Kevin Scott on The Future of Programming, AI Agents, and Microsoft’s Big Bet on the Agentic Web

7 snips

May 20, 2025

Kevin Scott, Microsoft’s CTO with 41 years of programming experience, dives into the transformative future of AI agents. He shares insights on the essential role of the Model Context Protocol for agents to access diverse tools and data. Scott parallels the agentic web to the early internet, emphasizing the need for a shared language. He addresses the balance between open innovation and security, advocating for a collaborative model. With anecdotes from his journey, he highlights the importance of craftsmanship in software and the necessity to embrace technological change.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

00:00 / 00:00

Ship To Close The Capability Overhang

Close the capability overhang by building products that leverage current model reasoning and planning strengths now.
Don't wait for perfect models; focus on delivering features that match available capabilities.

00:00 / 00:00

Agentic Web Needs Infrastructure

The agentic web needs plumbing like the internet: standard protocols and agent-readable sites to let agents act and fetch fresh data.
MCP and NLWeb are early primitives aiming to be the HTTP/HTML equivalents for agent access and composition.

00:00 / 00:00

Action Over Chat: Agents Must Act

Agents become useful only when they can take action: use tools, change systems, and consult diverse information sources.
Access to APIs, websites, and system integrations is essential for useful delegation to agents.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

I interviewed Microsoft CTO Kevin Scott about the future of agents and software engineering for another special edition of AI & I.

With 41 years of programming behind him, Kevin has lived through nearly every big shift in modern software development. Here’s his clear-eyed take on what’s changing with AI, and how we can navigate what’s next:

The real breakthrough for the agentic web is better plumbing. Kevin thinks agents won’t be useful until they can take action on your behalf by using tools and fetching data. To do this, agents need access across your systems—and Microsoft’s answer is adopting Model Context Protocol, or “MCP,” that allows an agent to access tools and fresh data beyond its knowledge base, as their standard protocol for agents to move through contexts and get things done.
How the agentic web echoes the early internet. Just as protocols like HTTP and HTML gave the web a shared language, Kevin believes the agentic web needs its own infrastructure—the first glimpses of this include MCP (the HTTP of agents) and NLWeb, Microsoft’s push to make websites legible to agents (similar to what HTML did for browsers).
Open ecosystems can coexist with strong security systems. Kevin argues that the “tradeoff” between ecosystems that allow “permissionless” innovation and robust security is a false dichotomy. With AI agents that understand your personal risk preferences—and know your communication habits across email, text, and other channels—they could detect when something suspicious is happening and act on your behalf.
The craftsman’s dilemma in the age of agents. Kevin is a lifelong maker—of software, ceramics, even handmade bags—and he cares deeply about how things are made. Because this can feel at odds with coding with AI agents, Kevin’s approach is to notice where the process matters most to him, and where it's okay to optimize for outcomes. After four decades of seeing breakthrough technologies, his advice is simple: be curious, try stuff, and use it if it works for you.
The future of software engineering agents is plural. Kevin believes the future of software engineering agents will be diverse because developers who enjoy the freedom of playing with different tools is one of the most consistent patterns he’s seen in his decades in tech. What will drive this diversity, he says, is builders who deeply understand specific problems and tailor agents to solve them exceptionally well.
How agentic workflows will evolve. Kevin sees a shift from short back-and-forth interactions with agents to longer, async feedback loops. As the agentic web matures and model reasoning improves, people will start handing off bigger, more ambitious tasks and letting agents run with them.

Timestamps:

Introduction: 00:01:44
The race to close the “capability overhang”: 00:02:49
How agents will evolve into practical, useful tools: 00:04:31
The role Kevin sees Microsoft playing in the agent ecosystem: 00:06:48
How robust security measures can coexist with open ecosystems: 00:12:05
Kevin's philosophy on being a craftsman in the age of agents: 00:15:39
How the landscape of software development agents will evolve: 00:20:52
The future of agentic workflows: 00:25:33