Microsoft has prepared the stage for an AI future in which intelligent agents from different companies can work together and remember users’ past interactions more effectively. This bold vision is expected to take centre stage at the company’s annual Build Developer Conference in Seattle.

Microsoft Supports Open Standards Across AI Platforms

Speaking with journalists just before Microsoft’s Redmond headquarters event, Chief Technology Officer Kevin Scott expounded on the need for standard protocols that would allow agents to work for autonomous systems that perform tasks like debugging code to work across platforms.

Supporting the Model Context Protocol to Create the ‘Agentic Web’

Microsoft is putting its backing behind the Model Context Protocol open-source initiative that was founded and introduced by Anthropic, a Google-backed AI startup. Scott said that this would power an “Agentic web,” a new paradigm in which, just as hypertext changed the dynamics of the early Internet, it would change the conception of the agents.

Scott said.

“It means that your imagination gets to drive what the agentic web becomes, not just a handful of companies that happen to see some of these problems first.” 

Scott also said that Microsoft is trying to help AI agents have better memories of things that users have asked them to do, noting that, so far, “most of what we’re building feels very transactional.”

But making an AI agent’s memory better costs a lot of money because it requires more computing power. Microsoft is focusing on a new approach called structured retrieval augmentation, where an agent extracts short bits of each turn in a conversation with a user, creating a roadmap to what was discussed.

Scott also said

“This is a core part of how you train a biological brain, you don’t brute force everything in your head every time you need to solve a particular problem.”