> For the complete documentation index, see [llms.txt](https://docs.mediarithmics.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mediarithmics.io/collaboration/plan-and-integrate/setup-clean-rooms.md).

# Understand clean room concepts

Understand the Bunker, Clean Room Template, and Clean Room layers, and the privacy guarantees behind them, before you configure anything.

## Your goal

Understand the pieces a Data Clean Room partnership is made of, and the privacy guarantees they come with, before you configure your environment.

## Expected outcome

Clarity on where your data will be stored, how a partnership is structured, and what privacy guarantees apply to every result you or your partner will see.

## Understand the pieces, in this order

{% stepper %}
{% step %}

### Where your data is stored

Every dataset you bring into the module lives in an encrypted **Bunker**.

[Bunkers](/collaboration/plan-and-integrate/setup-clean-rooms/bunkers.md)
{% endstep %}

{% step %}

### How a partnership is structured

A **Collaborative App** scopes what kind of collaboration is possible; your organisation's **Clean Room Template** configures it; a **Clean Room** is the actual space where you and a partner collaborate.

[Clean Rooms](/collaboration/plan-and-integrate/setup-clean-rooms/clean-rooms.md)
{% endstep %}

{% step %}

### What privacy guarantees you get

Every aggregated result you or your partner see is protected by differential privacy, a minimum threshold, and rounding.

[Security and privacy](/collaboration/plan-and-integrate/setup-clean-rooms/security-and-privacy.md)
{% endstep %}
{% endstepper %}

Once these are clear, the hands-on setup - requesting your Bunker, configuring a Clean Room Template, creating your first Clean Room, and sharing datasets - is covered in [Manage your clean room templates](/collaboration/prepare-your-environment/manage-your-clean-room-templates.md) and the rest of the `Prepare your environment` group.

## In this section

<table data-view="cards" data-search="false"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Bunkers</strong></td><td>The encrypted location that hosts your datasets.</td><td><a href="/collaboration/plan-and-integrate/setup-clean-rooms/bunkers.md">Bunkers</a></td></tr><tr><td><strong>Clean Rooms</strong></td><td>The Collaborative App, Clean Room Template, and Clean Room layers, and who collaborates in each.</td><td><a href="/collaboration/plan-and-integrate/setup-clean-rooms/clean-rooms.md">Clean Rooms</a></td></tr><tr><td><strong>Security and privacy</strong></td><td>Differential privacy, the privacy budget, minimum threshold, and rounding.</td><td><a href="/collaboration/plan-and-integrate/setup-clean-rooms/security-and-privacy.md">Security and privacy</a></td></tr></tbody></table>


---

# 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://docs.mediarithmics.io/collaboration/plan-and-integrate/setup-clean-rooms.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.