> 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/overview.md).

# Evaluate a Data Product

Review a Data Product's context, assets, and trust signals before you query or consume it.

Evaluating is the second step of the consumer journey. You found a product that looks relevant; now you check whether it is actually fit for what you need. This step answers what is in the product, who owns it, how it is built, whether quality checks pass, and whether anyone is keeping it alive.

Open a product from the Hub: select its card, then **More details** on the context card. The product page is your evaluation surface.

![Data Product page header with metadata, Jump to links, and the Data Quality Test panel](https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-a9a149f2bfec8c9aacc9aa8012bdc8dbee71c201%2Fdp-overview-header.png?alt=media)

## Read the header first

The header gives you a fast read before you open any section: the name, a plain-language description, and metadata for **Gateway**, **Version**, **Domain**, **Type**, **Repository**, **Issue tracker**, **References**, and **Members**. The **Data Quality Test** panel on the right shows the share of rules passed and the status of each quality dimension (Accuracy, Completeness, Conformity, Consistency, Coverage, Timeliness, Uniqueness, Validity); select **Know more** for the full breakdown. Use the header to decide in seconds whether the product is worth a closer look.

**Jump to** links take you straight to **Home**, **Assets**, **Data quality**, **Runs**, **Metrics**, **Perspectives**, **Apps**, and **Activate**.

The actions at the top right:

* **Star:** mark the product as a favorite, so it appears under **Favorites** in the Hub.
* **Request change:** tell the owners that something is missing (a field, dimension, or historical data you need) or something is incorrect (a value, count, or refresh that doesn't look right). Describe the change in up to 500 characters and select **Submit**. The request is visible on the product page, and anyone with access can view it and add their name to it.
* **Explore:** query the product in [Studio](https://v2.dataos.info/consume/evaluate/query-in-studio.md). The arrow next to it picks a query mode directly. If the product requires a data-sharing agreement, Studio first shows a **Review agreement** page with the agreement text; select **Accept and continue** to proceed.

## Where to look

Three live signals sit in the stats bar: **freshness** (time since last refresh, the expected cadence, and how many models are healthy), **queries** (total run against the product), and **followers**. Below that, the sections each answer a specific question:

<table><thead><tr><th width="189.23724365234375">Section</th><th>What it tells you</th></tr></thead><tbody><tr><td>Overview</td><td>A single view of how data flows from inputs through models and semantic models to metrics and connection paths. Grasp scope and shape without opening every asset.</td></tr><tr><td>Purpose</td><td>Appears only when the product defines it.</td></tr><tr><td>Trust &#x26; Freshness</td><td>The signals for whether you can rely on it. See <a href="https://v2.dataos.info/consume/evaluate/trust-and-freshness.md">Trust and freshness</a>.</td></tr><tr><td>Activation</td><td>The supported consumption paths: Connect via MCP, Plug into BI tools, Build on the APIs, and Query in your DB Client.</td></tr><tr><td>Adoption</td><td>Usage (active users, new users, repeat %), performance (queries, query time), and the perspectives and apps built on it.</td></tr><tr><td>Members</td><td>Who is responsible and how to reach them.</td></tr></tbody></table>

The Overview section also has an **Is it a right fit for me?** panel with *Good for*, *Not good for*, and *Caveats*, drawn from the product's own [`usage.yaml`](https://v2.dataos.info/build/productize/init-and-configuration).

Open **Metrics** from the **Jump to** links and click a metric card to open its side drawer. If a policy masks or filters the metric's data, the drawer shows a **Protected** banner; select it to expand the humanized row filters and see exactly what's restricted for you. Trend arrows on a card reflect the actual period-over-period change and use the standard positive color for a positive trend, so read them as-is rather than a rough estimate.

## Evaluate in depth

From here, dig into whichever signal matters for your decision:

* [Explore assets](https://v2.dataos.info/consume/evaluate/assets.md): inputs, outputs, semantic models, metrics, and how data flows between them.
* [Query in Studio](https://v2.dataos.info/consume/evaluate/query-in-studio.md): query the governed semantic models and validate the data yourself.
* [Trust and freshness](https://v2.dataos.info/consume/evaluate/trust-and-freshness.md): quality checks, freshness, and AI-readiness.
* [Track activity](https://v2.dataos.info/consume/evaluate/track-activity.md): run history, version history, and recent changes.
* [Understand in natural language](https://v2.dataos.info/consume/consume-with-ai/understand-in-natural-language.md): have an AI client summarize health, lineage, ownership, and limitations. This is evaluation's AI mode.

## You are done when

You know what the product provides, you trust the signals it shows, and you can decide whether to [activate](https://v2.dataos.info/consume/activate/overview.md) it.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://v2.dataos.info/consume/evaluate/overview.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
