← AI and I
AI and I
Kevin Scott on The Future of Programming, AI Agents, and Microsoft’s Big Bet on the Agentic Web
00:28:02
Loading summary
Transcript129 lines
- [00:00]
Dan Shipper
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?
- [00:10]
Kevin Scott
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.
- [00:27]
I've been a woodworker for almost as long as I've been a programmer.
- [00:30]
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. 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. Like you've got to figure out how to plumb things through where agents can like talk to those things. Like one of the things the 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.
- [01:27]
Be curious, try stuff and if it works for you, use it. And if it doesn't, don't.
- [01:44]
Dan Shipper
Kevin, welcome to the show.
- [01:46]
Kevin Scott
Thanks for having me.
- [01:47]
Dan Shipper
One of the things that's interesting is I was here last year and, and you said two things. There are two big themes. One was agents are gonna 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. There were a lot of graphs of like we're building big infrastructure, we're building these bigger models and every two years we're gonna get these big performance improvements. This year the emphasis is really on the agentic web. So what has changed? What have we learned from last year to this year?
- [02:17]
Kevin Scott
Yeah, I think there's a bunch of.
- [02:19]
Things that have changed. Like one of the, that I think last year people were really in this state of mind that they were doubting that the scaling laws were gonna 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.
- [02:47]
And I think the other thing too.
- [02:49]
That'S happened, honestly, is that the reasoning capabilities of the mod has actually gotten a little bit ahead of what we're using the models to do in products. 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 big thematic things why scaling laws might not be be as interesting to talk about at this year's Build as last.
- [03:28]
And then the other thing too is that we've just discovered as all of.
- [03:32]
These agents have emerged over the past year. And so like, both the number of agents and like the amount of time that people are spending doing stuff inside of these agents or with these agents is 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, you know, the things that I was talking about at the keynote today at Build were, you know, 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 like, you use them for like one thing and like, you know, memory's coherent across the course of that task. But yeah, then it may or may not completely go away and like, you're starting from scratch the next time, which really inhibits your ability to delegate increasingly complicated tasks to these things.
- [04:30]
And then there's just this real issue.
- [04:33]
That 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.
- [04:47]
And in order for that to really.
- [04:51]
Be great, you need like an ecosystem that looks a lot like the Internet, where 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. Like, 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 and wait 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 like, real progress with like, 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 NL web that are like, serving, you know, the same 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 like just lots of activity in the open community and like a bunch of things hopefully getting to ubiquity so that agents can actually do stuff.
- [06:06]
Dan Shipper
Right. So I think to, to play that back, like, one of the things I hear is like, we have agents. Agents are starting to work and in order to make them powerful, agents need access. They need access to like, what? Whatever is out on the Internet, whatever is on your computer, all that kind of stuff.
- [06:19]
Kevin Scott
Yep.
- [06:20]
Dan Shipper
And you need basically protocols and processes for agents to be able to access that stuff. And so you're looking at different parts of the stack. So like the runtime layer where you're, you know, you're building like 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.
- [06:40]
Kevin Scott
Yep.
- [06:42]
Dan Shipper
I guess. Why is that important to Microsoft and like, what role do you want to play in that kind of an ecosystem?
- [06:49]
Kevin Scott
Well, look, I think there are two, maybe three things that are super important. So one is like, we make agents.
- [06:54]
And in order for our agents that.
- [06:56]
We'Re building for folks to be useful, like, we need to solve these problems inside of these agents.
- [07:02]
And like, even if you sort of scope it down narrowly to enterprise agents, like, one of the things the 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 so that we're not exposing the entire world to like Conway's law, which is, you know, organization. So Conway's law is this really funky thing in compilers where this guy Conway said that 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.
- [07:41]
Dan Shipper
You shift your org chart.
- [07:42]
Kevin Scott
Correct. You ship your org chart.
- [07:44]
And so you certainly, inside of the.
- [07:48]
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, like as an engineer, like all of this inefficient building when you don't have those standard protocols and services that everybody's using.
- [08:06]
But I think if you sort of.
- [08:07]
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. And I kind of see it right now. 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.
- [08:46]
Users of these systems who want them to be more useful and for people who are providers, who are like, hey, like.
- [08:52]
I want to be participating in this new agentic web is like people are doing less of one thing, which I knew how to connect to, like how. And they're, you know, they're sort of sitting here using these agents. Like, how do I get my stuff wired up into this? And like, how does it make sense for me, like, even from a business model perspective to do that?
- [09:10]
And so like, that's the two things.
- [09:12]
It's like, make our own agents more useful and then like, we're a platform company, like even more important than the agents that we're going to write ourselves.
- [09:21]
Like that platform layer that Microsoft has been building in technology for 50 years. Like, we just want to make sure.
- [09:28]
That we are helping solve the problems that are emerging as this agentic web is happening.
- [09:34]
Dan Shipper
Yeah, it's been, it's really cool to see you guys, like 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 policy that makes sure that if a website is serving you code, it's only able to execute on its own data. And MCP doesn't really have that. So what do you think the right security model is for this?
- [10:15]
Kevin Scott
Well, look, I don't know that I.
- [10:18]
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. We have a bunch of enterprise things that we care a lot about and that we're doing really good work with with the MCP team to get done. So, like, 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, like, they are entitled to see these resources in this system. And like, even having a way for an agent to sort of 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.
- [11:44]
And like, the important thing is let's.
- [11:46]
Do it in an open way.
- [11:49]
We don't need it to be proprietary.
- [11:52]
To our agents or our systems. We've just got to figure out how to get this done where things kind of work. Like the web works.
- [12:02]
Dan Shipper
Yeah. Well, it's an interesting question for me because I feel like there's maybe two potential models or potential go to markets for AI stuff 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 in between. And the thing about that model, which maybe it's sort of, you could say the App store, Apple iPhone model 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 innovation, basically because there's no central authority. So how did you guys think about making that decision?
- [12:42]
Kevin Scott
Yeah, so look, I know that that's.
- [12:44]
The argument that a lot of people make.
- [12:47]
I think it might be a false dichotomy.
- [12:53]
There is a thing that you have in these open systems where they are permissionless, and there's a real advantage in having permissionless innovation. So the thing that, as 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 having all of these complicated gatekeeping things that are sitting in between you, who are the person who had the idea and the people who might benefit from it. I think some of these middle layers that have emerged over the past handful of years just aren't contributing much value, honestly to the two parties in the transaction that matter, 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. 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.
- [14:02]
But like, I also think that there are ways that you can get real.
- [14:06]
Robust security in these systems, like leveraging some of the AI capability that you have now where you may be able to have better security. Like if you have an agent that you are running that is attending to.
- [14:26]
Your personal security requirements.
- [14:29]
Like, these are things I'm willing to share.
- [14:31]
These are things I'm not willing to share.
- [14:33]
Like, and that has some kind of knowledge of risk assessments. And like, yeah, like for instance, like my wife this morning while I was, while I was getting ready to jump on stage, like I got this flurry of emails that, 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. I texted her, I was like, hey, are you screwing around with the configuration here? And she's like, yes.
- [15:10]
And so like you could imagine like.
- [15:12]
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, like whether that's legit activity or illegitimate activity.
- [15:29]
So I think there's just a bunch.
- [15:31]
Of stuff like that you can have both. Right? I don't think it needs to be one or the other as you framed it.
- [15:38]
Dan Shipper
Yeah, that makes sense. One other thing that I'm curious about is it just seems pretty clear that software engineering is changing. 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 you do a lot of ceramics, you make your own bags, you love having your hands in things. And I think one of the knocks on using agents for coding is 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, as someone who cares about the craft of code, looking into this future of coding with agents, how do you feel about that?
- [16:24]
Kevin Scott
Well, so let me start by saying that I, I.
- [16:30]
Love the fact that my people and like when I say my people, I mean makers writ large. So software engineers or mechanical engineers or woodworkers or potters or just sort of pick your thing where people are trying to create things from raw materials or nothing. If you are really passionate about what you do, you're going to have very strong opinions about how you do it.
- [16:56]
The tools that you use, the materials.
- [16:58]
That you use, how things get put together. It is a necessary thing for you to be great at your job.
- [17:05]
The interesting thing is people have lots.
- [17:07]
And lots of different opinions. And like one of the event 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.
- [17:19]
And so the thing that you get.
- [17:22]
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 where.
- [17:31]
The.
- [17:31]
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.
- [17:40]
And so I think the reality is that people will have choice. When I go into a text editor.
- [17:50]
I probably shouldn't say this because we.
- [17:52]
Make Visual Studio code, I'm such an.
- [17:56]
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.
- [18:07]
Like I just refuse to go use something different even though I know for sure that that is sub optimizing a.
- [18:16]
Part of what I'm doing. But I make the decision anyway because like I get to choose.
- [18:22]
And then in other aspects of my making, like either software or something else that I'm doing, I will be like, okay, the important thing here is not the way that I'm doing this particular.
- [18:34]
Part of it, it's the outcome that I'm trying to get to.
- [18:37]
And I'm going to use the most powerful or most convenient way to go.
- [18:46]
Get to the outcome.
- [18:47]
And like you Know, I don't care who's going to throw rocks at me for doing it. And like it's literally everywhere. Like 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 real woodworkers only use hand tools. 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.
- [19:17]
Tools versus just power tools?
- [19:21]
And I understand it. Like, I actually think it's interesting, the debate itself, but like sometimes like people are going to make, you know, different choices because like they value something different than you do if you value the process more than you value the outcome. Like sometimes you'll make different decisions and people who value the outcome more than.
- [19:41]
Dan Shipper
The process 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, but, but.
- [19:53]
Kevin Scott
It'S just so varied. Right. And like, so the thing that I will say is like I would never in a million years tell anyone not.
- [19:59]
To have strong opinions about their craft. Like have them.
- [20:02]
Like it's great. Like the advice that I would give people and like this is not me telling them, it's just advice.
- [20:07]
Like things that I found useful for.
- [20:09]
Myself is just have an open mind, 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.
- [20:20]
Like non software dimension of making that came along where I'm like, like I don't want to learn like 3D printers. Like I waited forever to learn how to use 3D printers.
- [20:32]
And like I regret it. Like I should have started earlier. 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.
- [20:46]
Yeah.
- [20:46]
And so just be curious, try stuff and if it works for you, use it. And if it doesn't, don't.
- [20:52]
Yeah.
- [20:53]
Dan Shipper
What do you think is the future of software engineering agents? Is there going to be one agent to rule them all? Or is it you're just going to use many different agents with different taste or how do you see that ecosystem shaping up?
- [21:02]
Kevin Scott
Yeah, look, I think it's going to be a lot of different agents and it's good to have a lot of agents. And we certainly with GitHub copilot and the GitHub agent stuff that we're working on, I think we will compete very.
- [21:16]
Hard to be a tool that lots.
- [21:18]
Of people will choose because it's very useful to them.
- [21:21]
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 is 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.
- [21:56]
Dan Shipper
What are the dimensions? Do you have an opinion on the dimensions along which the different agents might differ?
- [22:02]
Kevin Scott
Well, I think the most important thing about.
- [22:08]
Agents is probably the product making part of them.
- [22:14]
And so the most interesting startups that.
- [22:17]
I'm seeing right now are not trying to 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.
- [23:00]
Dan Shipper
Yeah.
- [23:00]
Kevin Scott
And I think honestly because it's so much easier now to like have that.
- [23:07]
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 they're interesting, like all of them. It's a lot to respond to when you're a company building software development tools yourself.
- [23:33]
But 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, people have high tolerance and high interest in giving things A try.
- [23:51]
Dan Shipper
So we're almost out of time. But I'm curious. Let's say it's a year from now. We're back at build. 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 predictions for what we're going to be talking about?
- [24:12]
Kevin Scott
Yeah, I think people who are still.
- [24:13]
Like, hanging on to these ideas that, oh, like, the technology's not ready yet because, like, I, you know, 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 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. Yeah, it was this loud chorus of, like, oh, you know, the progress is going to, you know, is about to end, and, like, everything's going to stop and, like, everybody's going to be super disappointed. Like, 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.
- [25:14]
Like, you know, what.
- [25:14]
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.
- [25:32]
So, yeah, like, I. I think we're.
- [25:35]
We're gonna.
- [25:36]
We're going to see a ton of.
- [25:39]
Progress on the level of ambition, of problems that people are tackling with agents. And then I think modalities that are going to be really different is this agentic web starts to get more complete, more plumbed out, and the model's reasoning and planning capability get better and better. 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. 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, it's 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.
- [26:53]
Dan Shipper
Sounds like a future I want to be in. Yeah.
- [26:55]
Kevin Scott
Yeah, me too.
- [26:56]
Dan Shipper
Right. Well, Kevin, thank you so much. It was really, really great to talk to you.
- [27:02]
Kevin Scott
Good to talk to you as well. Thank you for having me on.
- [27:03]
Dan Shipper
Of course.
- [27:12]
Podcast Host
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 rollercoaster 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.
- [27:56]
Kevin Scott
Deal.
- [27:58]
Fancy.
- [28:00]
Dan Shipper
That's how you know it's the real deal.
- [28:01]
Kevin Scott
Excellent.