Skip to content
Vibedata

Build something that is not there yet

Build AML monitoring features at account-day grain

  • When the monitoring vendor wants governed features and the team hand-writes them with no tests behind them.
  • When nobody can say what a feature like structuring indicator actually counts without reading the query.

Build a documented feature table at account-day grain covering velocity, structuring indicators, counterparty novelty, and cross-border and round-amount ratios. Covers the feature computation, not alerting or case disposition.

Area
Transformation
Runs on
  • Microsoft Fabric Lakehouse
  • Microsoft Fabric Warehouse
  • MotherDuck
  • DuckDB
Built with
  • dbt
Industry
Banking
Readiness
SupportedEverything this Recipe composes runs today, without a case that proves this exact shape.
Before you start
needs an agreed novelty window and reporting threshold band

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 `banking-aml-features` at https://getvibedata.ai/cookbook/banking-aml-features Read the Recipe and execute it in the context of the current Intent.

Recipe id banking-aml-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.

  • exactly one row exists per account per day
  • every feature has a written definition attached to the model
  • a reproduced account's features match the value the monitoring team calculated by hand
  • the counterparty-novelty window is applied consistently across the whole table
Recipe promptThe task specification the agent reads. Reference only — it is not what you copy.
Deliver: Build AML monitoring features at account-day grain.

Build a documented feature table at account-day grain covering velocity, structuring indicators, counterparty novelty, and cross-border and round-amount ratios. Covers the feature computation, not alerting or case disposition.

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:
- exactly one row exists per account per day
- every feature has a written definition attached to the model
- a reproduced account's features match the value the monitoring team calculated by hand
- the counterparty-novelty window is applied consistently across the whole table

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 novelty window and reporting threshold band.

How it goes

  1. State the outcome in one sentence, in the language the request arrived in.
  2. Let it profile the inputs the grain, the joins and the measures actually depend on.
  3. Review the design. Disagreeing about grain here costs a sentence; after the model exists it costs a rewrite.
  4. Let it build in an isolated copy, with the tests and the documentation landing beside the model rather than after it.
  5. 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.

Next to this one