> 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/get-started/readme.md).

# Consumer journey

Consuming a Data Product happens in three stages: **discover** the right one, **evaluate** whether you can trust it, then **activate** it where you actually work: a report, an application, an API, or an AI agent. You discover and evaluate a product once; after that you activate it as often as you like without re-validating.

AI runs through all three as a mode, not a separate track. At each stage you can either use the DataOS interface or describe what you need in natural language to a connected AI client. The "or ask AI" paths below point to that mode.

## Discover

Learn how to find a Data Product, perspective, or metric that matches a business, analytical, operational, or technical use.

* **In the Hub:** from the DataOS home page, select **Products** to open the Hub. It lists every available product as a card; search, filter, and sort to land on the right one. See [Search the Hub](/consume/discover/search-the-hub.md).
* **Or ask AI:** connect an AI client to the Data Product Model Context Protocol (MCP) server and find products by describing what you need. See [Discover in natural language](/consume/consume-with-ai/discover-in-natural-language.md).

## Evaluate

Learn how to confirm that a product is relevant, trustworthy, and fit for its intended use.

* **Explore the assets:** see what the product is made of before you commit, its inputs, models, semantic models, and metrics, and how data flows between them. See [Explore assets](/consume/evaluate/assets.md).
* **Check trust and freshness:** review quality checks, freshness, and AI-readiness so you know what the product is good for. See [Trust and freshness](/consume/evaluate/trust-and-freshness.md).
* **Look at recent activity:** review run history, version history, and recent changes. See [Track activity](/consume/evaluate/track-activity.md).
* **Query in Studio:** query the governed semantic models directly, pick dimensions and measures, run, and validate. See [Query in Studio](/consume/evaluate/query-in-studio.md).
* **Or ask AI:** have an AI client summarize health, lineage, ownership, and limitations, and establish trust through conversation. See [Understand in natural language](/consume/consume-with-ai/understand-in-natural-language.md).

## Activate

Learn how to consume the data product through BI tools, database clients, APIs, or AI workflows. Once you discover and trust it, use it where you work without re-validating it each time.

<table><thead><tr><th width="175.52691650390625">Path</th><th>Use it when</th></tr></thead><tbody><tr><td><a href="/pages/Zp6H5YAiKzkjYf6A8j7Q">BI tools</a></td><td>Your deliverable is a report or dashboard in Power BI or Tableau</td></tr><tr><td><a href="/pages/LyBO1RyM3EvKbz3VR6eE">APIs</a></td><td>An application or service needs governed data programmatically</td></tr><tr><td><a href="/pages/cZPmdhcP8sSFX0VOwX9H">Database clients</a></td><td>You want to query from a desktop SQL client</td></tr><tr><td><a href="/pages/Iv7IrhZxYMLqhTFHWRF2">Consume with AI</a></td><td>You want AI clients or agents to query within governance</td></tr></tbody></table>

New here? Start with [Before you begin](/consume/get-started/before-you-begin.md) to get tenant access and an [API token](https://v2.dataos.info/references/key-concepts/api-tokens), then go to [Discover](/consume/discover/overview.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 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/get-started/readme.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.