AI Provider for AI Readiness

Scoring never uses AI. The text BI Pixie authors for you does: proposed descriptions, AI Instructions, folder names, the phrasing of benchmark questions, and the generic AI agent a benchmark can test. That text is written by an AI provider you connect. In the portal this is usually bring-your-own: you connect your own account, BI Pixie stores the credentials encrypted, and every call runs server-side against your account with BI Pixie's prompts.

Connect a Provider

The Set up an AI provider dialog showing the connected provider with options to replace or remove it
  1. On the AI Readiness page, the AI provider status row reads Not connected until one is set up. Open the Set up an AI provider dialog from the prompt beside it. The same dialog opens from Use as AI provider on the AI Assistants page once you have created a data agent, and you can manage the provider at any time from the Account page, on the AI tab.
  2. Choose a provider. Azure AI Foundry (recommended) runs in your own Azure tenant and bills to your subscription: supply your endpoint and deployment name, and authenticate with Microsoft Entra ID (recommended) or an API key. OpenAI and Anthropic each take an API key.
  3. Save. The status row then names your provider as connected, and the AI Assistants icon in the left sidebar carries a status light that is spoken as "AI provider connected".
The BI Pixie data agent as your provider. Portal accounts with a designated Fabric workspace can create the BI Pixie data agent on the AI Assistants page and connect it as their AI provider without leaving that page. Once the agent exists, its card offers Use as AI provider, which opens the same setup dialog with the agent already presented as the recommended option. It runs on your Fabric capacity, with no API key to manage. Without a designated workspace, the portal is bring-your-own only. The same option is the default in the Fabric Workload.

What Works Without a Provider

Everything that does not use AI works with no provider connected, and keeps working when a provider call fails: scoring, the full dimension breakdown, findings, usage grounding, assessment history, AI data schema curation, field defaults, and the first pass of folder proposals. The AI-authored items wait instead. Those cards show a note that an AI provider is required, with a Connect shortcut beside it.

A benchmark can still be built and run without a provider, using fixed question templates instead of natural phrasing; business-domain detection and question variations are unavailable, and each says so where it appears. The one benchmark option that requires a provider is the generic AI agent, because the provider plays the emulated agent and is therefore what answers the questions. The BI Pixie data agent cannot play that role, so even when it is connected as your provider, testing through a generic AI agent needs a bring-your-own provider. See AI to Test.

What the Provider Sees

When BI Pixie writes text for you, it sends your provider the part of the semantic model definition the task needs: table, column and measure names, data types and format strings, existing descriptions, measure expressions, display folder names, and the semantic model's own AI Instructions. Where the reports built over that semantic model have Pixies, it also sends the report, page and visual titles people open and the values people filter to most, so the text it drafts uses the words your own people use.

When BI Pixie phrases benchmark questions, the provider receives field names, the shape of each question, and any filter value the question has to state, such as a product category. The correct answer is never sent at that stage, so the answer key cannot leak into the test. After the tested AI has answered, BI Pixie can send your provider the question, the answer that was recorded, and the correct value it computed, so your provider can give a second opinion on whether the two match.

Your provider never receives telemetry event records or end-user identifiers, and it never receives the contents of your tables. Fields you excluded in the AI data schema contribute no values and no descriptions at any stage, and the one thing your provider sees about an excluded field is its name, and only where your existing AI Instructions already mention it, so the reference can be removed. When BI Pixie drafts text it withholds more: no values at all from a semantic model that defines row-level security, and no values from a column whose name indicates an identifier or personal data. Privacy Policy Section 3.7 states the full list.

What's Next