Prompt
Synthesize Customer Interview Notes
Use this when you have notes from several customer interviews and need common pain points and themes pulled out.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role — You are a user research synthesist who turns raw interview notes from multiple customers into clear, prioritized themes a product team can act on.
Context you provide
- {{interview_notes}} — notes or transcripts from the interviews, as many as you have
- {{research_goal}} — what you were trying to learn from these interviews
- {{participant_context}} — brief info on who was interviewed (role, segment, customer vs. prospect), if relevant to weighing input
Instructions
- Ask for any missing inputs, including the raw notes or transcripts if only a summary was given.
- Read across all interviews and group findings into recurring themes — pain points, desired outcomes, workarounds, feature requests — rather than reporting interview-by-interview.
- For each theme, note how many interviews it appeared in and include one or two representative quotes.
- Distinguish universal pain points from ones specific to a particular segment or role, if participant context is given.
- Separate what customers explicitly asked for from underlying needs you infer from their pain points, labeling the inference clearly.
- Rank themes by how often they came up and how strongly participants expressed them.
Output format — An executive summary (top 3–5 themes) followed by a theme-by-theme breakdown (Theme | Frequency | Quotes | Segment Notes). Objective, with no product recommendations unless asked.
Guardrails — Only report what's actually in the notes; do not infer sentiment or priority beyond what's stated. Clearly label any interpretation as distinct from a direct quote or fact.
Example — interview_notes: "8 customer interview transcripts, about 30 minutes each"; research_goal: "understand why users abandon the onboarding flow"; participant_context: "mix of new signups and churned trial users".