Build something that is not there yet
Reconcile inventory positions across warehouse, ERP, and physical counts
- When on-hand quantity disagrees between the warehouse system and the ERP and nobody notices until the annual count.
- When shrink only shows up once a year at physical count instead of being tracked as it happens.
Build a variance mart across warehouse, ERP, and physical-count positions at SKU, location, and day grain, with a mechanism classified on every variance and a shrink metric. Covers reconciliation and variance classification, not adjusting the systems of record.
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 `ops-inventory-reconciliation` at https://getvibedata.ai/cookbook/ops-inventory-reconciliation Read the Recipe and execute it in the context of the current Intent.
Recipe id ops-inventory-reconciliation · 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.
- every variance carries exactly one classification (in-transit, unposted receipt, unit-of-measure, count error)
- positions reconcile within the agreed threshold for a day with no open count
- an in-transit item is excluded from the variance until the receipt posts
- no position is adjusted by the reconciliation; variances are reported, not corrected
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Reconcile inventory positions across warehouse, ERP, and physical counts. Build a variance mart across warehouse, ERP, and physical-count positions at SKU, location, and day grain, with a mechanism classified on every variance and a shrink metric. Covers reconciliation and variance classification, not adjusting the systems of record. 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: - every variance carries exactly one classification (in-transit, unposted receipt, unit-of-measure, count error) - positions reconcile within the agreed threshold for a day with no open count - an in-transit item is excluded from the variance until the receipt posts - no position is adjusted by the reconciliation; variances are reported, not corrected 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
- dlt 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
- the grain the requester expects, where the request leaves it open to more than one reading
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 and dlt in the project, or the intent to add it.
- Needs unit-of-measure conversions and the system of record named up front.
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.