Start with the job to be done

The working assignment is to make a multi-constraint laptop recommendation auditable without requesting hidden reasoning for a college buyer who must verify seller claims. That sentence is narrower than “use Chain-of-thought prompting.” It identifies a deliverable and a reviewer. Write a definition of done with three layers: the output must satisfy the audience's need; factual or functional claims must be traceable; and a named person must own the final decision. 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.

Start by separating tasks. The model may draft, classify, transform, compare, or suggest. It may not silently approve, publish, grade, deploy, cite, or consent on someone's behalf. For this assignment the authoritative material is candidate options, authoritative specifications, weighted criteria, constraints, missing facts, calculation method, and required output format. Anything absent from those inputs is either an explicit assumption or an unanswered question.

Use this prompt as a realistic starting contract:

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.

Notice what the prompt does: it states the setting, limits the output, names forbidden behavior, and requests evidence that can be reviewed. It does not ask the model to “make it amazing.” If a constraint matters, make it testable. Replace “be accurate” with a source boundary, formula check, test command, rights ledger, or approval step.

A useful response would look like this: A criteria table, explicit unknowns, a short recommendation tied to three inspectable facts, and a verification checklist. That description is intentionally observable. “Looks good” is not acceptance. The operator 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. Keep the source material beside the draft so review means comparison, not memory.

Run the work through decompose → gather → calculate → answer → verify. Stop when an authoritative input is missing, a high-risk claim lacks evidence, private material cannot be safely removed, or the proposed action exceeds the permission granted. Escalation is successful workflow behavior, not model failure.

Common framing mistakes are equating longer rationale with truth; post-hoc justification; invented specifications; hidden weighting; arithmetic that cannot be reproduced. Prevent them by writing a one-paragraph job card: user, decision, deliverable, source of truth, constraints, reviewer, and stop condition. This card becomes the anchor for every later prompt.