退订流的回答是订阅产品里最被低估的数据集。它同时包含给出的理由（通常很礼貌）和理由背后的理由（真实驱动）。下面 15 个 Prompt 聚类退订原因、分离可挽回与必然流失、定位风险峰值的生命周期阶段，把发现转成 save-flow 和产品修复优先级。区别于通用流失分析，这一组专门解析自愿退出的数据。
适合哪些场景
订阅型 PM 和生命周期营销、管 save-flow 的 CX lead、做 cohort 流失研究的增长分析、想知道流失用户真实想法的创始人。
什么时候不建议这样写 Prompt
月流失用户少于 50 不要用——逐条读。只有单选 dropdown 没有自由文本时也别用——需要 free-text 或访谈转录。
Prompt 结构公式
流失原因 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
- 季度退订流综合
- 退场访谈转录聚类
- Save-flow 文案生成
- 可挽回 vs 必然流失分流
- 降级轨迹诊断
15 个可直接复制的 Prompt 模板
1. 退订自由文本聚类
默认。按根本驱动聚类，不按表面回答。
You are a retention analyst. Below are {N} free-text cancel-flow responses for {product}. Cluster into 6-8 root reasons (not surface labels). For each: count, % of churners, 3 representative verbatim, classification (reversible / inevitable / unclear), suggested counter-move.
Responses: {paste}可替换变量： N、responses、product
优化建议： 聚类只是 dropdown 镜像时追加：“Ignore the multiple-choice labels users selected. Cluster only by the free-text explanation.”
2. 可挽回 vs 必然 vs 错配 分桶
From this churn analysis, split reasons into 3 buckets: (1) reversible (we could prevent with product / pricing / support work), (2) inevitable (life event, role change, project ended), (3) misaligned (we should not have sold them in the first place). For each bucket: count, % of churn, recommended action.
Clustering: {paste}3. 生命周期阶段流失图
Below are churned users with tenure (days since signup). Map churn reasons against lifecycle stage: early (0-14d), trial (14-30d), early-paid (30-90d), mature (90d+). Output: stage × reason matrix. Highlight which stage produces the most reversible churn.
Data: {paste}4. 退场访谈综合
Below are 10 exit-interview transcripts (15-30 minutes each). Synthesize: top 5 themes, 3 surprising findings, 2 things multiple users said that contradict our beliefs. For each finding: which transcript supports it, recommended action.
Transcripts: {paste}5. 降级轨迹诊断
Some users downgrade before churning. Analyze the downgrade trail: average days from downgrade to churn, common reasons given at downgrade, whether a save-attempt at downgrade prevents churn. Output: trail timeline + intervention point recommendation.
Data: {paste}6. 理由背后的理由
Users often give polite cancel reasons that hide the real one ("price" can mean "not getting enough value"). For each of these 5 verbatim responses, infer the likely underlying reason. Mark confidence and what additional question would confirm.
Responses: {paste}7. Save-flow 文案生成
For each of these 6 cancel reasons, write 2 save-flow messages: (a) a soft acknowledge + offer (extend trial, pause, talk to founder), (b) a no-pressure exit (thanks + feedback ask). Voice: respectful, never desperate. Less than 60 words each.
Reasons: {paste}8. 按 persona 偏斜
Compare churn reasons across user personas ({free-to-paid, paid-power, paid-occasional, enterprise}). Highlight reasons that skew sharply by persona — those become persona-specific interventions.
Data: {paste}9. 竞品流失提取
From these cancel-flow responses, extract mentions of competitors ("switching to X", "X has better Y"). For each: which competitor, what feature they cited, frequency. End with the top 3 competitor-driven losses and what we would need to close that gap.
Responses: {paste}10. 价格型流失诊断
For users citing pricing as cancel reason, diagnose: is it absolute price (too expensive), perceived value (not enough for the price), pricing structure (wrong tier), or budget cycle (price unchanged, budget shrank)? Recommend a different counter-move per sub-cause.
Responses: {paste}11. 季度退订理由变化
Compare last quarter's churn reasons to this quarter's. Output: reasons that grew, reasons that shrank, new reasons, vanished reasons. Hypothesize why each shifted. End with 3 themes worth investigating next quarter.
Q-1: {paste}
Q0: {paste}12. 自愿 vs 被动流失分流
Below is our churn dataset including both voluntary cancels and involuntary churn (failed payments, expired cards). Separate them. For involuntary churn: analyze recovery rate by retry strategy. For voluntary: cluster reasons. Output two parallel reports.
Data: {paste}13. 不同干预的挽回率
We tried 4 save-flow interventions ({pause, discount, talk-to-founder, content-only}) over the last 90 days. Measure: save rate per intervention, durability of saves (still active at 60 days), cost per save. Recommend which interventions to keep, modify, kill.
Data: {paste}14. 退款请求模式审计
Below are refund-request reasons over 90 days. Cluster by root cause. Highlight any pattern where refund requests cluster within 7 days of signup — that signals an onboarding or messaging problem upstream.
Requests: {paste}15. 预测性流失信号
From this dataset of churned vs retained users, identify 5 leading indicators of churn in the 14 days before cancellation. For each signal: how to detect it programmatically, what intervention to trigger, expected save rate. Mark which signals are causal vs correlative.
Data: {paste}容易踩的坑
- 按 dropdown 标签聚而不是 free-text。
- 把”太贵”当价格问题——它通常意味着”价值不足”。
- 忽略被动流失（信用卡失败）——通常占 20-30%，最便宜可修。
- Save-flow offer 没测 60 天后的留存——短期挽回可能更糟。
- 只听一段情绪化退场访谈就动作，没看集群。
- 没识别流失集中的生命周期阶段——早期与后期需要不同干预。
- 把可挽回和必然流失混在一起——后者浪费精力。
优化技巧
- 退订流必须含 free-text；只有 dropdown 数据几乎无用。
- 按根因聚，不按表面标签聚。
- 每条理由先打可挽回 / 必然 / 错配标签，再考虑干预力度。
- 挽回的耐久度看 60-90 天；短期挽回可能比放手更糟。
- 定量退订数据配每季度 5-10 次退场访谈——数字 + 故事。
- 建一条”我们不挽回”政策——追必然流失会耗光团队。
- 每季度看理由 delta——漂移意味着产品、市场或定价转变。
FAQ
- 它和通用流失分析有何不同？: 通用版做 cohort、曲线、指标。这一组专门解析自愿退出的文本数据并产出可执行原因。
- 需要多少条退订文本？: 聚类至少 50 条 free-text。低于 50 逐条读找规律。
- save-flow 给折扣可以吗？: 只当退订理由明确是价格时。给价值问题打折会训练用户期待折扣并侵蚀收入。
- 怎么分可挽回 vs 必然？: 用模板 2。可挽回：产品缺口、定价、onboarding。必然：人生事件、岗位变动、项目结束。
- 没退订但不再用的怎么办？: 是另一题——属于参与度 / 留存范畴，不是退订理由。用留存实验那组 Prompt。