// 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,
More Shipping",
"minutes": 1,
"body": "
The destination—and the first six months toward it
Improve accepted engineering work.
Not the number of times we ask AI.
Proposed strategy · 35 minutes + 15 minutes Q&A
", "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": "Solo architect → CTO
No formal authority over teams
Stack, tools, process, baselines
Capacity and actual bottlenecks
Less rework. Sound quality.
Understand the total burden.
If the bottleneck is CI or review capacity, fix that—not the prompt count.
", "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 + `Solid → lifecycle · Dotted ⇢ executes and governs
Humans direct, guide and review. Not deployed or promised in six months.
`, "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": `Eight separate AI Agents, each human-controlled.
` + contributionsFigure + `AI Agent = Claude, Cline, ChatGPT or a similar tool, used under human control.
A strategic progression—not a six-month schedule or automatic graduation.
", "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": "Triggers → skills → handoffs → acceptance.
Relationships and cooperation—not merely a catalogue.
", "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": "Earn a dependable building block.
Do not promise the entire destination.
An invitation with an exit.
Not a rollout disguised as a favor.
Trace real changes.
Rank friction and evidence gaps.
One willing team.
Baseline + smallest intervention.
No partner, reliable checks or lawful evidence → no live pilot.
", "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": "Build and independently qualify.
Pair on bounded real work.
Reconcile outcomes and burden.
Include pending and abandoned work.
Missing follow-up is “unknown”, not “all clear”.
", "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": "Champion + backup.
Check a second team’s fit.
Team operates without daily help.
CTO chooses the next investment.
New scope → new baseline.
No automatic company-wide rollout.
Support is work.
Put it in the budget.
Proposed capacity envelope—not known company availability.
", "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": "Task / PR / CI / defect links + a small effort record; no individual league tables.
", "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": "Tempting signal
More PRs or generated lines
Shorter PR elapsed time
Higher acceptance rate
No defects recorded
Question before believing it
Useful work—or smaller slices?
Less effort—or less waiting?
Same task mix and denominator?
Enough follow-up and linkage?
AI usage is diagnostic.
It is not the score.
Try to break it
Wrong task · injected instruction
Missing tests · recovery
First revision
No approved prior skill = N/A
Remove + reload → current practice
Fictional teaching example · not Eldorado results or approval
Keep the useful practice.
Reject the unsupported benefit claim.
Existing AI practice is the comparator. A skill is tested only if needed.
", "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": "Proposed achievable picture. No guaranteed savings, headcount reduction or org-wide uplift.
", "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": "Coaching, context or deterministic tooling where friction remains.
Only with repeatable value, local fit and supported ownership.
Separate authority case, containment and human takeover.
Established destination. Evidence-led steps.
Separate authority—not automatic graduation.
Independent stop. Human takeover.
Readiness failure → hold or redesign. Missing evidence is never permission.
", "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": "Sponsor the learning.
Do not pre-approve the answer.
15 minutes for the hard questions.
No willing team?
Too little evidence?
A cheaper non-AI fix?
The proposed plan can change. The evidence standard should not.
", "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": "