Raw feedback is impossible to act on. The 500 verbatim responses you exported from Intercom, App Store, Typeform and Linear bury the actual signal under noise. These 15 prompts cluster, count, label and prioritize feedback into the small set of themes a roadmap can actually answer. Includes specific patterns for support tickets, NPS comments, churn-exit surveys, app reviews, and beta-test transcripts.
Who this is for
PMs and CX leads who own quarterly feedback synthesis, founders reading their own support inbox, research ops teams running large surveys, and growth teams looking for the next experiment angle.
When not to use these prompts
Skip when n is under 30 — at that size, read every response by hand. Skip too when the feedback is highly technical (engineering logs, code review) and needs domain-specific taxonomy that the AI lacks.
Prompt anatomy / structure formula
A feedback-clustering prompt should always carry six elements:
- Role: who the AI plays (senior PM / solo founder / product designer / indie dev / growth lead).
- Context: stage (idea / MVP / growth / scale), team size, traffic or ARR, platform (web / iOS / Android), audience, constraints.
- Goal: one concrete deliverable — one PRD section, one user-story set, one experiment design, one launch post.
- Constraints: timeline (this sprint / this quarter), scope cuts, must-not-break (existing flows, billing, compliance).
- Output format: table, checklist, ticket-ready JSON, or labeled blocks you can paste straight into Linear / Notion / Jira.
- Examples / signal: 1-2 reference docs or competitors you like, plus 1 anti-example you want to avoid.
Best for
- Quarterly support-ticket synthesis
- NPS comment clustering
- Churn / cancel-flow analysis
- Beta-test transcript synthesis
- App / Play Store review batch read
15 copy-ready prompt templates
1. First-pass theme extraction
Start here. Lets the AI propose its own taxonomy before you constrain it.
You are a senior PM clustering raw user feedback. Below are {N} verbatim responses. Group them into 8-12 themes. For each theme: (1) short label (3-5 words), (2) one-sentence description, (3) count of responses, (4) 2 representative verbatim quotes, (5) suggested severity (blocker / major / minor / nice-to-have).
Feedback: {paste}Variables to swap: N, feedback corpus
Optimization: If themes overlap, add: “Merge themes where 60%+ of underlying quotes could fit either. Keep clusters mutually exclusive.”
2. Constrained taxonomy clustering
Use this when you already know the categories you care about.
Cluster the feedback below into these predefined categories: {bug, missing feature, pricing, onboarding, performance, integration, support quality, other}. For each: count, % of total, top 3 verbatim, single recommended action. Anything in "other" exceeding 10% should suggest a new category.
{paste}3. Sentiment + theme matrix
Cluster the feedback below into themes AND label each with sentiment (positive / mixed / negative). Output a matrix: theme × sentiment, with counts. Highlight any theme where the same feature gets equal positive and negative comments — that is where the actual disagreement lives.
{paste}4. Churn-exit reason clustering
Below are {N} cancellation-flow survey responses. Cluster the reasons for leaving into 6-8 categories. For each: count, %, 2 verbatim, whether it is reversible (product fix vs life-circumstance), and one suggested counter-move.
{paste}5. NPS comment clustering by score band
Cluster these NPS comments into themes, but split the output by score band: detractors (0-6), passives (7-8), promoters (9-10). For each band: top 5 themes with counts. Highlight any theme that appears in BOTH detractors and promoters — that is your polarizing feature.
{paste}6. Bug vs feature-request separation
Take this mixed feedback corpus and split it into two stacks: bugs (something broken vs expected behavior) and feature requests (something not built yet). For each stack, cluster into themes with counts. Flag any items where the line is unclear.
{paste}7. Persona-aware clustering
Below is feedback tagged with user persona ({free / paid / enterprise / new / power}). Cluster themes BY persona — same theme can appear in multiple personas. Output: theme × persona matrix with counts. Highlight which themes are concentrated in {paid + power} — those move revenue.
{paste}8. “Jobs-to-be-done” reframing
Re-cluster this feedback using JTBD framing instead of feature categories. Output 5-8 jobs in the form "When X, I want Y, so I can Z." For each: count of underlying feedback, the products / workarounds users currently use for that job, where our product falls short.
{paste}9. Severity + frequency 2x2
For each theme in this clustered feedback, place it on a severity (low/high) × frequency (low/high) 2x2. Output as a table. The high/high quadrant is the next sprint. The high-severity / low-frequency quadrant needs an audit (rare but bad).
{paste themes + counts}10. Quote selection per theme
For each of these themes, pick the 3 most representative verbatim quotes for an internal share-out. Criteria: clarity, emotion, specificity. Exclude any quote with PII (names, emails, account IDs). Tag each quote with persona if known.
Themes + raw quotes: {paste}11. Cross-channel reconciliation
I have 3 sources of feedback for the same quarter: app reviews, support tickets, sales loss reasons. Compare the top 5 themes from each. Output a table: theme × source. Highlight: themes appearing in 3 sources (highest confidence), themes appearing in only 1 (channel-specific noise or hidden signal).
{paste 3 source summaries}12. Action recommendation per theme
For each theme below, propose 1 product action, 1 GTM / messaging action, and 1 thing NOT to do. Each action should be testable in 2 weeks. Mark which action belongs to which team.
{paste themes}13. Quarterly delta report
Compare last quarter's feedback themes to this quarter's. Output: themes that grew, themes that shrank, new themes, retired themes. Hypothesize 1 reason for each major delta. End with the 3 themes worth a deep-dive next quarter.
Last quarter: {paste}
This quarter: {paste}14. Feedback-to-ticket converter
Convert the top 5 themes from this clustering into engineering / design tickets. Each ticket: title (less than 12 words), problem (2 sentences from clustered evidence), proposed scope, success metric, linked verbatim quotes. Output as JSON for Linear / Jira import.15. Hallucination guard pass
Audit this AI-generated clustering against the source feedback. For each theme: confirm the count by spot-checking, flag any verbatim quote that does not appear in source, flag any claimed pattern not supported by at least 3 quotes. Output: confirmed themes vs themes to redo.
Clustering: {paste}
Source: {paste 20 random verbatim}Common mistakes
- Asking for 25 themes when 10 would do — overfitting to noise.
- No counts per theme — without counts, you cannot prioritize.
- Letting AI invent verbatim quotes — always pass the raw text and ask for spot-checking.
- Mixing bugs and feature requests in the same cluster — different actions, different teams.
- Ignoring sentiment — a popular theme split 50/50 positive vs negative is your most controversial issue.
- Re-clustering without comparing to last quarter’s clusters — drift is signal.
- Acting on a theme with under 5 supporting quotes — too small to invest a sprint on.
How to push results further
- Always strip PII before pasting feedback — names, emails, account IDs.
- Run template 15 (hallucination guard) on any clustering before sharing with execs.
- Pair every theme with at least 3 verbatim quotes; one is anecdote.
- Use template 11 (cross-channel) every quarter to spot signal vs channel noise.
- Re-export from your source tools (Intercom, Linear, Typeform) rather than reusing old extracts — themes shift weekly.
- When clusters look “balanced” with similar counts, push back — real signal usually has 2-3 dominant themes.
- Tie every theme to a single owner before the share-out, or nothing moves.
FAQ
- How much feedback can AI cluster at once?: Most models handle 100-500 short responses in one call. Beyond that, batch by week or segment, then re-cluster the summaries.
- How do I trust the AI did not hallucinate?: Use template 15 (hallucination guard) and spot-check 10 random verbatim quotes against source. If 2 are invented, redo.
- Should I share the verbatim with the AI raw?: Yes, but strip PII first. Verbatim language is the highest-value input — paraphrasing loses signal.
- How often should I cluster?: Monthly for active products, quarterly minimum. Drift between cycles is itself a leading indicator.
- What if themes feel too generic?: Add a constraint: every theme label must reference a feature, screen, or workflow — no abstract nouns like “experience” or “quality”.