Analyze customer feedback, reviews, or survey comments
Finds themes, sentiment, and priorities in customer feedback, and what to do about them.
The prompt
Role: Act as a UX researcher analysing voice-of-customer feedback at scale.
Context: Feedback sources and volume (reviews, support tickets, survey verbatims, NPS comments, sales notes): [SOURCES_VOLUME]. Time range: [TIME_RANGE]. Product areas to tag against: [PRODUCT_AREAS]. Segments to break down by: [SEGMENTS]. What decision this feeds: [DECISION].
Task: Produce: a coding scheme (themes / sub-themes tied to product areas); a themed summary with, per theme, the frequency, sentiment, an estimate of severity/impact, representative quotes, and the trend over the range; where themes differ by segment; and a prioritised list of recommended actions (fix / investigate / monitor) with the rationale.
Format: Sections: Coding scheme | Themed summary (table) | Segment differences | Recommended actions. ~500 words.
Verification: Give counts, not vague quantifiers ('many'); note where the sample is skewed (e.g. reviews over-represent extremes). Keep quotes verbatim and attributed to a source type.
Validation: Check the top theme against the raw feedback: does the count hold up and is the severity estimate reasonable, not inflated by a few loud voices? Adjust.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Customer Support prompts
What to fill in
- SOURCES_VOLUME
- TIME_RANGE
- PRODUCT_AREAS
- SEGMENTS
- DECISION
How this prompt is built
This prompt follows the RCTFVV structure (Role, Context, Task, Format, Verification, Validation). RCTFVV extends RCTF with two checking steps. Verification asks the model to review its own draft against your requirements; Validation asks it to flag assumptions and gaps you should confirm.
Related prompts
- Build a QA scorecard for support conversationsA rubric to review and coach customer interactions consistently.
- Respond to an angry customer and de-escalateDe-escalates an upset customer, owns the issue, and offers a concrete resolution.
- Improve my customer service operationA plan to improve service quality, speed, and efficiency across channels.
- Handle a warranty callback and decide what is coveredA fair way to assess a customer's warranty claim, decide responsibility, and reply clearly, whether the fix is covered or not.