Build something that is not there yet
Build retention cohorts and a churn feature table
- When "what's our churn rate" gets three different answers depending on who is asked.
- When a churn model was trained once in a notebook and nobody can regenerate the features it used.
Build retention cohorts from a stated cohort event and a churn feature table at the customer-month grain, with the churn definition set as configuration. Delivers the features and the cohort triangle; training or scoring a churn model is out of scope.
Sample This Recipe has not been materialized in the Cookbook repository yet. Its trigger, description, prompt, agent guidance and acceptance conditions, and the explanation below, are prototype drafts. Its name, job, area and readiness come from the reconciled Cookbook seed snapshot. Readiness is a separate question from this one: it says whether the capability exists, not whether the writing has been reviewed.
Use this Recipe
Use the VibeData Recipe `customer-retention-churn-features` at https://getvibedata.ai/cookbook/customer-retention-churn-features Read the Recipe and execute it in the context of the current Intent.
Recipe id customer-retention-churn-features · Not yet materialized in the Cookbook repository, so the pointer addresses this page.
Verified by
What has to be observably true before this Recipe is finished.
- the retention triangle is monotonic within each cohort
- the feature table has exactly one row per customer per month
- changing the churn definition in configuration changes the churned flag without a code change elsewhere
- a cohort's retention rate reproduces a previously reported figure
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Build retention cohorts and a churn feature table. Build retention cohorts from a stated cohort event and a churn feature table at the customer-month grain, with the churn definition set as configuration. Delivers the features and the cohort triangle; training or scoring a churn model is out of scope. Execute inside the current Intent. Its Domain, repository, platform, environment and attached sources are the context for this work — read them rather than asking for them. The work is done when: - the retention triangle is monotonic within each cohort - the feature table has exactly one row per customer per month - changing the churn definition in configuration changes the churned flag without a code change elsewhere - a cohort's retention rate reproduces a previously reported figure Report the evidence for each condition above with the result. A condition you cannot meet is something to say, not something to work around.
Agent guidanceHow the agent approaches the work, and what it will not do.
Profile the inputs the grain, joins and measures actually depend on before proposing a model. Put the design up for review — grain first — then build in an isolated copy with tests and documentation landing beside the model rather than after it.
Composes
- dbt model authoring and layering
- dbt in the project
- isolated-copy execution and gate verification
Asks first
Semantic decisions the Intent cannot supply. Never context Studio already holds.
- which Fabric target this work lands on, when the Domain carries both a Lakehouse and a Warehouse
Guardrails
- Build in an isolated copy. Production is read, never written.
What you need
- Microsoft Fabric Lakehouse, Microsoft Fabric Warehouse, MotherDuck, or DuckDB.
- A dbt project you can build, and read access to the models it starts from.
- dbt in the project, or the intent to add it.
How it goes
- State the outcome in one sentence, in the language the request arrived in.
- Let it profile the inputs the grain, the joins and the measures actually depend on.
- Review the design. Disagreeing about grain here costs a sentence; after the model exists it costs a rewrite.
- Let it build in an isolated copy, with the tests and the documentation landing beside the model rather than after it.
- Read the acceptance conditions against the run.
What you end up with
The deliverable, in your own repository, as transformation work a reviewer who knows the project reads as native to it. Alongside it, the evidence for every one of the acceptance conditions above — which is the part that is still there in three weeks when somebody asks.