Build something that is not there yet
Compute historical customer lifetime value with margin
- When the acquisition-payback conversation lacks an LTV figure anyone trusts.
- When lifetime value is quoted from a spreadsheet that nobody can trace back to actual orders and costs.
Compute historical lifetime value per customer with margin, from orders or subscriptions and a cost source, and roll it up cumulatively by acquisition cohort and tenure month. Delivers governed historical inputs; predictive or modeled LTV is a separate outcome.
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-historical-ltv` at https://getvibedata.ai/cookbook/customer-historical-ltv Read the Recipe and execute it in the context of the current Intent.
Recipe id customer-historical-ltv · 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.
- cumulative LTV by cohort ties back to total revenue for that cohort
- a previously reported cohort's LTV is reproduced from the same inputs
- refunds are applied under the stated rule and do not appear twice
- every customer in the source orders appears in exactly one acquisition cohort
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Compute historical customer lifetime value with margin. Compute historical lifetime value per customer with margin, from orders or subscriptions and a cost source, and roll it up cumulatively by acquisition cohort and tenure month. Delivers governed historical inputs; predictive or modeled LTV is a separate outcome. 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: - cumulative LTV by cohort ties back to total revenue for that cohort - a previously reported cohort's LTV is reproduced from the same inputs - refunds are applied under the stated rule and do not appear twice - every customer in the source orders appears in exactly one acquisition cohort 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.
- Needs an agreed margin and cost source.
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.