App / Product analytics and activation
Build a product retention cohort dashboard
Build a retention cohort App from qualifying product events, with weekly rates, cohort sizes, segment filters and clear incomplete period labels.
Product manager · Product analyst
Bring this question into Chat
Your starting prompt.
Build one App using [governed event Data] to compare weekly retention by signup cohort. Define retained activity as [qualifying event] rather than any visit. Show cohort sizes, retained counts and rates, with filters for [segment] and [plan]. Separate incomplete periods from completed periods and let reviewers inspect the underlying aggregate calculations without exposing user identifiers by default.
Copy this starting point, then replace the placeholders with your own inputs.
Method and review
Keep the assumptions visible.
Agree on event definitions, identity rules and cohort windows. Check instrumentation coverage before comparing activation, retention or engagement.
For this task, check
Changing the qualifying activity event changes the meaning of retention.
This starting prompt has no published worked example yet. Begin with a small sample and check the calculations before relying on the result.
Before you begin
- Bring exports you are allowed to upload, or data your Workspace can already query.
- Choose the reporting period and agree what each record represents.
- Select the data your App can query before building its views.
Build one App from data you have permission to query. Review its definitions and calculations with your team.
Take the next step
Make it your investigation.
Copy the prompt above, create or open your Workspace, and paste it into Chat. Add the inputs you have permission to use and adapt the assumptions with your agent.
Start exploringYour prompt is carried by copy and paste. Signing up does not submit it or start this work automatically.
Or start with your own agent
The setup prompt includes this public task. Your agent will help you connect when needed and use the access you approve.