原始反馈无法直接拍动作。从 Intercom、App Store、Typeform、Linear 导出的 500 条原话把信号埋在噪音下。下面 15 个 Prompt 把反馈聚类、计数、打标签、排序，变成 roadmap 能回答的主题集。覆盖支持工单、NPS 评论、流失退订、App 评论、beta 转录。
适合哪些场景
负责季度反馈整合的 PM 和 CX lead、自己读 inbox 的创始人、做大调研的 research ops、寻找下一个实验的增长团队。
什么时候不建议这样写 Prompt
n 小于 30 不要用——直接手读。高度专业（工程日志、code review）反馈也别用——AI 没领域分类法。
Prompt 结构公式
反馈聚类 Prompt 一定带这六个要素：
- 角色：让 AI 扮演谁（资深 PM / 独立创始人 / 产品设计师 / 独立开发者 / 增长负责人）。
- 上下文：阶段（想法 / MVP / 增长 / 规模化）、团队规模、流量或 ARR、平台（web / iOS / Android）、受众、限制。
- 目标：一个具体交付物——一段 PRD、一组用户故事、一个实验设计、一篇上线公告。
- 限制：时间线（本 sprint / 本季度）、要砍的范围、不能动的东西（现有流程、计费、合规）。
- 输出格式：表格、清单、可贴 ticket 的 JSON、或带标签的段落，能直接粘到 Linear / Notion / Jira。
- 示例 / 信号：1-2 份你欣赏的参考或竞品、加 1 个想避开的反例。
这套 Prompt 适合用在哪
- 季度支持工单综合
- NPS 评论聚类
- 流失 / 退订分析
- Beta 转录综合
- App / Play Store 评论批量阅读
15 个可直接复制的 Prompt 模板
1. 首轮主题提取
从这里开始。先让 AI 自提出分类法。
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}可替换变量： N, feedback corpus
优化建议： 主题重叠时追加：“Merge themes where 60%+ of underlying quotes could fit either. Keep clusters mutually exclusive.”
2. 约束分类法
已经知道你在乎哪些类别时用。
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. 情绪 + 主题矩阵
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. 流失原因聚类
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 按分段聚类
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 功能请求分流
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. 按 persona 聚类
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. JTBD 重构
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. 严重度 × 频率 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. 每主题挑代表原话
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. 跨渠道交叉核对
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. 每主题对应动作
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. 季度变化对比
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. 反馈转 ticket
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. 幻觉守门轮
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}容易踩的坑
- 让 AI 出 25 个主题，其实 10 个够——过拟合噪音。
- 不给每个主题计数——没数就没法排优先级。
- 让 AI 编造原话——一定要给原文并让它对照核查。
- Bug 和功能请求混到同一聚类——动作和团队都不同。
- 忽视情绪——同一功能 50/50 正负面，是真正的争议点。
- 没和上季度做对比——漂移本身就是信号。
- 少于 5 条原话就开搞——太薄，不值一个 sprint。
优化技巧
- 粘贴前先去掉 PII：姓名、邮箱、账户 ID。
- 给高管前必跑模板 15（幻觉守门）。
- 每主题至少配 3 条原话；一条只是 anecdote。
- 每季度跑一次模板 11（跨渠道）来区分信号与渠道噪音。
- 从 Intercom / Linear / Typeform 重导，不要复用旧导出——主题每周都在变。
- 聚类结果计数都很均时要怀疑——真实信号通常 2-3 个主题占主导。
- 分享前每主题指定一个 owner，否则没有动作。
FAQ
- AI 一次能聚多少条？: 多数模型一次 100-500 条短回复没问题。再多就分批，先按周或 segment 聚，再聚 summary。
- 怎么知道 AI 没在编？: 跑模板 15，并随机抽 10 条原话回源比对。若 2 条是编的，重做。
- 原话直接喂给 AI 吗？: 是，但先去 PII。原话是最高价值输入，转述会丢信号。
- 多久聚一次？: 活跃产品每月，最少每季度。周期之间的漂移本身是领先指标。
- 主题太泛怎么办？: 加约束：主题 label 必须引用一个功能、屏幕或工作流——禁用”体验""质量”这种抽象词。
相关阅读
标签: #Prompt #产品创业 #User Story