The AI landscape is shifting fast — from tools that just talk to us to agents that actually do work for us. In this post, I’m breaking down three things you need to understand right now: Cowork, Scout, and the new Copilot Studio UI. Whether you’re an end user trying to make sense of all the new terminology or someone looking to automate their working day, this is your starting point. ...
With Copilot Chat, Copilot in apps, Cowork, Scout (Frontier), declarative agents and custom agents all vying for your attention, it’s easy to feel overwhelmed. I’ve lost count of how many times someone has asked me, “Should I use Cowork for this or just Copilot Chat?” — and the honest answer is, it depends. If you haven’t already, I’d recommend reading my earlier post on Getting Started with Cowork, Scout (Frontier) & the New Copilot Studio UI first — it covers what each of these tools actually does. This post builds on that foundation and gives you a simple framework for choosing the right experience every time, plus two free resources you can use right now to make the decision for you. ...
When you embed a Copilot Studio agent on a webpage using DirectLine and the Bot Framework Web Chat control, it works great — but it’s text only. What if your agent could speak its responses out loud? In this post, I’ll show you how to intercept bot responses from the Web Chat store middleware and pass them to a text-to-speech engine so your agent speaks every reply in the browser. The pattern works with any TTS provider — the browser’s built-in Web Speech API, Azure Speech Services, ElevenLabs, or anything else. ...
I recently set out to give one of my Copilot Studio agents its own identity — something I could @mention in Teams and Word, like a proper digital colleague. What I discovered was a brand new preview feature called Entra Agent ID, and it taught me something important about where Microsoft is heading with AI agent identity. Let me walk you through what I found. The Idea: A Personal Productivity Assistant I wanted to build a Copilot Studio agent that could manage my emails, handle my calendar, and pull up Microsoft Learn docs on demand. Simple enough. But I also wanted this agent to have its own identity — something more than just another app registration buried in Azure. ...
If you’ve ever needed to dynamically create an Excel file from data in Power Automate — maybe from a Copilot Studio agent, a SharePoint list, or an API response — you’ve probably realised there’s more than one way to skin this particular cat. In this post, I’m going to walk you through three different approaches to generating and populating an Excel file, each with its own strengths and trade-offs. I’ll be using a sample F1 2026 driver grid as my data, but this could just as easily be data passed from a Copilot Studio Agent, a Dataverse table, or any other source. ...
What if your AI chatbot could handle routine customer questions and seamlessly hand off complex issues to a live agent — all without the customer noticing a hiccup? That’s exactly what I’ll show you how to build in this post. Whether you’re a developer, customer support manager, or IT enthusiast, by the end of this guide you’ll have a fully working Copilot connected to Dynamics 365 Customer Service Workspace and embedded on your website for real-time agent transfers. ...
Want your Power Virtual Agent to do more than just answer static questions? Making your chatbot truly interactive is achievable using Power Automate. When the bot asks the end user a question, it can accept input (entities), pass these to Power Automate and then in return tailor a response, based on the outcome of your flow. In order to demonstrate this, I built a parcel history bot that would query the DHL Tracking API and return to the user the current status and event history for a valid Tracking ID. This method can be re-applied to Microsoft Lists, Dataverse, Connectors and any other 3rd party API. You can watch a demo and see how it was built in more detail below. ...