Run a post-mortem on a churned customer account
A blameless review of why an account churned, with root causes, missed signals, and changes to prevent it next time.
The prompt
Help me run a post-mortem on a customer we lost.
Account details: [PRODUCT, CONTRACT VALUE, TENURE, CHURN DATE]
Stated reason for leaving: [WHAT THEY SAID - exit survey, email, call]
Timeline: [KEY EVENTS - onboarding, usage changes, support issues, stakeholder changes, renewal conversations]
Health signals we had: [HEALTH SCORE HISTORY, usage data, NPS, ticket volume]
What we did to save it: [ACTIONS AND TIMING]
Where they went: [competitor, in-house, no replacement, out of business - if known]
Analyze:
1. Stated reason vs. likely root cause - and whether they differ. Separate controllable causes (onboarding, product fit, service, relationship) from uncontrollable ones (acquisition, budget cut, closure).
2. Timeline of warning signs: when each first appeared and when we noticed it.
3. Decision points where a different action might have changed the outcome.
4. Whether this account should have been sold or onboarded the way it was (fit issues from day one).
5. Lessons in three buckets: CS process, product, and sales/handoff.
6. 3-5 specific changes with owners, and the signal or playbook that would catch this pattern earlier.
7. Whether to plan a win-back attempt, and when.
Keep it blameless: focus on systems and signals, not individuals. Mark gaps in the timeline as [UNKNOWN] rather than guessing.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Thinking & Decisions prompts
What to fill in
- PRODUCT, CONTRACT VALUE, TENURE, CHURN DATE
- WHAT THEY SAID - exit survey, email, call
- HEALTH SCORE HISTORY, usage data, NPS, ticket volume
- ACTIONS AND TIMING
- UNKNOWN
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Get and compare contractor quotes for a home projectA clear scope to send contractors, questions to ask, and a side-by-side comparison to choose the right quote.
- Shortlist and interview wedding venues and vendorsA shortlist plan with the right questions for each vendor type, a comparison table, and contract red flags to check before booking.
- Evaluate a feature request that sales says will close a dealA clear-eyed assessment of a deal-driven request, plus a reply to sales that protects the roadmap and the relationship.
- Build a scorecard to compare the homes I tourA weighted must-have list and a simple scorecard so you can compare homes and neighborhoods objectively after each viewing.