
||||
for(const n of spec.components){assert(measured.text.includes(n.label));assert(measured.text.includes(n.tag));for(const line of n.sublabel.split('\n'))assert(measured.text.includes(line));}
|
||||
for(const e of spec.connections)if(e.label)assert(measured.text.includes(e.label));
|
||||
if(width===1440){
|
||||
await page.setViewportSize({width:spec.meta.viewBox[0],height:spec.meta.viewBox[1]});
|
||||
await page.screenshot({path:`${dir}/${topic}-standalone-export.png`});
|
||||
}
|
||||
results.push({topic,width,nodes:measured.nodes.length,edges:measured.edges.length,complete:true});await page.close();
|
||||
}
|
||||
fs.writeFileSync(`${dir}/export-results.json`,JSON.stringify(results,null,2));
|
||||
console.log(`PASS ${results.length} standalone SVGs: exact graph, text, full-canvas containment and non-overlapping edge labels`);
|
||||
}finally{await browser.close();}
|
||||
})().catch(e=>{console.error(e);process.exitCode=1});
|
||||
@@ -0,0 +1,113 @@
|
||||
const {chromium} = require('playwright');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
(async () => {
|
||||
const base = process.argv[2] || 'http://127.0.0.1:4173';
|
||||
const output = `.cache/measurement-${process.argv[3] || 'local'}`;
|
||||
fs.mkdirSync(output, {recursive:true});
|
||||
const browser = await chromium.launch({headless:true, executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE, args:['--no-sandbox']});
|
||||
const results = [];
|
||||
try {
|
||||
for (const width of [1440, 390, 320]) {
|
||||
const context = await browser.newContext({viewport:{width,height:1000}, colorScheme:'light'});
|
||||
const page = await context.newPage();
|
||||
const errors = [];
|
||||
page.on('pageerror', error => errors.push(error.message));
|
||||
const response = await page.goto(`${base}/eldorado-v1/documentation/strategy/measurement/`, {waitUntil:'networkidle'});
|
||||
assert.equal(response.status(), 200);
|
||||
assert.equal(await page.locator('h1').innerText(), 'Measuring real output');
|
||||
assert((await page.title()).startsWith('Measuring real output |'));
|
||||
assert.equal(await page.locator('.strategy-content details').count(), 1);
|
||||
assert.equal(await page.locator('.strategy-content details[open]').count(), 0);
|
||||
assert((await page.locator('.strategy-content details summary').innerText()).includes('Implementation status'));
|
||||
assert.equal(await page.locator('.strategy-content h2').count(), 2);
|
||||
assert.deepEqual((await page.locator('.strategy-content h3').allTextContents()).map(text => text.replaceAll('\u200b', '')), ['Workflow effectiveness', 'Skills effectiveness & health']);
|
||||
assert.equal(await page.locator('.strategy-content ol').count(), 2);
|
||||
assert.equal(await page.locator('.strategy-content ol > li').count(), 16);
|
||||
if (width < 700) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
|
||||
const menu = page.locator('.theme-doc-sidebar-menu .menu__link').filter({visible:true});
|
||||
await menu.first().waitFor({state:'visible'});
|
||||
const metrics = JSON.parse(fs.readFileSync('research/ai-adoption/measurement-migration.json','utf8')).metrics;
|
||||
assert.deepEqual(await menu.allTextContents(), ['Target','Roadmap','6 Months Target','6 Months Roadmap','Skills lifecycle reference','Measurement',...metrics.map(m => m.title),'Collection and safeguards','Run the synthetic measurement example','Baseline','Governance','Quality','Adoption','Maintenance','Beyond 6 Months']);
|
||||
if (width < 700) await page.getByRole('button', {name:'Close navigation bar'}).click();
|
||||
const panel = page.locator('.archify-panel--story');
|
||||
const iframe = panel.locator(width > 700 ? '.story-desktop' : '.story-mobile');
|
||||
await iframe.scrollIntoViewIfNeeded();
|
||||
const frame = await (await iframe.elementHandle()).contentFrame();
|
||||
await frame.locator('svg[role="img"]').waitFor();
|
||||
const geometry = await frame.locator('svg[role="img"]').evaluate(svg => {
|
||||
const nodes = [...svg.querySelectorAll('[data-node-id]')].map(n => n.getBoundingClientRect().toJSON());
|
||||
return {nodes, width:innerWidth, height:innerHeight, minLabel:Math.min(...[...svg.querySelectorAll('text[data-node-label]')].map(n => parseFloat(getComputedStyle(n).fontSize)*n.getScreenCTM().a))};
|
||||
});
|
||||
assert.equal(geometry.nodes.length, JSON.parse(fs.readFileSync('diagrams/strategy-measurement.architecture.json')).components.length);
|
||||
for (const n of geometry.nodes) assert(n.x >= 0 && n.y >= 0 && n.right <= geometry.width + 1 && n.bottom <= geometry.height + 1);
|
||||
assert(geometry.minLabel >= 10, `readable node labels: ${geometry.minLabel}`);
|
||||
await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(() => document.documentElement.dataset.theme === 'dark');
|
||||
await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(() => document.documentElement.dataset.theme === 'light');
|
||||
for (const preset of ['signal-flow','blueprint','editorial','classic']) {
|
||||
await frame.locator('#btn-preset').click();
|
||||
await frame.locator(`[data-preset-value="${preset}"]`).click();
|
||||
assert.equal(await frame.locator('html').getAttribute('data-preset'), preset);
|
||||
}
|
||||
await frame.locator('#btn-export').click();
|
||||
const [download] = await Promise.all([page.waitForEvent('download'), frame.locator('[data-format="svg"]').click()]);
|
||||
assert.equal(await download.failure(), null);
|
||||
const path = `${output}/${width}.svg`; await download.saveAs(path);
|
||||
const svg = fs.readFileSync(path, 'utf8');
|
||||
assert(svg.includes('Workflow effectiveness') && svg.includes('Skills effectiveness & health') && svg.includes('No mandatory collection'));
|
||||
const exports = ['svg'];
|
||||
for (const format of ['png','jpeg','webp','svg-light','svg-dark','webm']) {
|
||||
await frame.locator('#btn-export').click();
|
||||
const option = frame.locator(`[data-format="${format}"]`);
|
||||
if (await option.isDisabled()) { exports.push(`${format}:unsupported`); await frame.locator('#btn-export').click(); continue; }
|
||||
const [file] = await Promise.all([page.waitForEvent('download', {timeout:60000}), option.click()]);
|
||||
assert.equal(await file.failure(), null);
|
||||
const target = `${output}/${width}-${format}-${file.suggestedFilename()}`;
|
||||
await file.saveAs(target);
|
||||
const bytes = fs.readFileSync(target); assert(bytes.length > 1000);
|
||||
if (format.startsWith('svg')) assert(bytes.toString().includes('eldorado-skills-typography'));
|
||||
else {
|
||||
const mime = {png:'image/png', jpeg:'image/jpeg', webp:'image/webp', webm:'video/webm'}[format];
|
||||
const dimensions = await page.evaluate(async ({mime,data}) => {
|
||||
const media = document.createElement(mime.startsWith('video') ? 'video' : 'img');
|
||||
const ready = new Promise((resolve,reject) => {media[mime.startsWith('video') ? 'onloadedmetadata' : 'onload'] = resolve; media.onerror = reject;});
|
||||
media.src = `data:${mime};base64,${data}`; await ready;
|
||||
return [media.videoWidth || media.naturalWidth, media.videoHeight || media.naturalHeight];
|
||||
}, {mime, data:bytes.toString('base64')});
|
||||
assert(dimensions.every(n => n > 0));
|
||||
}
|
||||
exports.push(format);
|
||||
}
|
||||
const opener = panel.getByRole('button', {name:/^Expand /});
|
||||
await opener.click();
|
||||
const close = panel.getByRole('button', {name:'Close full-screen diagram', exact:true});
|
||||
await close.waitFor({state:'visible'}); assert.equal(await close.innerText(), '×');
|
||||
await close.click(); assert(await opener.evaluate(n => n === document.activeElement));
|
||||
await opener.click(); await close.waitFor({state:'visible'}); await close.focus(); await page.keyboard.press('Escape');
|
||||
await page.waitForFunction(() => !document.querySelector('.archify-panel--story dialog').open);
|
||||
assert(await opener.evaluate(n => n === document.activeElement));
|
||||
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth));
|
||||
await page.evaluate(() => scrollTo({top:0, behavior:'instant'}));
|
||||
await page.screenshot({path:`${output}/${width}-top.png`});
|
||||
await page.locator('.strategy-content h2').nth(1).scrollIntoViewIfNeeded();
|
||||
await page.screenshot({path:`${output}/${width}-pilot.png`});
|
||||
await page.screenshot({path:`${output}/${width}-full.png`, fullPage:true});
|
||||
const links = await page.locator('.strategy-content a[href*="/measurement/"]').evaluateAll(nodes => nodes.map(n => n.href));
|
||||
for (const href of [...new Set(links)]) {
|
||||
const navigation = await page.goto(href, {waitUntil:'networkidle'});
|
||||
if (navigation) assert.equal(navigation.status(), 200);
|
||||
assert.equal(page.url(), href);
|
||||
if (new URL(href).hash) await page.locator(new URL(href).hash).waitFor({state:'visible'});
|
||||
}
|
||||
assert.equal(new Set(links.map(h => new URL(h).pathname)).size, 18);
|
||||
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth));
|
||||
assert.deepEqual(errors, []);
|
||||
results.push({width, geometry, links:links.length, title:true, sidebar:true, controls:true, exports, reference:true});
|
||||
fs.writeFileSync(`${output}/results.json`, JSON.stringify(results,null,2));
|
||||
await context.close();
|
||||
}
|
||||
console.log(`PASS ${results.length} Skills Measurement viewports: title/sidebar, optional registry, diagram geometry/controls/export, all reference links and no page errors`);
|
||||
} finally {await browser.close();}
|
||||
})().catch(error => {console.error(error); process.exitCode = 1;});
|
||||
@@ -0,0 +1,60 @@
|
||||
const {chromium}=require('playwright');
|
||||
const fs=require('node:fs');
|
||||
const assert=require('node:assert/strict');
|
||||
(async()=>{
|
||||
const base=process.argv[2]||'http://127.0.0.1:4173';
|
||||
const out=`.cache/skills-${process.argv[3]||'candidate'}`;fs.mkdirSync(out,{recursive:true});
|
||||
const browser=await chromium.launch({executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']}); const results=[];
|
||||
try {
|
||||
for(const topic of ['six-months','measurement','baseline','governance','quality','adoption','maintenance','stage01','stage02']) for(const width of [1440,1024,390,320]) {
|
||||
console.log(`Checking ${topic} at ${width}px`);
|
||||
const page=await browser.newPage({viewport:{width,height:900},colorScheme:'light'});const errors=[];page.on('pageerror',e=>errors.push(e.message));
|
||||
const route=topic==='six-months'?'six-months-roadmap':topic==='stage01'?'stage-01-skills-adoption':topic==='stage02'?'stage-02-autonomous-agent':['measurement','baseline'].includes(topic)?topic:`skills-${topic}`;
|
||||
assert.equal((await page.goto(`${base}/eldorado-v1/documentation/strategy/${route}/`,{waitUntil:'networkidle'})).status(),200);
|
||||
const panel=page.locator('.archify-panel--skills');assert.equal(await panel.count(),1);
|
||||
const iframe=panel.locator(width>1100?'.story-desktop':'.story-mobile');await iframe.scrollIntoViewIfNeeded();
|
||||
const frame=await(await iframe.elementHandle()).contentFrame();await frame.locator('svg[role="img"]').waitFor();
|
||||
// Keep iframe controls below the fixed portal header. Frame-local click
|
||||
// actionability cannot detect an overlay in the parent document.
|
||||
const showControls=async()=>{
|
||||
await panel.locator('dialog iframe').waitFor({state:'detached'});
|
||||
await panel.evaluate(n=>{
|
||||
scrollTo({top:n.getBoundingClientRect().top+scrollY-100,behavior:'instant'});
|
||||
return new Promise(resolve=>requestAnimationFrame(()=>requestAnimationFrame(resolve)));
|
||||
});
|
||||
};
|
||||
const geometry=await frame.locator('svg[role="img"]').evaluate(svg=>{
|
||||
const nodes=[...svg.querySelectorAll('g[data-node-id]')];const issues=[];let min=Infinity;
|
||||
for(const n of nodes){const rect=n.querySelector('rect').getBBox();for(const t of n.querySelectorAll('text')){
|
||||
const b=t.getBBox();min=Math.min(min,parseFloat(getComputedStyle(t).fontSize)*t.getScreenCTM().a);
|
||||
if(b.x<rect.x||b.y<rect.y||b.x+b.width>rect.x+rect.width||b.y+b.height>rect.y+rect.height)issues.push(n.id+':'+t.textContent);
|
||||
}}
|
||||
return {nodes:nodes.length,min,issues,width:innerWidth,svgWidth:svg.getBoundingClientRect().width};
|
||||
});
|
||||
const source=JSON.parse(fs.readFileSync(`diagrams/strategy-${topic}.architecture.json`));
|
||||
assert.equal(geometry.nodes,source.components.length);assert.deepEqual(geometry.issues,[]);assert(geometry.min>=10,JSON.stringify(geometry));
|
||||
for(const theme of ['light','dark']){
|
||||
await showControls();
|
||||
if(await frame.locator('html').getAttribute('data-theme')!==theme)await frame.locator('#btn-theme').click();
|
||||
await page.waitForFunction(t=>document.documentElement.dataset.theme===t,theme).catch(error=>{throw new Error(`${topic}/${width}/${theme}: theme synchronization failed`,{cause:error});});
|
||||
await panel.scrollIntoViewIfNeeded();await page.screenshot({path:`${out}/${topic}-${width}-${theme}-inline.png`});
|
||||
const open=panel.getByRole('button',{name:/^Expand /});await open.click();const close=panel.getByRole('button',{name:'Close full-screen diagram',exact:true});await close.waitFor({state:'visible'});
|
||||
const expanded=await(await panel.locator('dialog iframe').elementHandle()).contentFrame();await expanded.locator('svg[role="img"]').waitFor();
|
||||
await expanded.waitForFunction(t=>document.documentElement.dataset.theme===t,theme);
|
||||
await panel.locator('dialog').evaluate(n=>n.scrollTop=0);
|
||||
assert((await expanded.url()).includes(width<=1100?`${topic}-mobile/`:`${topic}/`));
|
||||
await page.screenshot({path:`${out}/${topic}-${width}-${theme}-fullscreen.png`});
|
||||
if(width<=700){await page.setViewportSize({width,height:480});assert(await panel.locator('dialog').evaluate(n=>n.scrollHeight>n.clientHeight));await panel.locator('dialog').evaluate(n=>n.scrollTop=n.scrollHeight);await page.screenshot({path:`${out}/${topic}-${width}-${theme}-short-bottom.png`});await page.setViewportSize({width,height:900});}
|
||||
await close.focus();await page.keyboard.press('Escape');assert(await open.evaluate(n=>n===document.activeElement));
|
||||
}
|
||||
await showControls();
|
||||
await frame.locator('#btn-preset').click();await frame.locator('[data-preset-value="blueprint"]').click();
|
||||
await frame.locator('#btn-preset').click();await frame.locator('[data-preset-value="classic"]').click();
|
||||
await frame.locator('#btn-export').click();const [download]=await Promise.all([page.waitForEvent('download'),frame.locator('[data-format="svg"]').click()]);assert.equal(await download.failure(),null);
|
||||
await download.saveAs(`${out}/${topic}-${width}.svg`);assert(fs.readFileSync(`${out}/${topic}-${width}.svg`,'utf8').includes('eldorado-skills-typography'));
|
||||
assert(!await page.evaluate(()=>document.documentElement.scrollWidth>innerWidth));assert.deepEqual(errors,[]);
|
||||
results.push({topic,width,geometry,controls:true,export:true,themes:true,fullscreen:true});fs.writeFileSync(`${out}/results.json`,JSON.stringify(results,null,2));await page.close();
|
||||
}
|
||||
console.log(`PASS ${results.length} Skills story contexts: geometry, themes, controls, exports, fullscreen and short-phone scrolling`);
|
||||
}finally{await browser.close();}
|
||||
})().catch(e=>{console.error(e);process.exitCode=1});
|
||||
Loaded 100 of 139 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user