Prompt
You are a principal product designer running a divergent ideation session with me. Design problem: {{design_problem}}. Users and context of use: {{user_and_context}}. Hard constraints (platform, must-have functions, limits): {{constraints}}.

Generate five structurally different concepts — different interaction models and information structures, not visual reskins of one idea. For each concept give:
- The core idea in one sentence.
- The interaction model (how the user moves through it), in words plus a simple ASCII wireframe.
- Who it fits best and in what situation.
- The main usability risk, named against a real principle (for example recognition over recall, error prevention, Hick's law).
- The cheapest way to test whether it works.

Include at least one deliberately unconventional option to stretch the range. Constraints: respect every hard constraint I listed. Do not claim any concept is "the best" — leave that judgment to me. Do not cite statistics, studies, or competitor features you cannot name and verify; if you invoke a pattern, name the design principle behind it rather than inventing evidence. Treat these as raw starting points, not finished designs.

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

What you get back (excerpt)

**Concept 3 — Command-bar first (unconventional).** Core idea: skip the dashboard; users type what they want. [ search or type a command... ] recent: Re-run "Q2 churn" Export CSV Fits power users doing repeat tasks. Main risk: recognition over recall — new users don't know what to type; mitigate with visible suggestions. Cheapest test: a clickable prototype seeded with three commands, 5 users. **Concept 1 — Guided history list.** Lower ceiling, higher floor; best for occasional users. Risk: gets long fast — needs search and grouping...

The full workflow

  1. Frame the problem and list every real constraint before generating.
  2. Generate the five concepts and drop any that break a hard constraint.
  3. Sketch the two strongest yourself to make them concrete.
  4. Validate with real users — usability principles suggest, but only testing decides.

Watch out for

AI ideation regresses toward the average of its training data — common patterns, and often the accessibility debt baked into them. Use the output as raw material and validate with real users, not as a finished direction.

Do not feed unreleased product strategy or NDA-covered material into consumer AI tools to brainstorm; treat confidential designs the way you would confidential documents.

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