Claude Meets Copilot Studio
This is the one I've been building toward. Over the last few posts we deployed Claude in Microsoft Foundry, said hello to it from code, and taught it to turn a messy support ticket into clean, structured data. All useful, all a bit back-end. Today it comes together into something you can actually hand to a colleague: a working agent, built in Copilot Studio, the low-code tool you already know,…
This latest post brings together the components of a working AI-powered agent, built using Microsoft's Copilot Studio and powered by Anthropic's Claude model. The integration is seamless, with no additional setup required beyond selecting Claude from the dropdown menu in the tool you already use daily. An admin must first enable Anthropic's models in the Microsoft 365 Admin Center, but once done, the models are available in the Power Platform Admin Center for use in agents.
The agent is then created in Copilot Studio, with a name, description, and system prompt that defines its behavior and tone. Knowledge sources can be added to provide the agent with relevant information, such as a policy document in this case. The result is an agent that can provide accurate, context-aware responses, demonstrating the value of combining the power of Claude with the familiarity of Copilot Studio.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
