Mastery: your playbook

Your mastery artifact is a reasoning audit card containing decomposition, evidence, concise rationale, calculations, assumptions, and independent checks. It should let a competent colleague repeat make a multi-constraint laptop recommendation auditable without requesting hidden reasoning without inheriting unstated assumptions. Include the job card, source requirements, prompt contract, examples, rubric, privacy boundary, escalation rule, and recovery steps.

Use decompose → gather → calculate → answer → verify as the spine. For every stage, name the input, action, output, owner, check, and stop condition. Include the concrete prompt:

Compare three laptops for college using price, measured battery life, weight, and required-software compatibility. First output a short comparison plan and evidence table. Then recommend one in under 150 words with three deciding facts. Finally list unknowns to verify on seller pages. Give concise rationale, not private hidden reasoning.

Then include a specimen response: A criteria table, explicit unknowns, a short recommendation tied to three inspectable facts, and a verification checklist. Label it as an example, not a guaranteed result. Attach proof from the independent check: you must open authoritative product pages, recalculate weighted scores, check units and model variants, test software requirements, and see whether the recommendation changes under reasonable weights.

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: do not include account details, private purchase history, or personally sensitive constraints unless they are necessary and safe to share.
6. Operations: I can recover from equating longer rationale with truth; post-hoc justification; invented specifications; hidden weighting; arithmetic that cannot be reproduced.
7. Communication: I disclose limitations and ownership clearly.

A weak score is a practice target, not a reason to pad the playbook. Ask for visible work products—plans, formulas, evidence tables, assumptions, and checks. A model's private reasoning is neither required nor a substitute for proof.

Package the project as build an auditable three-option decision brief with evidence table, formula, sensitivity test, recommendation, and open questions. 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.

Transfer the method to choosing among three event venues. Supply verified capacity, rental fee, transit distance, and accessibility facts; leave catering cost unknown. Require a comparison plan, evidence table, explicit arithmetic, concise rationale, and unknowns list. Recalculate totals independently and vary the weighting between cost and accessibility. If the recommendation changes, report the threshold instead of presenting one option as universally best. Do not request hidden reasoning or reward a longer explanation. The assessable evidence is the table, formula, assumptions, sensitivity result, and links to authoritative venue information.