Audit intermediate Works with: Any AI

User Interview Notes Quality Review

Rubric scoring Has example

Check notes for bias and missed insights.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Review the quality of my user interview notes and what I concluded from them. Research goal: [RESEARCH_GOAL]. Interview guide used: [INTERVIEW_GUIDE]. Notes from [NUMBER_OF_INTERVIEWS] interviews: [PASTE_NOTES]. My conclusions: [MY_CONCLUSIONS].

Score each dimension from 1 to 5 with quotes from the notes:
1. Questions asked were open and non-leading (identify any leading questions).
2. Notes capture what people did, not only what they said they would do.
3. Direct quotes are separated from my interpretations.
4. Stories and specifics (last time it happened) instead of generalities.
5. Variety of participants relative to the target users; missing groups.
6. Evidence for each conclusion: the number of participants supporting it, with the quote.
7. Contradictions and surprises recorded, not smoothed over.
8. Confirmation bias check: did I look for evidence against my hypothesis?
9. Actionable insights linked to decisions.

Provide a table of my conclusions with Evidence strength (strong, moderate, anecdotal, unsupported), the participants who support it, and a counter-example. List the three conclusions I should soften or drop, and five better follow-up questions for the next round. Do not add insights that are not in the notes.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Scores: leading questions 2/5 ("Don't you find the dashboard confusing?" in interview 3), behavior vs opinion 3/5, quotes separated from interpretation 2/5, participant variety 2/5 (all five are admins; no end users).
Conclusion check
Conclusion | Evidence | Strength
"Users want a mobile app" | 2 of 5 mentioned phones; both asked directly | Weak, led by questions
"Setup takes too long" | 4 of 5, with stories ("I gave up on Friday") | Strong
Soften or drop: the mobile app conclusion. Better follow-up questions: "Tell me about the last time you needed this away from your desk." "What did you do instead?"

• interviews
• rigor