Build a repeatable workflow

Use this topic-specific sequence: inventory → scan roles → choose experiment → build → interview → decide. 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 choose and run a two-week AI career experiment instead of guessing a forever title, begin with the job card and sanitized packet. Run the constrained prompt:

I enjoy explaining hard ideas, interviewing people, and editing. Skills: classroom teaching, spreadsheets, basic research. Constraint: four hours weekly and no career break. Suggest three role-family experiments. For each: transferable evidence, one gap, a two-week portfolio artifact, and one professional to learn from. Do not predict salary or hiring probability without current sources.

Save the response beside its prompt and input version. Then apply the quality rubric and collect five current job descriptions per path, count repeated requirements, interview a practitioner, inspect current labor sources, and evaluate whether the work itself fits. 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 chasing trendy titles; fabricated salary claims; treating course completion as evidence; ignoring domain expertise; building projects no target role values. 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 career experiment portfolio with job-description matrix, skill evidence map, project, practitioner notes, and next-decision memo. Titles change faster than durable work. Optimize for evidence that you can perform a useful task, explain trade-offs, and learn from feedback. 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.