Use prompt moves that transfer

First, orient the model with the real audience and decision. Second, ground it in supplied sources. Third, constrain scope, format, and forbidden actions. Fourth, inspect by asking for assumptions, unsupported claims, or tests. Applied to this topic, those moves support make a multi-constraint laptop recommendation auditable without requesting hidden reasoning, not vague content generation.

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.

The likely useful output is: A criteria table, explicit unknowns, a short recommendation tied to three inspectable facts, and a verification checklist. Follow with a critic pass, not a request to “improve it”:

Audit the draft against the original contract. Return a table:
criterion | pass/fail | exact evidence | smallest correction.
Do not introduce new facts. List unresolved questions separately.

This second prompt changes the mode from creation to inspection. For alternatives, request deliberately different options and specify the axis of difference. For revision, name one defect and freeze everything else. For extraction, require a schema and define unknown/null behavior. For decisions, ask for criteria, evidence, assumptions, and sensitivity—not hidden private reasoning.

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.

Do not confuse fluent explanations with evidence. 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. The prompt is successful only when the resulting artifact survives an external check.

Watch for equating longer rationale with truth; post-hoc justification; invented specifications; hidden weighting; arithmetic that cannot be reproduced. If the answer is too broad, shrink the deliverable. If it invents, tighten “use only” boundaries and require source labels. If formatting drifts, provide a short valid example and validate mechanically. If every option sounds alike, define meaningful axes. If revision damages good sections, quote the exact passage to preserve.

Keep prompt versions with short notes: what changed, why, and what happened. That creates transferable knowledge. Copying a “perfect prompt” without its data, risk level, and reviewer rarely does.