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 develop an original campaign key visual from a rights-cleared creative brief, not vague content generation.

Create three concept directions for a neighborhood night-market poster. Goal: communicate handmade food and evening community. Medium: bold paper-cut collage; palette: indigo, coral, cream; leave top third clear for approved copy. No logos, readable generated text, named living-artist imitation, copyrighted characters, or identifiable people.

The likely useful output is: Three distinct, art-directable concepts described by composition, focal point, palette, texture, and intended audience response. 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: Three distinct, art-directable concepts described by composition, focal point, palette, texture, and intended audience response. That description is intentionally observable. “Looks good” is not acceptance. The operator must compare against the brief, inspect hands/faces/text, check brand fit and accessibility, run a reverse-image similarity check when appropriate, and confirm asset licenses. Keep the source material beside the draft so review means comparison, not memory.

Do not confuse fluent explanations with evidence. AI can expand options, but art direction decides what deserves refinement. Keep typography and factual copy under deterministic human control, and document provenance. The prompt is successful only when the resulting artifact survives an external check.

Watch for style-name imitation; generic mood words; accidental trademarks; generated gibberish text; endless variation without selection criteria; hidden reference rights. 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.