Loading...

BYOM: Using Azure AI Foundry models in Copilot Studio

BYOM: Using Azure AI Foundry models in Copilot Studio

Copilot Studio gives you a fast, secure way to build conversational agents and deploy them into the Microsoft 365 environment without writing code. But what happens when the default models aren’t enough? That’s where Azure AI Foundry comes in. Copilot Studio now supports direct integration with models deployed via AI Foundry. That means you can choose exactly the model you need, like a language model with stronger reasoning capabilities, an image analysis model, or something domain-specific, and then connect it directly to your Copilot Studio agent.

Example

An IT team is managing support requests across multiple business units. Users often submit screenshots: Error messages, UI glitches, device warnings, but rarely with context. Traditional agents struggle with this format. Text-only prompts don’t help when the issue is visual. Instead of trying to route these through a human queue, we use Azure AI Foundry to deploy a vision model capable of:

  • Performing OCR on screenshots
  • Identifying key UI elements
  • Classifying common issues based on screen layouts

We connect the model to a Copilot agent in Microsoft Teams. Now, users can upload a screenshot, and the agent can recognize a known error and suggest next steps within seconds. No manual ticket triage, no copy-paste from Outlook to ServiceNow.

How to connect an AI Foundry model to your Copilot agent

  1. Find a model in the huge AI Foundry catalog. You can also fine-tune an existing model
  2. Deploy your model in Azure AI Foundry
  3. You will get 3 values, that you need in one of the following
  • A deployment name
  • An endpoint URL
  • An API key

Once you have that, navigate to Copilot Studio and open the agent you want to enhance.

  • Go to Settings –> Generative AI
  • In the Primary response model dropdown, select Connect a model in the From Azure AI Foundry (preview) section

Once prompted, paste in the:

  • Target URI (endpoint)
  • Deployment name
  • API key

Copilot Studio will verify the connection. Once successful, your agent is now powered by that specific model.

Boom, done! 🧨

PS: This is a super new feature. In case you don’t see the From Azure AI Foundry (preview) section please be patient, it will roll out soon™️. Also make sure, that in your Power Platform environment, you have the Get new features early switch set to Yes

early access to new features

Published on:

Learn more
Luise Freese: Consultant & MVP
Luise Freese: Consultant & MVP

Recent content on Luise Freese: Consultant & MVP

Share post:

Related posts

Announcing the end of support for Node.js 20.x in the Azure SDK for JavaScript

After July 9, 2026, the Azure SDK for JavaScript will no longer support Node.js 20.x. Upgrade to an Active Node.js Long Term Support (LTS) ver...

5 hours ago

MCP Apps on Azure Functions: Quickstart with TypeScript

Learn how to build and deploy MCP (Model Context Protocol) apps on Azure Functions using TypeScript. This guide covers MCP tools, resources, l...

11 hours ago

Setting up Power BI Version Control with Azure Dev Ops

In this blog post is a way set up version control for Power BI semantic models (and reports) using the PBIP (Power BI Project) format, Azure D...

6 days ago

Azure Developer CLI (azd) – March 2026: Run and Debug AI Agents Locally, GitHub Copilot Integration, & Container App Jobs

Run, invoke, and monitor AI agents locally or in Microsoft Foundry with the new azd AI agent extension commands. Plus GitHub Copilot-powered p...

6 days ago

Writing Azure service-related unit tests with Docker using Spring Cloud Azure

This post shows how to write Azure service-related unit tests with Docker using Spring Cloud Azure. The post Writing Azure service-related uni...

7 days ago

Azure SDK Release (March 2026)

Azure SDK releases every month. In this post, you find this month's highlights and release notes. The post Azure SDK Release (March 2026) appe...

11 days ago

Specifying client ID and secret when creating an Azure ACS principal via AppRegNew.aspx will be removed

The option to specify client ID and secret when creating Azure ACS principals will be removed. Users must adopt the system-generated client ID...

11 days ago

Azure Developer CLI (azd): Run and test AI agents locally with azd

New azd ai agent run and invoke commands let you start and test AI agents from your terminal—locally or in the cloud. The post Azure Developer...

19 days ago
Stay up to date with latest Microsoft Dynamics 365 and Power Platform news!
* Yes, I agree to the privacy policy