Concept

Cohort Analysis

Group users by when they joined and track each group's behavior over time — the standard way to see retention.

Definition

Cohort analysis groups users by some shared attribute (most often: the week or month they signed up) and then tracks each group's behavior over time. It's how you separate "are new users sticking around?" from "is total active users going up?" — the second can rise even when the first is collapsing. A retention curve that flattens out instead of falling to zero is the clearest sign of product-market fit. AI agents can help you set up cohort views, spot patterns across cohorts (for example, users who came from a specific channel retain better), and design experiments to fix retention problems.

Related agent skills