Microsoft says that it’s embracing Google’s recently launched open protocol for allowing AI “agents” to communicate with each other.
On Wednesday, Microsoft announced that it would bring support for Google’s Agent2Agent (A2A) spec to two of its AI development platforms, Azure AI Foundry and Copilot Studio. Microsoft has also joined the A2A working group on GitHub to contribute to the protocol and tooling.
“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,” wrote the company 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.”
A2A, which Google unveiled in early April, allows agents — AI-powered semi-autonomous programs — to work together across different clouds, apps, and services. Using the protocol, agents can exchange goals and invoke actions. Developers get a set of interoperable components they can use to make sure agent collaboration occurs securely.
Once A2A support arrives for Azure AI Foundry and Copilot Studio, agents built using the platforms will be able to tap external agents for tasks, including agents created with other tools or hosted outside Microsoft. For example, a Microsoft agent could schedule a meeting while a Google agent drafts the email invites.
“[C]ustomers can build complex, multi-agent workflows that span internal [agents], partner tools, and production infrastructure — while maintaining governance and service-level agreements,” the company explained in its blog post. “We’re aligning with the broader industry push for shared agent protocols.”
While it’s far from perfect, agentic technology is attracting increasing investment as enterprises look to adopt it to boost productivity. According to a recent KPMG survey, 65% of companies are experimenting with AI agents. Markets and Markets projects that the AI agent segment will grow from $7.84 billion in 2025 to $52.62 billion by 2030.
Techcrunch event
Berkeley, CA
|
June 5
BOOK NOW
Microsoft’s decision to throw its weight behind A2A comes after the company introduced support for MCP, Anthropic’s standard for connecting AI to the systems where data resides, in Copilot Studio. Other major AI model providers, including Google and OpenAI, announced that they would adopt MCP earlier this year.