> 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/v1/discover/overview.md).

# Overview

Discovery is the first step of the consumer journey. It helps you find the right Data Product, perspective, or metric for your goal before you spend time reviewing details, querying outputs, or connecting tools.

Discovery happens in the Hub, where you search, sort, filter, and preview the products available in your tenant. You can also switch the search scope to **Perspectives** (saved, governed query views) or **Metrics** (computed business measures), so you can pick up a ready-made answer instead of building one.

## What discovery answers

Start from identifying a product name, a domain, a tag, or just an intent. By the end you can answer:

<table><thead><tr><th width="448.0406494140625">Question</th><th>Why it matters</th></tr></thead><tbody><tr><td>Is there a product for this use case?</td><td>Confirms whether a governed product already exists</td></tr><tr><td>Does the name, description, or tag match my intent?</td><td>Narrows the list to relevant options</td></tr><tr><td>Is there a metric that already tracks the measure I need?</td><td>Lets you use a ready-made value without a query</td></tr><tr><td>Is there a perspective that already answers my question?</td><td>Lets you reuse a saved, governed query</td></tr><tr><td>Who owns it?</td><td>Identifies the team to contact</td></tr><tr><td>Is it worth reviewing in detail?</td><td>Decides whether to continue to Evaluate</td></tr></tbody></table>

## Two paths

* [**Search the Hub**](/consume/v1/discover/search-the-hub.md): when you know part of what you need, browse, search, filter, and preview to land on the right product.
* [**Discover in natural language**](/consume/v1/consume-with-ai/discover-in-natural-language.md): when you only know your intent, describe it to a connected AI client and let DataOS surface matching products. This is discovery's AI mode.

When a product looks promising, open it and move to [Evaluate](/consume/v1/evaluate/overview.md) to decide whether to trust 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 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/v1/discover/overview.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.