Module 7 · Track B: Validate & Govern

7.1 · Validate with golden datasets

Prompt

Use these golden datasets and validation cases to check the metrics. Where a metric is ambiguous, reconcile it to the governed definition and add a golden-query test that pins the expected value.

You’ll see: accuracy checked against known-correct outputs — and a pinned test that will alert on drift.

7.2 · Govern with access policies

Prompt

Apply these access policies to the ontology: restrict sensitive surfaces to the right roles (fail closed), apply row-level filters by scope, and limit restricted data to authorized roles. Show the access logic in the .tql.

You’ll see: governance expressed in the model — fail-closed access rules, reviewable like any other file. (Module 9 takes this further with full personas.)

✅ Checkpoint

At least one metric has a golden-query test pinning its expected value
Sensitive surfaces fail closed, and you can point to the access logic in the .tql

Track B: Build from Documents Track B: The N+1 Document

​7.1 · Validate with golden datasets

​7.2 · Govern with access policies

​✅ Checkpoint

7.1 · Validate with golden datasets

7.2 · Govern with access policies

✅ Checkpoint