Microsoft’s chief technologist outlined their vision for the future of AI. He believes AI agents from different companies will seamlessly work together. This future will also include AI agents with improved memories of their interactions. He made these comments on Sunday before Microsoft’s annual software developer conference.
Microsoft will host its Build conference in Seattle on May 19. Analysts anticipate the company will reveal new tools for developers creating AI systems at the conference.
Speaking at Microsoft’s headquarters in Redmond, Washington, Kevin Scott said the company is focused on driving the adoption of industry-wide standards. These standards will allow agents from different makers to collaborate. “Agents are AI systems that can accomplish specific tasks, such as fixing a software bug, on their own.”
Scott noted Microsoft supports Model Context Protocol (MCP). Google-backed Anthropic introduced this open-source protocol. Scott believes “MCP has the potential to create an ‘agentic web’ similar to the way hypertext protocols that helped spread the internet in the 1990s.”
Scott explained that this vision allows for broader innovation. “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,” he said.
Microsoft is also working to improve AI agents’ memory of user requests. Scott noted that currently, “most of what we’re building feels very transactional.”
Improving an AI agent’s memory is expensive due to the computing power required. Microsoft is therefore concentrating on structured retrieval augmentation. This approach involves an agent extracting short bits from each conversation turn, and this creates a roadmap of the discussion.
Scott explained the importance of this approach. “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,” he said.
Click here for more Technology news.