🎯 Design
UX Research Prompt: Usability Notes to Findings, Next Tests
Turn your own usability session notes and task results into a task table, affinity themes, ranked findings, answers to your research questions, and next tests.
0Reviews
Prompt
Act as a UX researcher who synthesizes moderated usability sessions from the team's own notes, counts what participants actually did, quotes only words that appear in the notes, and ties every finding to a decision the team has to make. Inputs: - Product area and the flow tested: [ProductArea] - Study setup (method, number of sessions, participant IDs, who they are): [StudySetup] - Research questions: [ResearchQuestions] - Task results per participant: [TaskResults] - Session notes per participant, with any exact quotes in quotation marks: [ParticipantNotes] - Severity scale the team uses: [SeverityScale] - Decisions the team needs to make: [TeamDecisions] Generate: 1. Task table: each task with successes out of participants, the success rate, and which participant IDs failed. 2. Affinity themes: group the observations into themes, each with the participant IDs and the count. 3. Findings ranked by SeverityScale: the finding, the severity and why, the evidence by participant ID, and at most one verbatim quote per finding copied exactly from the notes. 4. Answers to each research question, with how many participants support the answer and a confidence note for a small sample. 5. Recommendations: one per finding, linked to the TeamDecisions item it answers. 6. Next tests: what the usability notes cannot answer yet and the smallest study that would. 7. Readout summary: five bullets the team can paste into a slide. Rules: - Use participant IDs only; never add names or personal details. - Never invent quotes, counts, or behavior that are not in the notes; mark anything uncertain as a question.
Instructions
Paste your own session notes with participant IDs, your task results, and the decisions your team needs. Works on ChatGPT, Claude, and Gemini. Check every quote against your notes before sharing the readout, and remove anything that could identify a participant. Get informed consent from every participant before recording or sharing their sessions. Use participant IDs only; never paste names, emails, faces, or other personal data.
Generated Output
This image was generated using the prompt above.
Examples
Example Input
ProductArea: city bike-share app, buying a day pass and unlocking a bike StudySetup: 5 moderated remote usability sessions, P1 to P5, all first-time riders ResearchQuestions: RQ1 Can first-time riders buy a day pass without help? RQ2 What stops them at unlock? TaskResults: T1 find the nearest station: 5 of 5 succeeded. T2 buy a day pass: 2 of 5 succeeded without help (P2, P4). T3 unlock a bike: 4 of 5 succeeded (P3 failed). ParticipantNotes: P1: looked for passes under Account first; stopped at the payment screen and said "I'm not putting my card in without knowing the cost"; needed a hint to continue. P2: bought the day pass in under a minute; unlocked on the first scan. P3: picked single ride by mistake and said "Single ride and day pass look the same"; at unlock, held the phone too far from the code and gave up after three tries. P4: bought the day pass; asked "Does the day pass start now or when I unlock?" P5: scrolled the map looking for passes before opening the menu; stopped at the payment screen and said "Why do I need to add a card before I see the price?" SeverityScale: High = stops a key task for 2 or more participants; Medium = stops one participant or confuses 2 or more; Low = slows one participant TeamDecisions: D1 move passes onto the map screen or not; D2 show the price before asking for card details or not
Example Output
1. TASK TABLE T1 Find the nearest station: 5 of 5 (100%). No failures. T2 Buy a day pass without help: 2 of 5 (40%). Failed: P1, P3, P5. T3 Unlock a bike: 4 of 5 (80%). Failed: P3. 2. AFFINITY THEMES A. Price hidden until card entry: P1, P5 (2) B. Passes hard to find: P1 (Account), P5 (map) (2) C. Pass options unclear: P3 (picked single ride), P4 (start time question) (2) D. Unlock scan distance: P3 (1) No issues observed: P2. 3. FINDINGS (ranked) F1 High: Riders will not enter a card before they see the price. It stopped T2 for P1 and P5, which meets High (2 or more). Quote (P5): "Why do I need to add a card before I see the price?" F2 Medium: Single ride and day pass are hard to tell apart. It stopped one participant (P3 bought the wrong option) and confused P4 about when the pass starts. Quote (P3): "Single ride and day pass look the same" F3 Medium: Passes are not where riders look first. P1 checked Account and P5 scrolled the map before finding the menu; it confused 2 but stopped neither on its own. F4 Medium: The unlock scan fails if the phone is too far from the code. It stopped one participant (P3 gave up after three tries). 4. RESEARCH QUESTIONS RQ1: Mostly no. 2 of 5 bought a day pass without help. The three failures came from F1 (P1, P5) and F2 (P3). Confidence: directional only with 5 sessions, but the price issue repeated in 2 of 3 failures. RQ2: Scan distance, seen once (P3). 4 of 5 unlocked. Confidence: low, one participant; needs more sessions. 5. RECOMMENDATIONS F1 -> D2: Yes, show the price on each pass before card details. F2 -> (new): Label each option with what it covers and when it starts, since P4 asked exactly that. F3 -> D1: Test a passes entry on the map screen; P5 looked there first, P1 looked under Account, so the evidence is split. F4 -> (new): Add a distance hint on the unlock screen and retest. 6. NEXT TESTS - Does showing the price first fix T2? Run 5 more sessions on a prototype with prices visible. - Map screen vs menu for passes: a quick first-click test with both versions. - Unlock distance: 5 sessions focused on T3 only, since one failure is not enough to size it. 7. READOUT SUMMARY - 2 of 5 first-time riders bought a day pass without help. - Top issue (High): price is hidden until card entry; it stopped P1 and P5. - Single ride and day pass look alike; P3 bought the wrong one. - Riders looked for passes on the map (P5) and under Account (P1). - Decision asks: D2 show prices first (yes); D1 test passes on the map screen.