> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/evaluate/trust-and-freshness.md).

# Trust and freshness

Trust and freshness tells you whether a product can be relied on, across three signals: data quality, freshness, and AI-readiness. Check it before querying, reporting, integrating, or building on the product.

Open it from the product overview: click **Quality** in the Quick access bar, or **View all quality rules** / **View full run history** in the Trust and freshness section. The page has a **Summary** tab and a **Details** tab.

## Summary

The Summary consolidates all three signals so you can decide without opening every rule.

**Data quality** shows the share of rules passing as one gauge, the number of dimensions needing attention, and a per-dimension breakdown across **Validity**, **Uniqueness**, and **Completeness**, each with a passed-out-of-total count. The **Data quality trend** chart plots dimension scores over time, so you can judge whether quality is holding or slipping rather than reading a single snapshot.

**Data freshness** shows time since the last run, run duration, and a trend chart of recent runs (green for success, red for failure). An **Issues detected** label warns when recent refreshes failed. Click **View full run history** to open [Track activity](/consume/evaluate/track-activity.md).

**AI-readiness** tells you whether you can safely point an AI agent or MCP-aware tool at the product. Tier A means production-ready: connect with confidence. Lower tiers mean gaps, and the checklist shows what is missing (MCP server, validated prompts, rich descriptions, semantic layer).

## Details

When the Summary raises a concern, the Details tab pinpoints which checks are responsible. A coverage summary at the top shows how many dimensions, models, and columns are backed by rules, so you can spot what is unverified. The quality rules table lists one check per row, with the column it protects, the rule in plain language, its dimension and model, a pass or fail status, and a heatmap of the last 5 runs that shows whether a check is stable or flaky.

Two controls make this fast:

* **Group** by **Models** or **Dimensions** to see which model or dimension carries the most issues (each group shows an issue badge).
* Switch between **With rules** and **Without rules**. *Without rules* lists columns and models that have no checks assigned, which is how you find coverage gaps.

Use the column filters on **Dimension** and **Status**, and the search field, to narrow to a specific failing check or column.

## Questions this answers

| Question                                          | Where to look                       |
| ------------------------------------------------- | ----------------------------------- |
| Are quality checks passing overall?               | Summary: quality gauge              |
| Which dimensions have issues?                     | Summary: dimension breakdown        |
| Is the data recent, and did the last run succeed? | Summary: data freshness             |
| Is this product ready for AI use?                 | Summary: AI-readiness               |
| Which specific rules are failing?                 | Details: rules table, filter Status |
| Which models or columns have no rules?            | Details: Without rules              |

When the signals check out, you can [activate](/consume/activate/overview.md) the product with confidence. When they do not, review [recent activity](/consume/evaluate/track-activity.md) or contact the owner.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://v2.dataos.info/consume/evaluate/trust-and-freshness.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.