> 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/prerequisites.md).

# Prerequisites

Before installing Mosaic, confirm your organisation has the following.

Mosaic is **bring-your-own-licence (BYOL)** for both Power BI and AI inference. The Mosaic subscription covers the platform — workspaces, collaboration, agents, audit, integration. Power BI capacity and LLM inference are on you, in your own tenant. This keeps your data in your environment and your spend visible to your finance team.

## Microsoft 365 tenant

Mosaic uses **Microsoft Entra ID** as its sole identity provider. You need:

* An active Microsoft 365 tenant
* A Microsoft Entra administrator who can grant **tenant-wide admin consent** when Mosaic is installed for the first time

## Power BI capacity in your tenant

Mosaic plugs into the Power BI you already have. Embedded reports must be backed by your own capacity. One of the following is required:

* **Microsoft Fabric capacity** (F-SKU)
* **Power BI Premium**
* **Power BI Premium Per User** (PPU) for every user who will sign in to Mosaic
* **Power BI Embedded** capacity (A-SKU)

Mosaic does not include or resell Microsoft licensing. The capacity sits in your Microsoft 365 tenant, not Vizlake's.

## Power BI workspace and content

* At least one Power BI workspace assigned to a capacity above
* The reports, dashboards, and datasets you intend to embed must already live in that workspace
* You must have admin or member access on those Power BI workspaces

## LLM capacity in your tenant

Mosaic does not bundle AI inference. You bring your own LLM capacity, and Mosaic routes every chat, agent run, and DAX-generation call through it. One of the following is required:

* **Azure AI Foundry** project *(recommended)* — a deployed model in your own Azure subscription. Cleanest data-residency and billing story for Microsoft-native customers.
* **Anthropic API key** — direct integration with the Claude family
* **OpenAI API key** — direct integration with GPT-4 / GPT-4o

You'll connect this in [LLM Configuration](/mosaic/get-started/llm-configuration.md) after activation. Inference cost is billed by your provider, against your account — Mosaic does not handle inference billing.

## Mosaic plan

A Mosaic Standard or Mosaic Premium subscription via Microsoft AppSource.

* **Custom AI agents** require Mosaic Premium
* **Audit log export**, **priority support**, and **quarterly reviews** require Mosaic Premium

## Mosaic plan

A Mosaic Standard or Mosaic Premium subscription via Microsoft AppSource.

* **Custom AI agents** require Mosaic Premium
* **Audit log export**, **priority support**, and **quarterly reviews** require Mosaic Premium

## Recommended

* Familiarity with Power BI Admin Portal tenant settings - you'll touch these during configuration
* A test user account in your tenant for verifying the access flow before rolling out broadly
* A Microsoft Entra security group already created (or permission to create one) for grouping Mosaic users

## What's next

When the prerequisites are in place, follow [Installation Steps](/mosaic/get-started/installation-steps.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:

```
GET https://docs.aidi.ai/mosaic/get-started/prerequisites.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.