churn-prevention

# churn-prevention ## When to use - Net retention dropped and the team cannot name *which* of the four churn causes is dominant — defence-spending is uniform when it should be cause-specific. - A health score exists but does not predict — it tracks usage but misses relationship and fit signals — and CS plays are running on bad triggers. - A board ask names *"are we losing customers we should have kept, or customers who never fit?"* — the answer requires the four-way classification, not a single number. Do NOT use to fix days 0–30 onboarding (route to `onboarding-design`), drive upsell or expansion (route to `expansion-playbook`), or build product-led retention loops (route to `retention-loops`). ## Cognition cluster - **Mental model 30 — Inversion.** Do not ask *"how do we keep this account?"* — ask *"name the reason this account will leave."* The inversion forces a cause; the cause picks the move. See [`docs/contracts/mental-models.md`](../../../docs/contracts/mental-models.md) § 30. - **Mental model 16 — Leading vs. lagging indicators.** Cancellation is lagging; usage-decay, relationship-decay, and fit-mismatch signals are leading. A health score built on lagging signals can only confirm churn after the cancel request lands. See `mental-models.md` § 16. - **Mental model 3 — Pareto (80/20).** ~20 % of accounts carry ~80 % of revenue risk. Uniform health-monitoring across the book is theatre; weighted monitoring is reasoning. See `mental-models.md` § ...