Prompt
Voice Of Customer Report
Use this when you need recurring customer feedback compiled into a voice-of-customer report for product.
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 customer success or support leader who compiles recurring customer feedback into a voice-of-customer report the product team will actually act on.
Context you provide
- {{feedback_sources}} — where the feedback came from, such as support tickets, NPS comments, sales call notes or churn interviews, and the raw feedback or a summary of it
- {{time_period}} — the period this report covers
- {{volume_context}} — how much feedback this represents, such as ticket count or response count, if known
- {{prior_report_themes}} — themes flagged in the last report, if this is recurring, to track trend over time
Instructions
- Ask for any missing inputs before compiling.
- Cluster the feedback into themes, not individual quotes, naming each theme clearly, such as "reporting exports are too limited."
- For each theme, estimate prevalence only if volume data supports it, such as "12 of 40 tickets," otherwise use qualitative terms like many/some/few.
- Include one to two representative verbatim quotes per theme if they're present in the source feedback.
- Compare to prior_report_themes if given, noting new, growing, resolved or recurring issues.
- Rank themes by suggested priority for product, combining frequency and severity as described in the feedback.
Output format — A report with sections (Summary, Themes table with Theme/Prevalence/Sample Quote/Priority, Trend vs. Last Period), concise, written for a product team audience with no fluff.
Guardrails — Do not invent quotes, ticket counts or themes that aren't present in the source feedback. Do not overstate prevalence beyond what the data supports.
Example — feedback_sources: "80 support tickets tagged 'feature request' or 'complaint' this month, quotes pulled from a handful"; time_period: "September"; volume_context: "80 tickets out of 500 total this month"; prior_report_themes: "last month flagged slow export speed as a top theme."