Prompt
You are a design lead writing a concise decision document to help a design review go smoothly. Audience and what they care about: {{audience}}. The decision: {{decision}}. The evidence and alternatives I have: {{evidence_and_options}}.

Write a one-page rationale with these sections:
- Problem: the user problem in one or two sentences, in plain business language.
- Options considered: each alternative with its main tradeoff.
- Recommendation: the chosen direction and the top three reasons, tied to user evidence and business goals.
- Tradeoffs and risks: what we are giving up and how we would mitigate it.
- What we would measure: the signal that tells us this worked.

Constraints: translate design and UX jargon into language a product manager, an engineer, and an executive would each understand. Use ONLY the evidence I provided — do not invent research findings, usage metrics, user quotes, or competitor facts. Any claim I did not give you must be written as [NEEDS DATA], not stated as fact. Keep it to roughly one page and lead with the recommendation for skim-readers.

Fill in your details and the prompt updates live — then copy.

What you get back (excerpt)

**Recommendation:** Move verification to after the first save, not before signup. **Problem:** New users abandon at the verification wall before seeing any value (drop-off figure is [NEEDS DATA] — I have not confirmed the exact number). **Why:** (1) Users experience the core flow first; (2) fewer steps before the "aha" moment; (3) aligns with the Q3 activation goal you set. **Tradeoff:** A window of unverified accounts — mitigate with a verify-before-share gate. **We'd measure:** activation rate and share of accounts verified within 24 hours.

The full workflow

  1. Gather the real evidence and alternatives before prompting — the doc is only as good as its inputs.
  2. Run the prompt with your audience clearly described.
  3. Fill or cut every [NEEDS DATA] flag — never present an unverified number as fact.
  4. Rewrite the recommendation in your own voice, then circulate it before the review.

Watch out for

Never let AI invent research findings, metrics, or user quotes to strengthen your case — fabricated evidence is a serious trust and ethics failure, and it collapses the moment someone checks.

Keep unreleased strategy, roadmap, and confidential metrics out of consumer AI tools; share only what your NDA and company policy allow.

Where this comes from

Every use case on this site is grounded in real reports from working ux designers — not invented by us.

More AI use cases for ux designers

← All 6 use cases: How UX Designers Use AI