I wanted to share an approach for how I am using AI to improve documenting solution designs and thoughts around a solution.

So, I have been following the Model Context Protocol (MCP) world for a while now. I first heard about MCP just as we were going out to MVP Summit in March 2025. Already, the Microsoft Copilot Extensibility team were on the case with people like Fabian Williams experimenting with them. I have been following this space, reading articles and finally, over the summer, I have had some time to roll up my sleeves and look at how I would build an MCP Server.

In this post we delve into an issue where Copilot Studio questions were not being processed as expected leading to poor user experience.

Last week, Microsoft Build 2025 announced the introduction of Multi-Agent Copilots within Copilot Studio and the ability to configure one Copilot Agent to make use of other Copilot Agent’s and their tools. I have been pondering on this for a while, but whilst watching the demos, this got me thinking about how these Agents will be delivered. It’s clear that there will be a lot of thought required to deliver a solid multi-Agent architecture, which will need to be designed and engineered!

YouTube video by Microsoft Community Learning

In this blog post, the fourth of the series I discuss some ideas for future capabilities and making this feature more AI Agent friendly.

In this blog post, the third in the series I discuss some of the bugs that I have seen.