Microsoft’s Vision for an Internet Made for Agents With CTO Kevin Scott (Best of the Pod)

In 2025, Kevin Scott bet that the agentic web would be the next big thing in AI. The Microsoft CTO argued that for agents to be genuinely useful, they'd need to be able to take action on our behalf—which would mean giving them access to the same sprawl of tools, data, and systems that make up the internet. Today, that bet is starting to pay off, as the foundational infrastructure for the agentic web is now being built. On this week's AI & I, Dan Shipper revisits his conversation with Kevin. They discuss Microsoft's role in the agentic web, why openness doesn't have to come at the expense of security, and why programmers should stay curious about new tools rather than resist them on principle. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Go to https://attio.com/every and get 15% off your first year. Timestamps: 0:00 Start 1:44 Introduction 2:49 The race to close the "capability overhang" 4:31 How agents will evolve into practical, useful tools 6:48 The role Kevin sees Microsoft playing in the agent ecosystem 12:05 How robust security measures can coexist with open ecosystems 15:39 Kevin's philosophy on being a craftsman in the age of agents 20:52 How the landscape of software development agents will evolve 25:33 The future of agentic workflows Links to resources mentioned in the episode: Kevin Scott on X: https://twitter.com/kevin_scott Model Context Protocol (MCP): https://modelcontextprotocol.io NLWeb: https://github.com/microsoft/NLWeb GitHub Copilot: https://github.com/features/copilot

• 0:00Speaker 00

  You're someone who I think cares a lot about the craft of things. One of the knocks on using agents for coding is it gets rid of some of that feeling or something like that. How do you feel about that?

• 0:10Speaker 01

  I love the fact that my people, makers writ large, so software engineers or mechanical engineers or woodworkers or potters. If you are really passionate about what you do, you're going to have very strong opinions about how you do it. I've been a woodworker for almost as long as I've been a programmer. This is not the first moment in the past four decades where the nature of software development has changed in a non-trivial way. Like if agents are going to be useful, they have to take action on your behalf. They have to be able to use tools and make changes in systems and consult information sources that are diverse and rich.

• 0:51Speaker 01

  And in order for that to really be great, you need an ecosystem that looks a lot like the internet. If you have a source of information, you already have a website, you already have an API that's doing something for people out there, you've got to figure out how to plumb things through where agents can talk to those things. Like one of the things, CTO that I've been pushing for at Microsoft is like, I want all of our systems internally to speak a standard protocol to all of the agents that we're writing inside of Microsoft. Be curious, try stuff. And if it works for you, use it, and if it doesn't, don't.

• 1:44Speaker 00

  Kevin, welcome to the show.

• 1:45Speaker 01

  Thanks for having me.

• 1:46Speaker 00

  One of the things that's interesting is I was here last year.

• 1:48Speaker 01

  Yep.

• 1:49Speaker 00

  And you said two things. There are two big themes. One was agents are going to be everywhere. That's one of the things you said, which I think really came true. That was very prescient. Another thing is I noticed a big emphasis last year on scaling laws.

• 2:02Speaker 01

  Yep.

• 2:03Speaker 00

  There are a lot of graphs of like, we're building big infrastructure, we're building these bigger models, and every two years, we're going to get these big performance improvements.

• 2:10Speaker 01

  Yeah.

• 2:11Speaker 00

  This year, the emphasis is really on the agentic web.

• 2:14Speaker 01

  Yeah.

• 2:14Speaker 00

  So what has changed? What have we learned from last year to this year?

• 2:17Speaker 01

  Yeah, I think there's a bunch of things that have changed. Like, one of the things is that I think last year, people were really in this state of mind that they were doubting that the scaling laws were going to continue to work really well, whereas I think we've demonstrated year after year after year that they are intact and working quite well, that that's not a thing that people need to be reminded of anymore. And I think the other thing, too, that's happened, honestly, is that the reasoning capabilities of the models has actually gotten a little bit ahead of what we're using the models to do in products.

• 2:59Speaker 01

  So I've been talking a lot lately about this thing called the capability overhang. And I think we actually have some work to do collectively across the whole industry to close the gap between what the models are actually capable of and what we're delivering to users of that capability. So that's one of the thematic things, why scaling laws might not be as interesting to talk about at this year's Build as last. And then the other thing, too, is that we've just discovered, as all of these agents have emerged over the past year, and so like both the number of agents and the amount of time that people are spending doing stuff inside of these agents or with these agents, is

• 3:41Speaker 01

  that there's a bunch of other stuff, other than reasoning, that has to get sorted out in order to make them as useful as they should be. So the things that I was talking about at the keynote today at Build were, we need better agentic memory, like our agents right now, because memory is constrained in a bunch of interesting ways. They're a little bit transactional, so you use them for one thing, and memory's coherent across the course of that task. But then it may or may not completely go away, and you're starting from scratch the

• 4:21Speaker 01

  next time, which really inhibits your ability to delegate increasingly complicated tasks to these things. And then there's just this real issue that if agents are going to be useful, they have to take action on your behalf. Like, they have to be able to use tools and make changes in systems and consult information sources that are diverse and rich. And in order for that to really be great, you need an ecosystem that looks a lot like the internet, where if you have a source of information, you already have a website,

• 5:05Speaker 01

  you already have an API that's doing something for people out there, you've got to figure out how to plumb things through where agents can talk to those things and where all of the incentives are aligned for everyone to go have all of this stuff participating in ways that make sense to them in this agentic web. And so I think that is the big story this year. It's like you've seen the first glimmers of real progress with super awesome, simple, open protocols like MCP that are serving the same purpose in this agentic web as HTTP does on the internet, and where you have things like NLWeb that are serving the same

• 5:48Speaker 01

  moral equivalent purpose as HTML does on the internet. And so I think you're going to see these things, like simple things that are composable and layering and just lots of activity in the open community and a bunch of things hopefully getting to ubiquity so that agents can actually do stuff.

• 6:06Speaker 00

  Right. So I think to play that back, one of the things I hear is we have agents, agents are starting to work, and in order to make them powerful, agents need access. They need access to whatever is out on the internet, whatever's on your computer, all that kind of stuff.

• 6:18Speaker 01

  Yep.

• 6:19Speaker 00

  And you need basically protocols and processes for agents to be able to access that stuff.

• 6:25Speaker 01

  Yes.

• 6:25Speaker 00

  So you're looking at different parts of the stack.

• 6:27Speaker 01

  Absolutely.

• 6:28Speaker 00

  The runtime layer, where you're building memory and all this kind of stuff, and then MCP, which allows you to connect into the wider internet to get more information into agents.

• 6:40Speaker 01

  Yep.

• 6:41Speaker 00

  I guess, why is that important to Microsoft? And what role do you want to play in that kind of an ecosystem?

• 6:49Speaker 01

  Well, look, I think there are two, maybe three, things that are super important. So one is we make agents, and in order for our agents that we're building for folks to be useful, we need to solve these problems inside of these agents. And even if you sort of scope it down narrowly to enterprise agents, like one of the things, CTO that I've been pushing for at Microsoft, is I want all of our systems internally to speak a standard protocol to all of the agents that we're writing inside of Microsoft, so that we're not exposing the entire world to Conway's Law, which is organization. So Conway's Law is a really funky thing in compilers, where this guy Conway said that

• 7:33Speaker 01

  the number of stages or passes in your compiler is going to be dictated by the number of teams you have working on the compiler.

• 7:41Speaker 00

  You ship your org chart.

• 7:41Speaker 01

  Correct. You ship your org chart. And so you certainly, inside of the confines of a company like Microsoft, you don't want to be shipping your org chart when you are building your agents. And it's just kind of a horror show to watch as an engineer, like all of this inefficient building, when you don't have those standard protocols and services that everybody's using. But I think if you sort of imagine, if you really imagine what agents could do and what users, not me, but just people who are hoping these things can be more useful than they are right now, you need things to start happening the same way that they were happening with the web.

• 8:26Speaker 01

  And I kind of see it right now. Like MCP is a really great example. So it is a really simple protocol that solves a really important problem, not just for people who are making agents and building platform infrastructure, but for users of these systems who want them to be more useful, and for people who are providers who are like, hey, I want to be participating in this new agentic web. It's like people are doing less of one thing, which I knew how to connect to, and they're sort of sitting here using these agents. How do I get my stuff wired up into this? And how does it make sense for me, even from a business model perspective, to do that? And so that's the two things.

• 9:11Speaker 01

  It's make our own agents more useful, and then we're a platform company, even more important than the agents that we're going to write ourselves. Like, that platform layer that Microsoft has been building in technology for 50 years, we just want to make sure that we are helping solve the problems that are emerging as this agentic web is happening.

• 9:34Speaker 00

  Yeah. It's really cool to see you guys leaning really hard into MCP and integrating it into all of Windows and all that kind of stuff. That's really awesome. And it brings up for me, I've been starting to hear rumblings from people who are thinking a lot about MCP, that the security model needs a lot of work. And I'm curious for your take on that, because you're making a lot of comparisons between this stack and the internet stack. And the internet has a bunch of things in its security model, like the same origin and policy, that makes sure that if a website is serving you code, it's only able to execute on its own data.

• 10:10Speaker 01

  Yep.

• 10:10Speaker 00

  And MCP doesn't really have that. So what do you think the right security model is for this?

• 10:14Speaker 01

  Well, look, I don't know that I know what exactly the right security model is. But the interesting thing about MCP is it is so coherently simple that it's going to be relatively easy for the community to decide what the security model is. Like, we have a bunch of enterprise things that we care a lot about, and that we're doing really good work with the MCP team to get done. So we need agents to have identities so that you can build entitlement systems, so you can say this agent is acting on behalf of this person, and they are entitled to see these resources in this system. And even having a way for an agent to sort of...

• 11:00Speaker 01

  Go query a bunch of systems and say like, these, here's the thing that I would like to do. These are the systems I need to touch in order to do the thing. Like, what entitlements do I need to ask for in order to do this? And so I can request permission like from the user, like the person who's delegated this task to me. Like, can I present to them? Like, can I have permission to these things in order to do this thing you asked me to do? Yes or no? And then for the administrators of all of these systems, you know, like, hey, is it okay for all of this to be happening? And so like, there's, all of that's going to be like relatively straightforward to do. Like, not easy, but like relatively straightforward to do on top of MCP.

• 11:44Speaker 01

  And like, the important thing is like, let's do it in an open way. Like, we don't need it to be proprietary to like our agents or our systems. Like, we've just got to figure out how to get this done where

• 11:59Speaker 01

  things kind of work like the web works.

• 12:01Speaker 00

  Yeah. Well, it's an interesting question for me because I feel like there's, there's maybe two potential models or potential go to markets for, for AI stuff that, that you guys have been talking about. One is this sort of like verticalized model where you own the model and you own the UI layer. You do all the applications and everything between. And the, the thing about that model, which maybe it's sort of, you could say that the App Store, Apple iPhone model is, is a good example of that is you can guarantee security in a lot of ways. And an open model, it's harder to do security stuff, but you get much more like innovation, basically, because there's no central authority. So how did you guys think about making that, making that decision?

• 12:41Speaker 01

  Yeah. So, look, I, I know that that's the argument that a lot of people make.

• 12:46Speaker 00

  Yeah.

• 12:46Speaker 01

  I, I think it might be a false dichotomy.

• 12:52Speaker 01

  There, there is, you know, like a, a thing that you have in these open systems where they are permissionless.

• 13:00Speaker 00

  Yeah.

• 13:01Speaker 01

  And like, there, there's a real advantage in having permissionless innovation. So like, the thing that is an individual that excites me most about what's happening right now is the extent to which you can go innovate and build things without having to seek someone's permission. Like, where you have to have them grant you permission for distributing your things to other people. And, you know, like having all of these like complicated gatekeeping things that are sitting in between you, who are the person who had the idea and like the people who might benefit from it. Like, I think some of these like middle layers that we had, that have emerged over the past handful of years, like, just aren't contributing much value, honestly, to the two parties in the transaction that matter,

• 13:45Speaker 01

  which is the person who did the hard work to make a thing. And then the people who are going to either spend their attention or their money or some other currency that's valuable to like access the thing.

• 13:56Speaker 01

  So like, I get it kind of excited about that. And so like, that's one of the reasons why we've made the decisions that we want to. But like, I also think that there are ways that you can get real, robust security in these systems, like leveraging some of the AI capability that you have now.

• 14:16Speaker 01

  That, you know, where you may be able to have better security.

• 14:19Speaker 00

  Yeah.

• 14:20Speaker 01

  Like, if you have an agent that you are running, that is attending to your personal security requirements, like, these are things I'm willing to share. These are things I'm not willing to share, like, you know? And it has some kind of knowledge of risk assessment. And like, yeah, like for, for instance, like my wife this morning, while I was, uh, while I was getting ready to jump on stage, like, I got this flurry of emails that, uh, because I'm the like backup security account for my wife, where like somebody was like fiddling around with two factor authentication on her account. And like, the first thing I did was I texted her. Like, I didn't want to email her because somebody might have gained unauthorized access to her email account.

• 15:05Speaker 01

  I texted her, I was like, hey, are you screwing around with the configuration here? And she's like, yes. And so like, you could imagine like having an agent that is like privy to like a whole bunch of your communication modalities, like being able to like notice that something funky is going on and then like, you know, using a bunch of resources to triangulate, uh, like whether that's legit activity or illegitimate activity. So I, like, I think there's just a bunch of stuff like that, that like you, you can have both, right? Like, I don't think it needs to be like, you know, one or the other as you framed it.

• 15:38Speaker 00

  Yeah, that makes sense. One of the, one, one other thing that I'm, I'm curious about is it just seems pretty clear that software engineering is changing.

• 15:46Speaker 01

  Yeah.

• 15:47Speaker 00

  And you're someone who's been involved in software engineering for a long time. You're someone who also, I think, cares a lot about like the craft of things, like the craft of how things are made. We were talking earlier about you're making, uh, you do a lot of ceramics. You make your own bags, like you're, you love having your hands in things.

• 16:06Speaker 01

  Yeah.

• 16:06Speaker 00

  And I think one of the knocks on, you know, using agents for coding is like, it gets rid of some of that feeling or something like that, which I don't necessarily agree with, but I'm sort of curious for you, like, as someone who cares about the craft of code, looking into this future of coding with agents, like, how does that, how do you feel about that?

• 16:24Speaker 01

  Well, so let me start by saying that I, I,

• 16:29Speaker 01

  I love the fact that my people, and like, when I say my people, I mean, you know, makers writ large. So software engineers or, you know, mechanical engineers or woodworkers or potters or, you know, just sort of pick your thing where people are, you know, trying to create things from, you know, raw materials or nothing.

• 16:49Speaker 01

  If you are really passionate about what you do, you're going to have very strong opinions about how you do it. The tools that you use, the materials that you use, like how things get put together. It is a necessary thing for you to be great at your job. The interesting thing is people have lots and lots of different opinions. And like, one of the events you said, like, I've been doing it for a long time. Like, I am, like, I'm an old fart. Like, I wrote my first program when I was 12, which means I've been programming for 41 years. And so the, the thing that you get to see when you've been doing a thing for a very long time is like, this is not the first moment in the past four decades

• 17:28Speaker 01

  where the nature of software development has changed in a non-trivial way and where people have very strong opinions about the change and what it means. And so, you know, I, I think the, the reality is that people will have choice. You know, like, I still, when I go into a text editor, I probably shouldn't say this because like we make, you know, Visual Studio Code. Like, I'm such an old recalcitrant fart that I still use VI. I use Vim at least, but like my text editor of choice is like this extremely antiquated thing. And like, I just refuse to go use something different.

• 18:11Speaker 00

  Yeah.

• 18:11Speaker 01

  Even though I know for sure that that is sub optimizing a part of what I'm doing. But I make the decision anyway because like I get to choose. And then in other aspects of my making, like either, either software or something else that I'm doing, like, I will be like, okay, the important thing here is not the way that I'm doing this particular part of it. It's the outcome that I'm trying to get to. And like, I'm going to use the most powerful or most convenient way to go get to the outcome. And like, you know, I don't care who's going to throw rocks at me for doing it. And like, it, it's literally everywhere.

• 18:53Speaker 01

  Like, I, I've been a woodworker for almost as long as I've been a programmer. And when I was a teenager, like, the big debate was like, oh, are you a real woodworker? If you use power tools, like, you know, real woodworkers only use hand tools. Like, there's still a little bit of that debate today. But like, the real debate is like, are you a real woodworker? If you use CNC tools, like computer controlled power tools versus just power tools? And I understand it. Like, I actually think it's interesting, the debate itself.

• 19:25Speaker 00

  Yeah.

• 19:26Speaker 01

  But like, sometimes like people are going to make, you know, different choices because like they value something different than you do.

• 19:32Speaker 00

  Yeah.

• 19:33Speaker 01

  If you value the process more than you value the outcome, like, sometimes you'll make different decisions than people who value the outcome more than the process.

• 19:42Speaker 00

  And I think the, like, is it, are you a real woodworker, a real programmer? You're sort of saying like, you're only real if you do it the way I grew up doing it. When you ask that question in a lot of ways, you know?

• 19:52Speaker 01

  But, but it, it's just so varied, right? And like, so the, the thing that I will say is like, I would never in a million years tell anyone not to have strong opinions about their craft. Like, have them. Like, it's great. Like, the, the advice that I would give people, and like, this is not me telling them, well, it's just advice, like things that I've found useful for myself, is just have an open mind, uh, you know, when the tools are changing. I can't even tell you like the number of times where I have looked at a new technology in some other like non-software dimension of making that came along where I'm like, eh, like, I don't want to learn, like 3D printers. Like, I waited forever to learn how to use 3D printers. And like, I regret it. Like, I should have started earlier.

• 20:36Speaker 01

  Like, they're so damn useful for almost everything that I do. And for a whole variety of complicated reasons, like, I didn't let myself be curious about that, which is odd.

• 20:46Speaker 00

  Yeah.

• 20:46Speaker 01

  And so, you know, just like be curious, try stuff. Like, and if it works for you, use it, and if it doesn't, don't.

• 20:52Speaker 00

  Yeah. What do you think is the future of software engineering agents? Like, is there going to be like one agent to rule them all? Or is it, you're just going to use many different agents with different tastes? Or like, how do you see that ecosystem shaping up?

• 21:01Speaker 01

  Yeah, I look, I think it's going to be a lot of different agents. I mean, like, and, and it's good to have a lot of agents. And like, we certainly would GitHub Copilot and the, uh, you know, GitHub agent stuff that we're working on. Like, I think we will compete very hard to like be a tool that lots of people will choose because it's very useful to them. But I think it's unrealistic in the universe of developers to like think that like every developer on the planet is going to snap to using like one tool for like an important part of their job. Like, part of the joy of being a developer is you actually have that choice and you can sort of choose and play around with a bunch of different things and like do irrational things and like do rational things. And like, it's, it's just, you know, it, it is

• 21:45Speaker 01

  one of the very consistent things that I've seen over the past four decades of my programming life is like, people choose to change their tools all the time.

• 21:56Speaker 00

  What are the dimension? Do you have an opinion on the dimensions along which the different agents might differ?

• 22:02Speaker 01

  Well, I think the most important thing about,

• 22:08Speaker 01

  Agents is like probably the product making part of them. And so the most interesting startups that I'm seeing right now are not trying to

• 22:24Speaker 01

  innovate by building some kind of differentiated infrastructure. They're innovating because they think they have an understanding of a problem that someone has that is better than anyone else. And they think that they can pick up infrastructure or modify infrastructure or tune infrastructure to go solve their understanding of that problem in a world-class way. So I think that's what we need a lot of right now. And like, that's what's going to dictate the diversity of agents and like how, like which things get used for what.

• 23:00Speaker 00

  Yeah.

• 23:00Speaker 01

  And I think honestly, because it's so much easier now to like have that nuanced understanding of what someone's problem is and to pick up these tools to go take a swing at solving it, that you're just going to have a lot of companies like building a lot of things, trying to, you can even see it with the software development tools. It's like crazy how many things have come out over the past year. And like, they're interesting, like all of them.

• 23:28Speaker 00

  Yeah.

• 23:28Speaker 01

  Yeah, it's a lot to respond to when you're a company building software development tools yourself, but like, it's super, super interesting. And it's like, what we've seen is if you've got some kind of nuanced understanding of what someone needs, like people have like high tolerance and like high interest in like giving things a try.

• 23:49Speaker 00

  Yeah. So we're almost out of time, but I'm, I'm curious, like, let's say it's a year from now, we're back at Build.

• 23:57Speaker 01

  Yep.

• 23:58Speaker 00

  What are, what are some things that are a hot topic right now or big questions that people have right now that are not going to matter in a year? And what is going to matter in a year? And what are your, what are your predictions for what we're going to be talking about?

• 24:11Speaker 01

  Yeah, I think people who are still like hanging on to these ideas that, oh, like the technology is not ready yet because like I, yeah, I tried to do something and it was like marginally too expensive or like it was marginally capable of, you know, doing the thing that I wanted to do. Like I, I think anyone who is using those as excuses to wait to get started are going to be super behind because everything's going to get cheaper and everything's going to get more capable every year. I know like, and I think this is actually not a hard sell in 2025.

• 24:53Speaker 01

  Yeah, it was this loud chorus of like, oh, you know, the progress is gonna, you know, is about to end and like, everything's going to stop and like, everybody's going to be super disappointed. Like I, I mean, there's still some people out there saying that, but like, I don't think, you know, folks are paying much attention to them anymore. Mostly because like, you know, what, what do you win by paying attention to like some crank who's saying like, you know, the, the thing's about to stop, like you're sort of betting on failure and the cost of betting on failure versus betting on optimism is like, is a real big difference there.

• 25:30Speaker 00

  Yeah.

• 25:32Speaker 01

  So, yeah, like I, I think we're, we're gonna, we're gonna see a ton of progress on like the level of ambition of problems that people are tackling with agents. And then I think, you know, modalities that are going to be really different is like, is this agentic web starts to get more complete, more plumbed out and the models reasoning and planning capability get better and better. Like you're going to start to get to the point where you're able to go from this synchronous mode of interaction with agents to asynchronous. Like right now, most of what people do is like, they sort of sit down, like they got a thing they want to do, like they issue the prompts, like, and they wait until, you know, the thing comes back and like, you know, do something with that response.

• 26:18Speaker 01

  And so I think, you know, by next year, you're going to see people using these agents to like, hey, go sort this out and like, the agent is going to take a lot of time. It's going to go make a lot of calls out to systems, like the things that it's sort of like taking action on are going to like, take a while to come back. Then they're going to like integrate all of those responses and like do something and like that whole thing may iterate a bunch of times. And then, you know, at some non-trivial amount of time later, you're going to sort of say, okay, like here's the, here's the, here's as far as I got, like now it's your turn. Like go take some action now.

• 26:52Speaker 00

  Sounds like a future I want to be in.

• 26:54Speaker 01

  Yeah. Yeah, me too, right?

• 26:57Speaker 00

  Well, Kevin, thank you so much. It was really, really great to talk to you.

• 27:01Speaker 01

  Yeah, good to talk to you as well. Thanks for having me on.

• 27:03Speaker 00

  Of course.

• 27:11Speaker 02

  Oh my gosh, folks, you absolutely positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights and laughter that will leave you on the edge of your seat craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.

• 27:58Speaker 01

  Fancy.

• 27:59Speaker 00

  That's how you know it's the real deal.

• 28:01Speaker 01

  Yeah, excellent.