Build something that is not there yet
Build on-time transport performance by lane and day from trip events
- When on-time percent by lane gets recalculated with a different tolerance every time someone asks.
- When chronically late lanes don't surface until a customer complains about a specific shipment.
Build on-time percentage per lane and day from trip pickup and drop-off events, against an explicit tolerance. Covers lane-level on-time performance only; vehicle-day utilization is a separate Recipe with its own grain.
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 `logistics-lane-on-time-performance` at https://getvibedata.ai/cookbook/logistics-lane-on-time-performance Read the Recipe and execute it in the context of the current Intent.
Recipe id logistics-lane-on-time-performance · 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.
- pickup precedes drop-off for every trip in the output
- the on-time tolerance is documented on the model and applied identically across lanes
- a reproduced week's on-time percent matches operations' previously reported figure for that lane
- a lane is defined consistently as an origin-zone to destination-zone pair across the whole output
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Build on-time transport performance by lane and day from trip events. Build on-time percentage per lane and day from trip pickup and drop-off events, against an explicit tolerance. Covers lane-level on-time performance only; vehicle-day utilization is a separate Recipe with its own grain. 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: - pickup precedes drop-off for every trip in the output - the on-time tolerance is documented on the model and applied identically across lanes - a reproduced week's on-time percent matches operations' previously reported figure for that lane - a lane is defined consistently as an origin-zone to destination-zone pair across the whole output 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 lane definition and on-time tolerance.
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.