Microsoft Advocates for Open Standards to Enable Cross-Company AI Agent Collaboration

Microsoft's Vision for an 'Agentic Web'

Microsoft's Chief Technology Officer, Kevin Scott, has unveiled the company's ambitious vision for the future of artificial intelligence (AI) ahead of their annual Build developer conference. Scott envisions an 'agentic web' where AI agents from different companies can collaborate seamlessly, emphasizing the need for open standards and improved AI memory capabilities 1

1

2

2

.

Embracing Open Standards

At the heart of Microsoft's strategy is the adoption of the Model Context Protocol (MCP), an open-source standard introduced by Anthropic, a Google-backed AI company. Scott believes that MCP has the potential to create an "agentic web" similar to how hypertext protocols helped spread the internet in the 1990s 1

1

3

3

.

"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 explained 1

1

.

This approach marks a significant shift from Microsoft's past strategies, particularly during the browser wars of the 1990s. The company is now advocating for openness and simplicity, warning that a closed, vertically integrated approach could stifle innovation 2

2

.

Improving AI Agent Memory

Another key focus for Microsoft is enhancing the memory capabilities of AI agents. Scott noted that current AI interactions often feel transactional, lacking continuity and context 1

1

4

4

.

To address this, Microsoft is developing a technique called structured retrieval augmentation. This method allows AI systems to extract and retain concise, relevant information from each interaction, creating a structured summary or "roadmap" of the conversation 1

1

5

5

.

"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," Scott explained 1

1

.

Challenges and Implications

While the potential benefits of an 'agentic web' are significant, there are challenges to overcome. Improving AI memory is expensive due to the increased computing power required 4

4

5

5

. Additionally, there are concerns about the potential risks of autonomous AI agents interacting without human oversight 3

3

.

Industry Collaboration and Future Prospects

Microsoft's push for open standards and cross-company collaboration in AI development reflects a broader industry trend. Google, for instance, has introduced the Agent-to-Agent protocol (A2A), another open standard designed to facilitate communication between AI agents across different systems 2

2

.

As the AI landscape continues to evolve rapidly, Microsoft's vision for an 'agentic web' could potentially reshape how AI systems interact and collaborate, opening up new possibilities for innovation and application across various sectors 1

1

2

2

3

3

.