Introduction In my previous post, I went through how you can index documents from SharePoint in Azure AI Search and how this might benefit your agent over the built-in SharePoint integration. One key benefit that I didn’t touch on is that you can bring in additional columns from SharePoint that are not currently exposed, but you can using Azure AI Search. I covered why this might be important in a recent blog post. ...
Introduction Copilot Studio makes it super easy to add SharePoint as a knowledge source to your agents. However, there is one issue that I’ve noticed, which is that we cannot read the properties (metadata) of the documents in SharePoint. This is a problem because often important information about the document is not in the content itself, but rather in the properties of the document. Take this example below. The agent has been granted access to a document library. I have added a couple of documents and purposefully added a value to the property called ReferenceID that is not in the document content itself. When I ask the agent to provide the value that would be in the ReferenceID property, the agent is not able to provide the value. If the value was in the document content, the agent would be able to provide it. ...
Introduction As of December 2025, this feature is in public preview - more information can be found in the official documentation. Whilst it is possible to shortcut some these steps by using the Azure AI Search SharePoint agentic knowledge source, this doesn’t produce great results with Copilot out of the box, for example citations don’t link back to the original SharePoint document. Whilst in theory, M365 Copilot agents can use a built-in SharePoint knowledge source that leverages a semantic index, in practice, it can be hit and miss (inconsistent, not always matching to most relevant content, etc.). ...