> 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/consume-with-ai/discover-in-natural-language.md).

# Discover in natural language

Find the right Data Product by asking about topics, domains, metrics, or ownership in natural language.

Once you have connected an [AI client](https://v2.dataos.info/consume/consume-with-ai/connect-a-client.md) or [agentic framework](https://v2.dataos.info/consume/consume-with-ai/connect-an-agentic-framework.md) to Data Product MCP, you find products and learn what is in them by asking. This is the AI mode of [Discover](https://v2.dataos.info/consume/discover/overview.md): use it when you do not yet know which product you need, or want to see what exists for a topic, domain, or metric.

## What you can ask

These are starting points, not a fixed list. Phrase the question however reads naturally.

<table><thead><tr><th width="245.29376220703125">Question type</th><th>Example</th></tr></thead><tbody><tr><td>Explore the catalog</td><td><code>What Data Products are available?</code></td></tr><tr><td>Find by domain</td><td><code>What Data Products are in the finance domain?</code></td></tr><tr><td>Find by metric</td><td><code>Which Data Products have revenue metrics?</code></td></tr><tr><td>Find by owner</td><td><code>What Data Products does dana.lee own?</code></td></tr><tr><td>Find by topic</td><td><code>Show me all Data Products related to customer orders.</code></td></tr><tr><td>Find by personally identifiable information (PII) status</td><td><code>Which Data Products contain PII tables?</code></td></tr></tbody></table>

## What you get back

Enough to pick the right product without leaving the chat: a list of matches with name, domain, owner, lifecycle stage, and a link to open each one. Table searches also include the table type, column count, engine, and PII status, so you can judge fit and sensitivity before you commit. Results are always scoped to what your token is authorized to see.

Responses are non-deterministic and depend on your catalog and permissions, so wording and order vary from one run to another.

## Next

Once you have a product worth using, ask the assistant to summarize its health, lineage, ownership, and limitations. See [Understand in natural language](https://v2.dataos.info/consume/consume-with-ai/understand-in-natural-language.md).


---

# 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/consume-with-ai/discover-in-natural-language.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.
