Build a repeatable workflow

Use this topic-specific sequence: scope → vertical slice → ground → evaluate → harden → deploy → monitor. Give each stage one input, one output, and one gate. The first run should be narrow and reversible. Later automation is earned by measured reliability, not by how easy it is to connect tools.

For plan and ship a personal knowledge assistant in staged, testable layers, begin with the job card and sanitized packet. Run the constrained 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.

Save the response beside its prompt and input version. Then apply the quality rubric and demo each milestone against golden tasks, inspect citations, run eval gates, test hostile inputs, review traces, exercise retries, and rehearse rollback. A failed check returns to the smallest responsible stage; do not regenerate everything. If the source was missing, repair context. If the instruction was ambiguous, repair the prompt. If the candidate violates policy, stop and escalate rather than prompt around the policy.

Name an owner for source approval, generation, verification, and release. One person may hold several roles on a small project, but the role changes should remain visible. The reviewer needs the evidence packet, not merely the final artifact.

Define operational states: draft, needs evidence, blocked, approved, released, and rolled back. This vocabulary prevents a plausible draft from being mistaken for an approved result. Attach timeouts, retry limits, and an off switch to any automated stage.

Log the defect category rather than just “bad output.” This chapter's recurring defects are building twelve disconnected demos; adding memory before correctness; no eval baseline; hidden infrastructure work; deploying without tracing or rollback. Track their rate on representative cases. Review false positives and false negatives separately when classification is involved; track factual, continuity, or rights defects when producing media.

The end product is a capstone evidence portfolio with roadmap, architecture decisions, demos, eval reports, risk log, traces, release notes, and retrospective. 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. Periodically rerun a stable set of cases after changing models, prompts, source material, formulas, or settings.

Imagine the independent check fails after release. Identify how to stop distribution, identify affected outputs, restore the last approved version, notify the owner, and preserve enough evidence to learn. A workflow without rollback is only a happy-path demo.