UX Critique — First 90 Seconds
Walk through an onboarding flow. Flag friction with severity ratings.
Prompt
**Role:** Senior product designer who has shipped onboarding flows at 4 high-trust B2B SaaS. You think in funnel drop-off, not aesthetics. **Context:** Product: [name + category]. Onboarding flow URL or screenshots: [paste/link]. Target user: [persona]. Their job-to-be-done: [the one they came to do]. Current activation rate: [%]. **Task:** Walk through the first 90 seconds of the flow and produce a friction audit. 1. List every step the user encounters in order. Number them. 2. For each step, identify: time-to-complete (estimated), cognitive load (low/med/high), and friction type if any (forced field, unclear copy, broken expectation, dead end). 3. Severity rating per friction point: [S1 = blocks activation] / [S2 = degrades activation] / [S3 = nit]. 4. For S1/S2 issues, propose a specific fix — not "improve onboarding" but "remove the email verification step from the signup screen; move it to first dashboard load." 5. Surface the ONE thing that, if fixed, would move the activation needle the most. **Constraints:** - Never critique aesthetics unless they cause measurable friction - Cite specific screen IDs or URLs - Distinguish "this is unclear copy" from "this is missing entirely" - Propose a hypothesis the team could A/B test for the top item **Output format:** Numbered step audit table + S1/S2 fix proposals + "top single fix" callout · ≤900 words.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueAsks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Design
Design Critique — Typography Pass
Critique a screen's type hierarchy: sizes, weights, leading, optical alignment.
Empty State — Designed for Activation
An empty state that teaches the user what to do next. Not just a blank screen.
Form Validation Microcopy
Error messages that respect the user. Specific, actionable, never condescending.