Microsoft is joining more than 50 technology partners and providers, including Salesforce, Oracle and SAP, in adopting Google's Agent2Agent protocol, which the company recently launched to allow AI agents to communicate with each other. Microsoft also announced that it is joining the A2A working group on GitHub to contribute to the protocol and tooling.
A2A lays the foundation for agent collaborations to occur securely in a flow of work across various models, domains, and ecosystems. The adoption would allow, for example, a Microsoft agent to schedule a meeting while a Google agent drafts the e-mail invites.
Google wrote in April:
“To maximize the benefits from agentic AI, it is critical for these agents to be able to collaborate in a dynamic, multi-agent ecosystem across siloed data systems and applications. Enabling agents to interoperate with each other, even if they were built by different vendors or in a different framework, will increase autonomy and multiply productivity gains, while lowering long-term costs.”
Microsoft wrote in a blog post:
“Customers can build complex, multi-agent workflows that span internal [agents], partner tools, and production infrastructure — while maintaining governance and service-level agreements. We’re aligning with the broader industry push for shared agent protocols.”
Microsoft's decision to support A2A comes after the company introduced support for Anthropic's Model Context Protocol, its standard for connecting AI to the systems where data resides, in Copilot Studio, which Google and OpenAI also said they would adopt earlier this year.
