TextIntermediate

Cohort retention analysis in plain language

Viktor Submitted by Viktor Added 17 days ago
Here's my signup and activity data: {{describe columns or paste sample}}.

1. Build monthly signup cohorts and show retention by month-since-signup as a triangle table. State clearly whether you're measuring any-activity, key-action, or revenue retention, and which is most meaningful here.
2. Identify where the curve flattens — or say plainly if it doesn't, and what that means.
3. Compare cohorts: which improved, which degraded, and separate real product improvement from composition change (different acquisition mix, different definition).
4. Segment retention by the one dimension that discriminates most, and show it.
5. Find the early action that best correlates with month-3 retention. Then argue against your own finding: what confounds it, and what would test causality.
6. Give the two things this analysis says we should do, and the one thing it explicitly does not support.

Flag any cohort too small or too recent to interpret.

How to use it

Step 5's self-rebuttal is essential — 'users who did X retain better' is the most over-actioned correlation in product analytics.

Compatible popular AI tools

These tools are mapped to this prompt based on their capabilities.

People who liked this prompt

8 community likes