> 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-1.md).

# Before you begin

Before consuming a Data Product, make sure these four prerequisites are in place.

<table><thead><tr><th width="166.7294921875">Prerequisite</th><th>Why it matters</th></tr></thead><tbody><tr><td>Tenant access</td><td>Determines which Data Products appear in the Hub and which semantic models, outputs, and APIs are available to query. Without access to the right domain or business area, the product cannot be found or reached.</td></tr><tr><td>Roles and permissions</td><td>Control what the consumer can actually see and use inside that Tenant.</td></tr><tr><td>A deployed Data Product</td><td>Provides the governed inputs, models, metrics, quality checks, and connection endpoints the consumer interacts with. If no relevant product is deployed, there is nothing to discover, validate, or consume.</td></tr><tr><td>A DataOS API token</td><td>Authenticates external tools such as Power BI, Tableau, MySQL-compatible SQL clients, Data APIs, and AI clients such as Cursor or Claude Desktop. Generate it before connecting any tool.</td></tr></tbody></table>

## Get Tenant access

Request Tenant access from the DataOS Operator or Tenant Admin for the organization. Include the business or technical goal, the Tenant name if known, and the Data Products or domain needed for the use case.

If the required Tenant is unknown, the DataOS Operator or Tenant Admin can identify the correct Tenant from the requested domain or Data Products.

After access is granted, the Tenant becomes available for discovery and consumption across the Hub, Studio, APIs, and AI clients.

## Required roles and permissions

A user must have data-consumer role assigned in the tenant to be able to access the Hub and consume data products.&#x20;

## Get a DataOS API token

Generate and copy the token before connecting a BI tool, SQL client, API client, SDK, or AI client.

{% stepper %}
{% step %}
Start where tokens are managed. Open Home in DataOS — the Home page shows Products, Workbench, and Resources, along with Generate API tokens under Access developer tools.

![DataOS Home page showing Products, Workbench, Resources, and Generate API tokens under Access developer tools](/files/jMdkhKXZnOzYnl51jTG8)

Open the profile menu from the top-right corner and select API Tokens to reach the page where you create and track your tokens.

![Profile menu open showing My Profile, API Tokens, and Log out options](/files/Pp59TB0JZb0iAFfSNUpS)
{% endstep %}

{% step %}
Create a token scoped to your needs. Select + New, enter a name you will recognize later, and set an expiry in hours or as a date so the token does not outlive its purpose, then select Save.

![Create an API token modal with Name and Expiry fields](/files/E1c2YLMMNsDv8wS1h0xD)
{% endstep %}

{% step %}
Capture the token now — this is your only chance. Copy the value as soon as it appears, because it is shown only once.

![Copy your API token modal showing the token value with a warning that it cannot be viewed again](/files/m4Y5Y3PbIb7eJsFP8phe)
{% endstep %}

{% step %}
Keep the token safe and know where to use it. Store it securely; the API Tokens page confirms the token was created with its name, creation date, and expiry so you can track and revoke it later.

![API Tokens page showing the newly created token with creation and expiration dates](/files/0EsnLzsyli8eip9KlHT4)

Use the token as the password or bearer token depending on the consumption path: MySQL clients use it as the password, BI tools and AI clients use it as a bearer token or API token field.
{% endstep %}
{% endstepper %}


---

# 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-1.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.