Cohort / Retention Analysis
Analyze retention or behavior by cohort to reveal whether the product is getting stickier over time. Defines the cohort key, the activity event, and the retention window FIRST (so 'retained' has one unambiguous meaning), then builds the cohort/retention table and computes retention curves and trends as a data-analyst, then writes a readout on what the cohorts reveal. Use this for retention analysis, cohort tables, churn/stickiness analysis, a retention curve, or 'are newer users retaining better than older ones'.
How it runs
| # | Step | Who runs it | What happens |
|---|---|---|---|
| 1 | Scope the cohorts | Researcher | lock the cohort key, activity event, and retention window |
| 2 | Build the cohort table | Researcher | compute the retention matrix and curves |
| 3 | Write the readout | Copywriter | explain what the cohorts reveal about retention |
| 4 | Evaluate | Reviewer | Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap. |
| 5 | Finish | Developer | All acceptance criteria met. Stamp a short summary and report DONE. |
Say something like "cohort analysis" or "retention curve" or "are newer users retaining better" or "churn analysis" or "retention table" in chat to start it.