Build something that is not there yet
Build a thirty-day readmission cohort with explicit exclusions
- When every department applies a different exclusion list before reporting the readmission rate.
- When the window-edge cases behave differently each time the cohort is rebuilt.
Build a thirty-day readmission cohort from encounter data, with the index-admission rule and every exclusion expressed as tested logic. Covers the cohort and its rate by service line and facility, not case-level chart review.
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 `healthcare-readmission-cohort` at https://getvibedata.ai/cookbook/healthcare-readmission-cohort Read the Recipe and execute it in the context of the current Intent.
Recipe id healthcare-readmission-cohort · 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.
- each window-edge case, such as exactly thirty days or a same-day transfer, is covered by its own test
- each exclusion, such as a planned readmission or an in-hospital death, is applied by tested logic, not a manual filter
- a reproduced month's rate matches the quality team's previously reported figure for that service line
- no encounter is counted as its own index admission and readmission at once
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Build a thirty-day readmission cohort with explicit exclusions. Build a thirty-day readmission cohort from encounter data, with the index-admission rule and every exclusion expressed as tested logic. Covers the cohort and its rate by service line and facility, not case-level chart review. 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: - each window-edge case, such as exactly thirty days or a same-day transfer, is covered by its own test - each exclusion, such as a planned readmission or an in-hospital death, is applied by tested logic, not a manual filter - a reproduced month's rate matches the quality team's previously reported figure for that service line - no encounter is counted as its own index admission and readmission at once 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 index-admission definition and exclusion list.
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.