Build an Intune Copilot with Microsoft Copilot Studio

In the last post I explained how you can build a CoPilot using the Azure OpenAI Studio. In this blog post we will build an Intune Copilot with the Copilot Studio instead. Here we will also utilize the Azure OpenAI Service. This is similar to the approach I used for my Intune AI Voice Bot, where AI is also used to interact with Microsoft endpoint management scenarios. Let’s have a quick look into building this as well:

What are the prerequisites for an Intune Copilot

• A license for Microsoft Copilot Studio (or an existing Power Virtual Agents license).
  • It is also possible to start with an free trial

• Your Microsoft 365 tenant admin to deploy the Dynamics 365 and Copilot Studio app in the Microsoft 365 admin center.
• Access to the limited preview, by submitting a support ticket.

How to start your Intune Copilot

Open the CoPilot Studio via https://web.powerva.microsoft.com/ and login.

• Click on New copilot

• Enter a Name for your CoPilot and select the language.

Once this is done the bot is created and we have to add your custom data via skills. But before, let’s have a look at which functionalities are available.

The Studio

There are basically 3 essential parts. #1 is the menu element, where you can select the options to create plugins, add your documents, build flows or everything else. #2 is the Copilot playground to test stuff and validate that everything works after you configure it. The third part is the Main Part where you can take the configurations for the different options in #1.

Add your documents to the Intune Copilot

Go to Settings -> Generative AI and upload a document. In my case I used an export of Microsoft Learn docs so the bot can answer based on official guidance.

That’s it? Let’s test our Intune Copilot by asking a question about this document.

The answer is bad. Let’s have a look at what is missing. It was too easy. I forgot to activate the “Improve the reach of the conversation with generative responses“. Now the Intune Copilot answers with content from the documents.

Create an AI Plug-In for your Intune Copilot

We have to create a PlugIn for this document. But how does it work? There are two kinds of PlugIns. One is an AI Plug-In like this:

Here you have an Input / Input Variables, and with this an Answer will be generated using GPT. This is an example of a Text classifier. You give the model a Text and some Categories, and it will assign a category to the text.

The second one is a Conversational PlugIn. Here you can build a kind of flow that powers a richer experience:

This flow offers you the full flexibility to connect to your data via the GPT Playground, make Conditions, Prompt for Auth and much more.

How to integrate your Intune Copilot in Teams

Also this is very easy. You can select Channels in the Settings and select Microsoft Teams.

If you want to compare this with the Azure OpenAI Studio way, check out how to create your own Intune Co Pilot using Azure OpenAi Studio.

• Select activate Teams and that’s it.

Common pitfalls and tips for a reliable Intune Copilot

The single most common mistake is the one I made above: forgetting to enable generative answers. If your Intune Copilot keeps falling back to “I don’t know”, check that setting first before you touch anything else. A second pitfall is uploading documents that are too broad. Instead of dumping the entire Microsoft Learn library, give the bot a focused export of the topics your users actually ask about, such as compliance policies, app deployment and enrollment. This keeps answers accurate and fast.

Finally, always test from the Copilot playground after every change and watch how it grounds its answer. If a response looks wrong, the playground shows you which source it used, which makes debugging much quicker than testing inside Teams.

Now you will find your Intune Copilot in the Teams AddOns. If you enjoyed this, you might also like this post about how to build your custom GPT apps. If you want to go deeper into the concepts behind this, check out my Deep Dive into Co-Pilots.