Write a prompt you can actually test
A useful marketing prompt defines the job, supplies reliable facts and makes the result easy to check.

Six things to specify
Goal: Name the work to produce.
Audience and context: Explain who will read it and where.
Approved sources: Separate evidence from instructions.
Constraints: Set limits and prohibited claims.
Output format: Specify sections and lengths.
Review criteria: Define what passes and fails.

Try it with LumaDesk
Fictional exercise; the reference below was written for this guide.
A — Approved: shared editorial calendar, approval tracking; French and English. No pricing or performance figures.
B — Older, unapproved draft: German support; 30% time saving.

Reusable prompt
Using A and B above, write homepage copy for LumaDesk aimed at independent agencies. Only A authorizes product claims; use B solely to flag conflicts. Produce three headlines of at most 12 words each, one 60–80-word paragraph and a list of missing facts. Do not invent pricing, German support or time savings. Mark missing information unknown. Before returning the copy, check every claim against A and verify the lengths.

Reference outcome
The copy can mention the calendar, approvals and two supported languages. Pricing and measured results remain unknown; B’s conflicting claims are flagged, not adopted.

Pass or fail?
1. Every product claim is supported by A.
2. Missing facts are marked unknown.
3. Headlines and paragraph respect the limits.
4. B’s conflicting claims are not silently merged.

Improve one thing at a time
Fix one recurring issue, then replay the same three cases: complete sources, missing pricing and a conflicting old draft.

OpenAI · Prompt engineering: https://developers.openai.com/api/docs/guides/prompt-engineering
Anthropic · Prompt engineering: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview
OpenAI · Evaluation best practices: https://developers.openai.com/api/docs/guides/evaluation-best-practices