Microsoft is adopting Google’s open protocol, Agent2Agent (A2A), for linking AI “agents” to communicate with each other. The company announced on Wednesday that it will bring support for A2A to Azure AI Foundry and Copilot Studio, its AI development platforms.
A2A, launched by Google in early April, enables AI-powered semi-autonomous programs to work together across different clouds, apps, and services. The protocol allows agents to exchange goals and invoke actions, providing developers with interoperable components to ensure secure collaboration.
“By supporting A2A and building on our open orchestration platform, we’re laying the foundation for the next generation of software — collaborative, observable, and adaptive by design,” stated Microsoft in a blog post. “The best agents won’t live in one app or cloud; they’ll operate in the flow of work, spanning models, domains, and ecosystems.”
With A2A support, agents built using Azure AI Foundry and Copilot Studio will be able to tap external agents for tasks, including those created with other tools or hosted outside Microsoft. For instance, a Microsoft agent could schedule a meeting while a Google agent drafts email invites. This will enable customers to build complex, multi-agent workflows that span internal agents, partner tools, and production infrastructure while maintaining governance and service-level agreements.
Benioff warns OpenAI about Microsoft’s “playbook”
Microsoft has also joined the A2A working group on GitHub to contribute to the protocol and tooling. The company stated that by supporting A2A, it is laying the foundation for the next generation of software — collaborative, observable, and adaptive by design. Microsoft’s decision comes as the company continues to invest in AI technology, with its recent introduction of support for MCP, Anthropic’s standard for connecting AI to data systems, in Copilot Studio.
