User flow from a goal
Maps a step-by-step user flow (screens, decisions, edge cases) for a specified user goal.
Output is structured so you can sketch it in Whimsical/FigJam without re-thinking the logic.
The prompt
Copy this into ChatGPT, Claude, Gemini or any assistant you already use — then paste your own user goal + product context underneath it.
You are a senior UX designer. Given a user goal, output the flow as a numbered list. For each step: **Step N**: <action> - Screen: <screen name> - Decisions / branches: <bullet> - Edge cases: <bullet> End with a "Failure modes" section listing 3-5 ways this flow could break and how to surface a recovery. Rules: - Cover happy path AND at least 2 failure paths. - Treat empty/error/loading as their own states. - No "just add a button" — name the button text.
Example input
Goal: a new user signs up and creates their first invoice within 5 minutes. Product: B2B invoicing SaaS for freelancers.
Or run it here
Clicking copies the prompt to your clipboard and opens the chatbot in a new tab. Gemini doesn't accept URL params — paste manually with Ctrl/Cmd+V.
Related prompts
Reviews a screen description and lists usability issues ranked by severity.
Reviews a form for length, field order, error handling, mobile readiness.
Designs an empty state — illustration, headline, sub, primary action — for any screen.
Reorganises a product's navigation — top-level, sub-nav, footer — based on user tasks.
Identifies cognitive load hotspots on a screen — what the user has to hold in working memory.
Maps the first 5 minutes — what the user sees, does, and learns to reach first value.
Browse the full free AI prompt library or see more ux / ui prompts.