> For the complete documentation index, see [llms.txt](https://docs.aidi.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aidi.ai/mosaic/get-started/installation-steps.md).

# Installation Steps

Follow these steps after you've completed the [Prerequisites](/mosaic/get-started/prerequisites.md). The flow is: subscribe on AppSource, activate your tenant on the Vizlake landing page, configure Power BI, and invite your team.

{% stepper %}
{% step %}
**Subscribe via Microsoft AppSource**

1. Open the **Mosaic** listing on [Microsoft AppSource](https://appsource.microsoft.com/)
2. Click **Get it now** and choose **Mosaic Standard** or **Mosaic Premium**
3. Complete the purchase under your Microsoft 365 tenant's billing profile

After purchase, AppSource redirects you to the Vizlake activation page.
{% endstep %}

{% step %}
**Activate your tenant**

You arrive at the **shared Vizlake activation page** — the same landing experience used by [AiDi](https://docs.aidi.ai). It recognises which Vizlake product you've purchased (Mosaic or AiDi) and provisions the right tenant for you.

1. Sign in with the Microsoft Entra account that has **tenant administrator** rights
2. Review the requested permissions:
   * Sign in and read your profile
   * Read Power BI content on behalf of the user (delegated, OBO flow)
3. Tick **Consent on behalf of your organisation** *(strongly recommended — saves every user from a separate consent prompt later)* and click **Accept**
4. The activation page provisions your Mosaic tenant and redirects you to the product

{% hint style="info" %}
Tenant-wide admin consent at this step avoids per-user consent prompts later. If your organisation requires admin consent for any third-party app, see [Azure App Registration → Tenant-wide admin consent](/mosaic/get-started/powerbi-configuration/azure-app-registration.md).
{% endhint %}
{% endstep %}

{% step %}
**Configure Power BI**

Mosaic must be allowed to call your Power BI tenant on behalf of your users. Complete the [Power BI Configuration](/mosaic/get-started/powerbi-configuration.md) section before inviting users.
{% endstep %}

{% step %}
**Configure your LLM**

Mosaic doesn't include AI inference - you bring your own LLM capacity. Connect [Azure AI Foundry](/mosaic/get-started/llm-configuration/azure-ai-foundry.md) *(recommended)* or paste an [API key from Anthropic / OpenAI](/mosaic/get-started/llm-configuration/byo-api-key.md). Until this step is done, the chat panel will show "AI not configured" and agent runs are blocked.
{% endstep %}

{% step %}
**Onboard your team**

Activate creates a **personal workspace** for the admin who signed in, with a "Getting Started" page. To work with others, create a shared workspace and invite teammates by email - see [Accessing Mosaic](/mosaic/user-access/accessing-mosaic.md).
{% endstep %}

{% step %}
**Smoke-test before broad rollout**

Before rolling Mosaic out to your whole BI team:

* Sign in with a test user from your tenant
* Confirm the test user can see the workspace they were invited to
* Embed one Power BI report and confirm it renders under the test user's identity (Row-Level Security should hold - the user should only see what they could in Power BI directly)
* Run a sample DAX query to confirm Power BI access is working end-to-end
  {% endstep %}
  {% endstepper %}

## What if something goes wrong?

If activation fails, contact `info@vizlake.com` with:

* Your Microsoft Entra tenant ID
* The exact error message visible on the page
* Approximate time of the issue (so we can correlate with our logs)


---

# 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:

```
GET https://docs.aidi.ai/mosaic/get-started/installation-steps.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.