Mastery: your playbook

Your mastery artifact is a capstone evidence portfolio with roadmap, architecture decisions, demos, eval reports, risk log, traces, release notes, and retrospective. It should let a competent colleague repeat plan and ship a personal knowledge assistant in staged, testable layers without inheriting unstated assumptions. Include the job card, source requirements, prompt contract, examples, rubric, privacy boundary, escalation rule, and recovery steps.

Use scope → vertical slice → ground → evaluate → harden → deploy → monitor as the spine. For every stage, name the input, action, output, owner, check, and stop condition. Include the concrete prompt:

Turn this capstone goal into six two-week milestones: an assistant answers questions from my approved notes with citations. Sequence API, structured output, retrieval, citations, tools, memory, evals, injection defense, tracing, retries, deploy, and monitoring. For each milestone define a demo, test, dependency, risk, and stop rule. Do not pretend all layers fit at once.

Then include a specimen response: A dependency-aware roadmap that ships a narrow cited-answer slice early, then adds quality and operational layers behind explicit gates. Label it as an example, not a guaranteed result. Attach proof from the independent check: you must demo each milestone against golden tasks, inspect citations, run eval gates, test hostile inputs, review traces, exercise retries, and rehearse rollback.

Run the same playbook on a second case that differs in one meaningful way. Keep the quality bar fixed. Explain which context fields and constraints changed. If the workflow only succeeds on the memorized example, it is not mastered.

Teach the method in five minutes to someone who has not read this chapter. Ask them to identify the source of truth, the riskiest failure, and the human decision. Their answers reveal whether your playbook is explicit.

Score yourself:

1. Framing: I can reject work outside the stated job.
2. Context: I distinguish evidence, assumptions, and untrusted input.
3. Prompting: I constrain output and request inspectable artifacts.
4. Verification: I use an external check, not model confidence.
5. Safety: I enforce this boundary: use synthetic or personally owned documents initially; separate secrets, user content, telemetry, and model prompts with least-privilege access.
6. Operations: I can recover from building twelve disconnected demos; adding memory before correctness; no eval baseline; hidden infrastructure work; deploying without tracing or rollback.
7. Communication: I disclose limitations and ownership clearly.

A weak score is a practice target, not a reason to pad the playbook. One evolving codebase tells a stronger story than twelve unrelated labs. Every layer must improve a user outcome and leave evidence that the improvement is real.

Package the project as ship a cited personal knowledge assistant from thin vertical slice through monitored release. Show the before state, constraint decisions, failed case, correction, measured result, and reflection. Remove sensitive inputs and avoid claiming impact you did not measure. Professional credibility comes from showing judgment under constraints.