CHECKLIST, CONDITION 3 OF 10, read 13 Nov 2026
Certified: 7 of 17 tools check it by rule, 7 leave it to a person
- The test
- The asset carries a certified, endorsed or verified status from someone with the authority to give it.
- Why it matters
- A certificate tells the agent which of several similar assets to trust. Without it the agent has no way to tell the vetted table from a scratch copy.
- How to check it
- Look for a certified, verified or endorsed badge in the catalog and see who set it and when. Confirm the status is not Draft or Deprecated.
- What failing looks like
- Three tables hold revenue, none is certified, and the agent picks the one that sorts first.
What each use case needs
| Use case | Need | Why |
|---|---|---|
| Metric agent | required | A metric answer should come only from assets a person has vouched for. |
| Coding agent | recommended | A coding agent can work on uncertified models, since the change is reviewed in a pull request anyway. |
| Write-back agent | required | An agent should only write to or from assets that have been approved for that use. |
7 tools check certified by rule
- OvalEdge, rank 1, 64.5.
- Euno, rank 2, 62.5.
- OpenMetadata, rank 4, 61.0.
- Atlan, rank 5, 59.0.
- Secoda, rank 6, 58.5.
- Databricks Unity Catalog, rank 7, 58.0.
- Ataccama, rank 10, 49.5.
7 tools leave certified to a person
- DataHub, rank 3, 61.0.
- Alation, rank 9, 50.5.
- Qlik Talend Cloud, rank 11, 46.5.
- Snowflake Horizon, rank 13, 45.5.
- Precisely, rank 14, 43.0.
- Informatica, rank 16, 36.0.
- Collibra, rank 17, 36.0.
3 tools show none found on 13 Nov 2026
- dbt, rank 8, 52.5.
- Monte Carlo, rank 12, 46.0.
- Actian, rank 15, 39.0.
What the sources say
- Monte Carlo, Redefining AI-ready data: "datasets have been validated for quality standards."
- Atlan, AI-ready data for talk-to-data: "People set certificates (Atlan docs) such as Verified, Draft or Deprecated, and asset owners (Atlan docs) are the primary contact for questions about status and quality."
- dbt Labs, AWS and the dbt Semantic Layer for AI agent revenue accuracy: "it resolves a business question against certified metric definitions using tools like list_metrics , get_dimensions , and query_metrics"
Other conditions
Sources
- Monte Carlo: Redefining AI-ready data, read 13 Nov 2026
- Atlan: AI-ready data for talk-to-data, read 13 Nov 2026
- dbt Labs: AWS and the dbt Semantic Layer for AI agent revenue accuracy, read 13 Nov 2026
Last reviewed 13 Nov 2026.