# Fresh: 14 of 17 tools check it by rule, 1 leave it to a person

CHECKLIST, CONDITION 5 OF 10, read 13 Nov 2026

**The short answer.** The asset was updated within the freshness window that the use expects. 14 of 17 ranked tools check it by rule, 1 relies on a person and 2 show none found on 13 Nov 2026. For a write-back agent it is required; for a metric agent it is required.

- **The test:** The asset was updated within the freshness window that the use expects.
- **Why it matters:** An agent answers as if the data is current. A stale table produces an answer that is wrong and looks right.
- **How to check it:** Compare the last successful load time with the expected schedule, using dbt source freshness or the catalog. Check that the window is written down.
- **What failing looks like:** The nightly load failed on Monday, and on Wednesday the agent reports Tuesday sales as zero.

## What each use case needs

| Use case | Need | Why |
| --- | --- | --- |
| Metric agent | required | Metric questions are usually about now, so a stale source gives a wrong answer. |
| Coding agent | not needed | A coding agent edits code and does not depend on how recent the rows are. |
| Write-back agent | required | Writing from stale data overwrites newer values in the target system. |

## 14 tools check fresh by rule

- [OvalEdge](/platforms/ovaledge/), rank 1, 64.5.
- [DataHub](/platforms/datahub/), rank 3, 61.0.
- [Atlan](/platforms/atlan/), rank 5, 59.0.
- [Secoda](/platforms/secoda/), rank 6, 58.5.
- [Databricks Unity Catalog](/platforms/databricks/), rank 7, 58.0.
- [dbt](/platforms/dbt/), rank 8, 52.5.
- [Alation](/platforms/alation/), rank 9, 50.5.
- [Ataccama](/platforms/ataccama/), rank 10, 49.5.
- [Qlik Talend Cloud](/platforms/qlik-talend/), rank 11, 46.5.
- [Monte Carlo](/platforms/monte-carlo/), rank 12, 46.0.
- [Snowflake Horizon](/platforms/snowflake/), rank 13, 45.5.
- [Precisely](/platforms/precisely/), rank 14, 43.0.
- [Actian](/platforms/actian/), rank 15, 39.0.
- [Informatica](/platforms/informatica/), rank 16, 36.0.

## 1 tools leave fresh to a person

- [OpenMetadata](/platforms/openmetadata/), rank 4, 61.0.

## 2 tools show none found on 13 Nov 2026

- [Euno](/platforms/euno/), rank 2, 62.5.
- [Collibra](/platforms/collibra/), rank 17, 36.0.

## What the sources say

- Monte Carlo, [Redefining AI-ready data](https://montecarlo.ai/blog-redefining-ai-ready-data): "Timeliness: Content is fresh and appropriately timestamped to avoid outdated or misleading information."
- Atlan, [AI readiness assessment for data estates](https://atlan.com/know/ai-agent/data-for-ai/ai-readiness-assessment/): "Context freshness belongs in this dimension, not in a separate hygiene exercise, because an answer computed from a stale source is wrong in a way no quality test catches."
- dbt Labs, [5 dbt MCP server patterns that work in production](https://www.getdbt.com/blog/5-dbt-mcp-server-patterns-that-work-in-production): "Source freshness fails, the agent skips the dependent models and pages the on-call engineer instead of running on stale data."

## Other conditions

- [Named owner](/checklist/owner/)
- [Documented](/checklist/documented/)
- [Certified](/checklist/certified/)
- [Quality tests pass](/checklist/quality/)
- [Sensitivity classified](/checklist/sensitivity/)
- [Lineage known](/checklist/lineage/)
- [Active use](/checklist/usage/)
- [Metric defined](/checklist/metric_definition/)
- [Access policy allows AI use](/checklist/access/)

## Sources

- Monte Carlo: Redefining AI-ready data: https://montecarlo.ai/blog-redefining-ai-ready-data (read 13 Nov 2026)
- Atlan: AI readiness assessment for data estates: https://atlan.com/know/ai-agent/data-for-ai/ai-readiness-assessment/ (read 13 Nov 2026)
- dbt Labs: 5 dbt MCP server patterns that work in production: https://www.getdbt.com/blog/5-dbt-mcp-server-patterns-that-work-in-production (read 13 Nov 2026)

Last reviewed 13 Nov 2026. Canonical: https://aireadydatacheck.com/checklist/fresh/
