The Pragmatic Engineer - From Chrome DevTools to AI Engineering, with Addy Osmani

Episode Date: August 19, 2026

Brought to You By:• Antithesis – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages.• Google Cloud Run – run your code and host LLMs directly on top of Google’s scalable infrastructure, without having to worry about managing infra.• Sentry – application monitoring software considered “not bad” by millions of developers—Addy Osmani spent more than 14 years at Google, working on Chrome, DevTools, Core Web Vitals, and most recently, AI developer experience.If you've ever opened Chrome DevTools, or optimized a page for Core Web Vitals, you’ve used software built by Addy Osmani. In this episode, I sit down with Addy and we talk about his path from building a web browser aged just 16 to becoming a director at Google. We discuss what he learned from building tools for millions of developers, Google’s engineering culture, and why he continued doing hands-on coding work as a manager. We also get into how he works with AI agents today, the risks of ‘cognitive surrender,’ his approach to ‘loop engineering,’ and why it’s good to develop skills in product management, go-to-market, and other areas.—Timestamps00:00 Intro02:50 Addy’s current workflow05:11 Addy’s path into tech15:04 Addy’s work on jQuery16:44 TodoMVC21:44 Getting hired at Google and working on Chrome27:17 Building dev tools40:15 Core Web Vitals45:42 Google’s engineering culture51:03 Addy’s career trajectory at Google57:55 The director role at Google1:01:40 Cognitive debt and cognitive surrender1:03:03 Working with agents1:05:52 Loop engineering1:12:55 The changing role of the software engineer1:18:15 How Addy uses AI in writing1:27:40 What’s next for Addy1:28:47 Career advice—The Pragmatic Engineer deepdives relevant for this episode:• What is loop engineering?• Inside Google’s engineering culture• How AI-assisted coding will change software engineering: hard truths• Are AI agents actually slowing us down?• How Claude Code is built• How Codex is built• From IDEs to AI Agents with Steve Yegge• Google’s engineering culture: the podcast—Production and marketing by ⁠⁠⁠⁠⁠⁠⁠⁠https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠. For inquiries about sponsoring the podcast, email [e-mail]. Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe

If you've ever opened Chrome DevTools or optimize the page for Core Web Vitals, you've used software built by Adi Osmani. Adi spent 14 years at Google, most of it on Chrome, going from software engineer to director of engineering. And when starting out in tech, as a teenager in rural Ireland, he built his own web browser from the ground up. Today we talk about the inside story of Chrome DevTools, why it became the closest thing Google has to an IDE

and the problems that are still unsolved like memory debugging. What becomes different when you become a director at Google and how Adi stayed hands-on building software while building an engineer org with more than 50 people. How AI is changing software engineering, cognitive depth, cognitive surrender, loop engineering, and software factories, and many more. If you want to hear from someone who has spent decades helping developers understand the web and is now thinking deeply about how AI changes software engineering, this episode is for you. This episode is presented by antithesis. If you work with agents, your job is no longer just writing code, it's specifying and testing it.

An antistesis is the most effective method of verifying agentic code today. Before we get into Addie's journey at Google, I wanted to talk about a really cool product at Google, Google Cloud Run, and their recently launched Cloud Run Sandboxes. When you're building AI applications or AI agents, you often want to run untrusted programs like execute some Python code the model generated, or run a headless browser to fetch data from the web, or even execute code submitted by a user. But how do you make this fast and secure? This is exactly what Cloud Run sandboxes do. Cloud Run sandboxes are ephemeral, isolated GVisor environments that spin up extremely fast. They were built with security in mind. They enforce credential and environment isolation. Basically, they have no access to your services environment variables or secrets.

Sandboxes also operate with log-down network egress, denied by default, to the internet. Accelerate development, eliminate infrastructure toil, and run interested workloads with confidence on Google Cloud Run. Try Cloud Run sandboxes today at cloud. Addy, it's so nice to have you in person on the podcast. Oh, thank you for having me. And before we kick off into your career and how you got started, I wanted to ask just before we started recording, we were talking about how has your day-to-day workflow changed recently

a bunch thanks to all these tools? So agents have allowed me to take the improbable and turn it into the possible in ways that are kind of weird and wonderful every day. I manage a lot of my life now using agents. And one example, just from, you know, this week we've got the AI World Fair happening in San Francisco. I'm doing a closing keynote a couple of days in. And so I wanted to make sure I wasn't repeating any beats that other speakers had gone into depth then. And I also wanted to make sure there was good connective tissue from my talk to a lot of the other sessions that had happened.

Now, normally in the old days, you kind of pray and hope that there was any content from these sessions online. and maybe you'd look through the abstract, I was able to fire off a bunch of agents, you know, go through everything that you can find about the talks from the last couple of days, look at the abstracts, any social content, anything around that that can be useful. And that was able to help me kind of sculpt what I already wanted to talk about into something that I hope is refined and will give people a way to connect from other parts of this conference back to, you know, the way that I'm going to close it up. That for me just feels very empowering, you know, something that would have taken a very long time.

If I would have even been able to do it at all is now very much within reach. And then you mentioned that it feels like, and a lot of people tell you, like there's kind of like both fun and chaos at the same time right now, like everywhere, right? Yeah, yeah, absolutely. Fun and chaos. I think that, you know, for many of us, when you have a lot of ideas or a lot of vision, you're often bounded by time or how much can I actually do. and in some ways agents have unchained us. And this is one of those reasons why, you know, you keep hearing, oh, hey, what are you doing with all of that time?

Agents have freed up while I'm doing more work. I think for many of us, if we didn't enjoy it, we wouldn't be filling that time up with work, but we're having fun with it. And so it's fun thriving in that chaos. Yeah, but now take me back to the very beginning. A lot of us know you and I've gotten to know you when through your work at Google, through your books,

but I'd like to start from even before. Where did you start out? How did you have your first contact with computers and how did you build a web browser when you were a teenager in high school? So I've always been fascinated with understanding how things work. And I grew up in rural Ireland, which was at times, you know, we didn't necessarily have the best internet connectivity. This was back in the days of dial-up. And so my first contact with computers was, I was probably eight or nine years old. We were very fortunate that my dad was able to get us our first desktop machine. And, you know, I'd play around with apps. I'd play around but just like trying to browse the internet.

And it was always fascinating to me, like, how does any of this work? I'm just typing in something into an address bar and all this information is just rendering somehow. I'm getting back text, photos, videos, like, how does any of this stuff work? And so over time, like I would build out websites. I'd start to get into programming.

My very first programming language was Pascal. So I'm a big, big fan of the Borland Tool Suite. I learned C++ when I was fairly young. And there was one year when I noticed that we had a kind of popular national science competition. And traditionally, that competition was very much about, you know, hey, do two, students have interesting breakthroughs or thoughts on physics or chemistry or any of those things. But the year that I'm talking about was the first year where they actually started to really take computing seriously. And as I mentioned, I didn't have the best internet connection.

This was also during the time when especially if you were a teenager, you started to get into learning about downloading stuff. And we didn't have fast internet connections back then. if you cared about, you know, checking out a song, you could be waiting hours for that to download. If you cared about trying out a music video, man, that could be a night, two days sometimes, to download it. And so I tried to study how these kind of download managers that were popping up worked. And download managers kind of offered this one hook. Well, rather than making one connection to a server, what if we spawned, multiple threads and made multiple connections to a server, and we kind of chunked content.

You know, it's classical computer science, you know, breakdown problems into smaller chunks. And so that was one of the ways. And if the server supported, you know, chunking, you were able to, in some cases, actually get your file downloaded a little bit faster. And so it dawned on me like, hey, we're using this technique for downloading individual files. has anyone applied this to how we browse the web pages? Yeah, and so obviously I couldn't, you know, do something complicated before I, you know, took my first baby steps. And so I thought, okay, I'm going to try exploring how you build a browser. I started to read, you know, specifications.

I was probably 15 years old when I started this, 15, 16. But I started to read specifications. Okay, HTML, CSS, JavaScript. one of the things that I gained a great deal of respect for, and I still have a lot of respect for, is developers throw all kinds of weird crap at browsers, and yet they still render something, right? If you ever want, you know, if you ever want an interesting experiment in therapy, if you're ever feeling bad about your code, open up the dev tools and just browse the web for 10 minutes. the number of things that will go wrong,

and yet you'll still be able to probably interact with the site, is just wild. And I had that... And going wrong, you can just look at the warnings and errors, honestly, just after. And so that was one of the most complicated things when I was trying to build a browser. It was like, yeah, you can parse HTML, you can parse documents, you can load up images.

But as soon as you run into pages that stop following those specs, and they take a very loose interpretation of what's supported, you have to really, you know, roll your sleeves up and try to behave the way that actual consumer browsers did. And so I had my fun building out a browser. Adding interactivity and JavaScript support was very difficult, managed to get it working. And then I'm a sucker for pain because I decided,

well, I guess Applets and... And Flash, and, you know, we had Windows Media Player back then. So people were, like, embedding all kinds of interesting content. I told myself, well, it's not a complete browser if it doesn't support all these other things. And so I added support for them. And then I could finally get on to what I actually wanted to work on, which was exploring if I could speed up web browsing for this point in time when you were kind of constrained by the hardware and bandwidth that was available locally. Back then, this was a personal pain because before I could get a good internet connection, I would literally every weekend, especially weird cargo pants that had a lot of pockets,

and I would fill my cargo pants with floppy disks. And I would walk down to our local library that just happened to have a slightly faster internet connection. And I would try to save as much as I could than go back home, check it out on my computer. And so this was a personal mission for me. I really, really wanted a faster internet connection. But I finally got to explore this idea. It worked. And in some, you know, back then, in many cases, there were servers that supported this idea.

It did make things a little bit faster. And so I, you know, I ended up building something that worked for me. I took it to this national science competition. I was nobody. I am nobody. I was nobody. I was just this kid. And I was kind of half expecting to just.

leave the competition and go back home at the end of it and say, like, yeah, you know, I showed some people some cool stuff. There was like a big live audience at the tail end of this whole event. It was, you know, on live TV and everything. And when they called out the overall winner, I was shocked because I didn't expect to win this thing. And that was my kind of first taste of media attention. It was very strange. The weekend right after, you know, you're a kid. You kind of like want to sleep in. on a Sunday morning. You don't really have too many people back then, like, calling your cell phone or whatever. Yeah. And my cell phone is just, like, not stopping. The first call is, like, from the Wall Street Journal. And basically, you kind of, like, went viral in a time where there was

not even Twitter, right? Like, there was, like, none of this just yet. Yeah. It's like, yeah, it's, Wall Street Journal, CNN. It's, I didn't really understand what was happening. But it was, it was my first taste of that world. One of the things that I learned from that experience was I still didn't fully understand everything that I was doing. You know, you're a teenager. Just because you can build an app that runs on your machine and accomplishes a goal, doesn't mean that you understand all of those layers behind the scenes. And that, I think, kicked off for me a lifelong thirst for knowledge and understanding how things work. In some ways, I can call myself a one-prick pony I care about understanding problems and how, you know, how to fix them, how they work behind the scenes.

I would go on to work at startups. I worked at AOL at one point, again, continuing this theme of working with browsers. When I joined AOL, at a very AOL moment, my first day, my manager was a very kind guy, I said like, hey, yeah, you know, go help the team. Just log against the browser, go help the team. It's like, okay, cool, I'll do that. So I fire up the AOL browser app and I have my work machine. This app is loaded up. And before I can debug anything, the first thing I'd ask me for is my credit card.

I'm like, I'm sorry, what? I need to enter in my credit card to even start my work. And my manager was busy. So I don't know if there was like some work around. I was like, okay, I guess, I guess this is what I need to do to get started with work. Wow. Different time. Very different time.

But two years later, I would join Google and I would, work on Chrome. But something for me that's been very interesting is, you know, if you treat computing as this onion where you just keep peeling back the layers, there's always something interesting behind the scenes. And the more of those layers that you can peel back and understand, I think in some ways, the better you can optimize for that world. You know, there's a time when I maybe only understood the surface of how things render. But if you're talking about browsers, you know, there is the network, there's compositing, there's the JavaScript engine, you go down another layer, there's chips, there's memory, there's GPU. And the more you understand about

all of these different foundational pieces, the better you can then optimize and build something that, you know, conserve people even unconstrained environments. So if you have a slightly slower phone, well, I understand now why the phone is slower and what constraints might require us to to think slightly differently about what we're building there. So I'm always a big fan of encouraging people to understand how things work. And then in the spirit of understanding, one project that you got involved on early on, you built your custom browser that did some cool stuff

and you understand how to render, parse, do some of these things. And then you join into the JQuery project. How did that happen? Yeah. And in JQuery for a while after you joined, it became for a while the most used library in the JavaScript ecosystem. So basically across the web, there were a few years of that. Yeah.

I think full kudos goes to John Resig, the creator of J. Kriri. Jay Kri was really my first contribution to a big community open source project. And John was someone that was very welcoming and created an environment where people could, you know, learn and become better open source contributors. I started off working with the team of people that would deal with triage and issues and then moved on to like working on blog posts and contributing to code in other ways. But as you said, it was so widely used that you end up with so many different use cases people have.

And a lot of the times back then people would have very strong opinions about like, hey, this thing should be in the main library in core versus being a plugin. And I got a lot of respect for how you effectively work with a community while also holding a line in terms of, you know, what decisions should be made to optimize for long-term maintainability, for example. But it was a great experience. And that helped me kind of carry those lessons on when I worked on my own open source projects. I was very grateful for that opportunity. Yeah. And one of your popular open source projects back in the day was called To Do NBC.

Yeah. Can we talk about what it was and what you started? Yeah, absolutely. There was a point in time back in the dark ages of JavaScript when we didn't have frameworks and we didn't have libraries. Over time, those things started to pop up and we began to have quite a few of them. And they all tried to accomplish in some cases overlapping goals, sometimes adjacent goals. And we're talking about angular and backbone.

Angular, backbone, YUI, XJS. And if you're too young for any of these terms to mean anything, that's also totally okay. But there was this burgeoning community of libraries and frameworks that were starting to pop up. And one thing that I personally struggled with was, well, how do these things differ? You know, you can go and you can check out

the landing page for any of these projects. And they all say, like, yeah, we're going to help you build apps, you know, easier. but I was very big into education and trying to understand how these things worked. So I started off by creating basically the same application in every one of these frameworks and try to standardize the functionality so that if you were in the same position I was and you just wanted to get a sense of, okay, well, how does the architecture philosophy change

between these things? How does the syntax differ? if they're telling you to build a component or a piece of UI, what is the position they're taking on it versus somebody else? And so I got a lot of personal value out of the way that I was building this thing up. And so I put it out into the world. I had no expectations of it being useful. But basically it was you implemented a to-do app or the same to-do app

with the different frameworks and you could kind of compare how they defer. Yeah, yeah. And the idea was I wanted an application that was simple enough for almost anybody to be able to use and reason about, but it needed to have enough interactivity and enough functionality that you could really kind of stress test at least some of that functionality of framework offered. In some cases, you know, that would be state management or routing or other things. And so I put this out into the world. I was kind of shocked at how many other developers were running into this exact same challenge. And the project quickly took off.

It started to get a lot of stars back in the day. It got thousands and thousands of stars very quickly, and I didn't quite know what was happening. And before long, I had people who were working on new frameworks or new versions of frameworks reaching out to me, saying like, hey, this is cool. here's my pull request with my framework. Can you add it? Can we work together on standardizing it? I met some of my first true open source friends through this project, people who are now,

you know, very well established in their own means like Cinderasorhus, who's written quite a lot of node modules over time. This idea of just giving people a simple enough application ended up becoming in some ways a standard for a number of years. I began to see that, you know, if a framework was giving people a tutorial about how to use them, they would actually use it to do MVC app as their baseline. It's been so many years. That was at the start of my career in many ways. Even this last year, I still see labs sometimes,

like showing off to do MVC apps when they're trying to test out features. And the longevity of this thing has been very surprising to me. Another thing that was surprising was at one point when the project was taking off, Apple reached out to me. No way. Yeah, Apple reached out to me, specifically the people who are working on Safari and WebKit, and they said, you know,

hey, we're interested in working on a browser benchmark to help browser vendors understand, like, are they doing a good job at being responsive? And responsive here doesn't mean responsive in the mobile sense, but responsive in terms of interactivity and are we responding to clicks and taps quickly. They reached out to me and they said, hey, would you like to collaborate with us on this thing?

And what that turned out to be was Speedometer. Spidometer, over the years, has become the primary responsiveness benchmark, web application benchmark for all browsers. And it's continued to be for a very long time. Browser vendors now collaborate together on it. They've kept it up to date. So as new frameworks, as new architectural paradigms have come out over the years, they've kept updating it.

And that in many ways is carried the legacy of that project through to today. And I've been just very happy that it's given people value of any kind. And you're building, except on the side, you're also working at consultancies,

AOL, at different startups. How did Google come along? So Google was an interesting one. I remember one of my first longer periods of time spent in the U.S. was when I was visiting, my wife and her parents out in the Midwest, and I was sitting, I remember, in their room watching TV, and there's this documentary about Google that came on. And they showed, like, you know,

early engineers that have been working there and why they enjoyed the environment. And I told myself, you know, I would love to work in a place like that someday. I continued to put out free education into the front end world, it's JavaScript world, web app world over the years. And at some point, I guess Google noticed that it was useful to some people. And so they reached out and wanted to interview me for a dev rel and builder role. There was some tooling that they were trying to build out at the time that they thought could be a good use of some of my skills, but also some just general evangelism,

they wanted to do in the tech community. And, you know, the stars aligned just happened to work out. And I ended up working on the Chrome team. And then when you join, can you tell us a little bit more about when you're the Chrome team? What was Chrome like? What kind of work did you and the team do? Because now Chrome is synonym for web browser.

I know there's other browsers. And every now and then, of course, they have some market share. But Chrome has largely won the market. but back then when you joined, this was not the case just yet, was it? I remember back when I joined, it was a period when we were very excited about developers bringing their creativity to the platform.

So what can you do to push on the platform and show us both what's possible as well as the gaps so that we can potentially help fill those gaps and build better APIs. So I remember there was this great Chrome experience, site that we had back in the day where we would, you know, sometimes work with studios or work with developers and just showcase like, hey, here's a cool WebGL example that maybe you wouldn't have otherwise come across. And that served as inspiration for some people.

It's maybe even go and then learn more about shaders or, you know, different libraries. It was also a period of time when I would say front-end tooling was still very much heavily evolving. You know, for- We're talking in 2012, 2013. Yeah, we're talking 2012, 2013. This was at a time prior to what I would now call meta-frameworks. So like NextJS, for example, a meta-framework.

It did not exist. So we're going all the way back to a time when we didn't have the best build tools, even for front-end. We didn't have... We didn't have things like ES build even. Yeah, we didn't necessarily have well-standardized JavaScript modules, you know, in all browsers. people were still using, you know, AMD and UMD, common JS, things like that. And, you know, the built tooling and the scaffolding tooling was still very much evolving. And so this was the period of time when you went through things like grunt for anyone that, you know, maybe we're dating ourselves, but grunt as a built system.

And also when you debug the browser, you would use Firebug. You would open it in Firefox and then hope that like an I.E. it would work, but if it didn't, there weren't many good debugging tools in IE specifically. Later, they became better, but back, there was a time where there was no. Yeah, and I think that, you know, back in the heyday, there were a lot of workarounds people were trying to apply to still have a toolbox of some sort before things got much better. We put some work into working with, you know, the folks who were building out build tools and test runners and scaffolding tools. We worked on our own contribution called

Yeoman back in the day. And Yoman was really about, I don't know that I'd call it the first meta-framework, but I would call it an attempt at trying to bring just a little bit of organization to your starting point.

Yoman was a scaffolding tool we created where you would get a wizard in your CLI and you'd kind of say, well, yeah, I'm trying to build this thing and maybe I'm interested in using this UI library and this testing library. and maybe I'm interested in deploying to this target.

Now, for folks who are listening in, those ideas might now sound very standard and things that you will find in all the tools you're regularly using. Back then, they didn't exist. And I wouldn't be surprised if many of the modules we created back then are still being used under the hood for some of your favorite tools. So it was very fun getting to be a part of that moment where we were trying to figure things out and reduce friction.

But I will say that, you know, there was this long period where we kept changing tools, what felt like every once in a while, right? You went from grunt to gulp to webpack to, you know, to Vee, roll up. All these things kept evolving. And I was happy to see the evolution. But I'm also happy that things in some ways feel like they've stabilized. Yeah, there was, I think it was churn, but I mean, that's when innovation happens.

Did you work on Google Chrome DevTools? Yeah. How did that start? Because I remember in 2012, I'm not sure if there was DevTools, but again, there was the state of the art was Firebase. It was, I think it was open source. It was actually just superior debugging on the web to anything before. And I'm not sure at what point, but I do remember, you know, Chrome DevTools slowly started

to emerge and it started to bring a bunch of new stuff. Like you could do performance monitoring, some of those things. Can you tell me from the inside? How did it start? What you built, how you figure it out what to build? Yeah. So I have to give a shout out to Pavel Feldman, who was the tech lead for ChromeDeft tools and really played a very large role in helping it come to be originally. There was this

period of time when, you know, Chrome was trying to figure out how it differentiated its developer tooling story from WebKit, where we had the, you know, Safari inspector, the WebKit inspector. And I think there's a very specific direction that was developer-centric and cared about the ecosystem that Pavel and his team were trying to help out with. And I noticed that they had a very good relationship talking to not just developer evangelist. This was the time when we had really sharp minds like Paul Irish around also, like working very heavily

with the Kremdev tools team. We would later have folks like Paul Backhouse, who is now known for things like impeccable, the impeccable skill for design. And I feel like one of the nice things, things about that period of time was you had these people who were web developer archetypes and were builders on the side, myself, Paul, the polls. And we would try to bring those insights to the DevTools team and help them understand, well, here are the areas of friction that we're running

into. In some cases, you can't just build tools to help you out with them because you don't have the underlying instrumentation. And so I was very happy to see things like performance tooling heavily evolve over the years. The DevTools Performance Panel is just an amazing piece of technology. The fact that you can just hit record, start interacting with your page, and you get a flame graph,

you get very deep tracing about where all the time is being spent, and that continued to evolve over time. And then we had, you know, really hard problems. Some of the hardest problems have been around memory, right? I would say sometimes,

I don't know if it's controversial, that very few developers understand memory management. And that makes it even harder to debug memory problems. And so the state of the art around memory debugging hasn't evolved all that much over the years. It's a hard problem. The DevTools team tackled a lot of interesting hard problems. Can we talk about a part that were you brought in something new?

Because debugging memory, just back in a day, it's pretty much, I mean, if you have a language that has, let's say, heap, you can try to visualize what's on there. you can attempt and maybe be successful at allocating which variables there are. And then you can try to also, I mean, some variables are the easy part. There's also stacks. And, you know, it gets a little bit messy, but you basically have a memory and you're typically interested in what is growing. And there's a part that I don't know that.

We got too far on that. But you're kind of trying to see, is this getting bigger? What are the loops? Where is my stack? Absolutely. I would say that there are a few interesting arcs where we were seeing, you know, ourselves and developers externally running into certain kinds of friction and, you know, work with the DevTools team to try evolving some tooling in that direction. One of the big arcs was embracing the fact that developers were increasingly using frameworks and libraries to build for the web. Yep. Now, for anyone that remembers those dark ages, imagine that you have a page that's very interactive.

It's using lots of different libraries, and you're trying to debug what's happened. What part of that code do you actually care about? Do you care about the framework code that is powering things behind the scenes? Do you care about the plugins or the components sitting on top of it that you haven't written? Do you care about the code you yourself have written? And so you have all of these very nuanced aspects of debugging that need a solution. One of the things that we tried to introduce was just this respect and understanding that, yeah, developers are going to be using these different tech stacks.

You know, we had a source maps story sitting there where potentially we can start to reason about what's in. You can map back to like what part of the code, which is not trivial. Exactly, which is not trivial. And a lot of kudos to the team because I think we ended up on a source map story. that really helps you reason well about, you know, even if you were using a long tool chain of things, like if you take a look at any tools that developers, for any big site, you know, whether it's Uber or Netflix or any large Twitter, any large site, you probably underestimate

the complexity and the number of tools that you're running at any one time for any one task, you know, and being able to still allow people to see, well, hey, here's actually the files that you care about. It's a hard problem. I think that allowing people to get that view, was part of the value that we brought. We introduced different kinds of black box views over the years so that you could say, well, hey, actually, I know that I don't care about you telling me there's an issue with, for example, the React library,

but I do want you to tell me that there's an issue with the React code that I wrote. And so giving you even those toggles, those controls, I think was very powerful for people. Mobile was another big moment that changed everything. And, you know, if you think, Think about mobile, today I would say, you know, there's probably established best practices around the things to test, right?

Like you want to test out your viewport with your tap targets. Like is, you know, if I'm tapping on something. Exactly. Is it big enough? Exactly. You know, there are all these different kinds of sensors even that mobile devices have. We didn't have tooling around any of this stuff originally. And so we ended up building out a nice device mode in DevTools that would allow you.

allow you to preview, you know, what your site would look like at different viewport sizes. You can very quickly kind of toggle and say, yeah, this is what it roughly looks like on an iPhone or a pixel device. And of course, you know, the absolute best kind of testing would be trying it out on one of those apps, those accurate devices. But even to quickly get a sense of whether you're heading in the right direction was very valuable to people. And we would evolve that over time as more of those best practices started to establish. I guess the web apps growing up, so PWA's progressive web apps. There was a period of time when, you know, people really wanted to make the web competitive compared to native. And so you think about, well, what are the things

that are missing? Well, you need a really good story for offline caching, push notifications, background, sync. all of these capabilities that, you know, we didn't necessarily have a strong story for. And because these are non-trivial features, you need to have a debugging story around all of them. And so we help build out the application panel so that you can go in and for any of these features, whether it's debugging service workers or it's debugging your cache or debugging any of these things, you're able to do that. And so even though the tool set has expanded over time for each of these eras, I feel like DevTools has been able to keep up, especially as the APIs in the browser has also been

evolving over time to meet these moments. Well, it's interesting because I usually, when I look through different companies and their strengths, Microsoft is amazing at building IDs and so as, for example, JetBrains. But for Google, I never felt that Google was any good at building IDs except for inside of Chrome. Like, whenever I have to debug a web application, I, I always, the past many, many years, I use Chrome DevTools because it had, I mean, the kind of debug functionality I'm used to having Visual Studio have, which is breakpoints, conditional breakpoints, all sorts of so many debug options from as you, as you just had performance, memory, being able to simulate some of those things.

So it's very interesting for me to see that it's almost as if I'm not sure if this was you, your team or Google as a whole, but they realize the browser is very important. And so they built like almost like an, it's almost like an ID in. of it. You can edit the things in line. And I think as engineers or as developers, unless you work in front and you never really noticed this, but when you do, it's fascinating how it came together. Yeah, it's really fascinating. And I think that are we an ID? Aren't we an ID? Is that a direction we want to go in? It was always a hot topic for the team. And I think that where things kind of landed was, well, we want to meet developers where they're at because you're always going to

have your favorite, you know, editor. Now we're talking about, you know, your control planes for your agents. You're always going to have a different surface, right, that you want to primarily work in. And as long as DevTools can meet you where you're at and be useful, I think that that's been something the team has tried to do. We continued having other eras. Jan Gao became our next tech lead after Pavel and helped us through the era of trying to figure out AI is now in the picture. and we want to both be able to help humans reason through this massive amount of data that the browser generates for you, as well as make it possible for you to connect your agent up to Chrome and DevTools and be able to have it just automate a lot of these journeys

for you. And so I think that for the first of those problems, I remember anytime I would work with a big site on their performance problems, you could easily spend half a day, you know, just looking at traces before you've even written anything. fixes at all. And now that we have LLMs, it's very quick to reason through massive stack traces and actually be able to get down to fixes you can make. And that's just been really, really wonderful to see it happen. Adi just described using LMs to go from massive stack choices to working fixes, which is the perfect moment to talk about our season sponsor, Sentry. You probably

already know what Centries because you're a developer. If not, just ask a devend they'll tell you. I use Century to monitor the back end of the pragmatic entry for any and all errors. Of course, doesn't only do errors, they also have logs, replay, spans, profiles, metrics, and more, because they're all connected by the same trace. One new capability sentry has built that I'm really liking is the ability to fix errors. Let me show you. Here's the list of errors on my admin backend. There's a recent error on an off that I want to check out.

Let's have SEAR run an autofix for us. SEAR is Century's AI debugging tool. First, it generates a root cost analysis. It's finding some problem with HTTP versus HTTPS URLs. Cool. Now that we know what's going wrong, Seer can create a plan on how to go about fixing it. I could go and edit this plan, but I'm happy with it, so let's create an actual code fix. Here's the code fix that Seer generated.

Assuming it looks good, and in my case it does, let's draft the pull request. And boom, the pull request is created, ready to merge. What I love about AutoFix is how Sentu went from showing a list of errors inside my application to offering me a fast way to fix it and close the loop while I say in charge. of this bug fix the whole time. Debugging just got a whole lot faster and a whole lot easier. Check out Century at Century.I.O. slash pragmatic and start detecting errors,

diagnosing their root causes, and fixing issues and regressions today. Addie mentioned things that change when we work with alum's. One thing is for sure. If you work with agents, your job is no longer writing code, it's specifying and testing it. And this leads us to our presenting sponsor, Anticisys.

Antisysis is the most effective method of verifying agentic code today. Let me explain how it works. Anticist runs your whole system in a hostile simulation. By doing so, it finds every bug before your users do. And because the simulation is fully deterministic, Antistis doesn't only find bugs, it gives you a perfect reproduction of every issue. To create such a tool, the Antistis team needed to invent new kinds of debugging tools as well. For example, here's what's called the bug probability graph.

The X axis is virtual time and the Y axis is probability. As Antistesis runs the hostile simulations, it plots timeframes when the bug probability increases, which greatly helps with finding a root cause of bugs. And Antisyses also has a log visualizer. Vertical lines going down represent events branching off from the same state, and the purple dots are where the book happens. Anticistis is as good as it gets being able to ship agent-written code. It's what teams at Jane Street, Fly.I.O. and the Etsy community use to ship with full confidence.

Head to Antisysc.comptac pragmatic to learn more. And with this, let's get back to Addy and talk about core web vitals. And one area that you really pushed, you and the team pushed the industry together, is core web vitals. You know, these are a standardized set of metrics to just figure out the real world experience the web pages. And some of the, you know, before this, again, you would, as a developer, you would measure like, right, how quick does it render or how quick does it download? It was very simple stuff. But you introduce things like LCP, largest contentful paint, CLS cumulative layout shift, FIE first input delivery. and then IMP interaction to Next Paint.

You were there. How did the team come up with these things? If you're not a web engineer, it takes a little time to understand them, but it does actually explain how users feel. I feel you somehow, inside of Google, managed to connect the kind of feel to a number. I think that the Chrome team has always had an appreciation

for user experience research, And again, every time there was a new moment for the web would reconsult that research to understand, well, what are users' expectations and how can we help meet them? The way that we used to reason about performance was very much like, hey, is a page loading? And what does that even mean? Well, for many people, is the page ready? But what does ready mean? Does that mean that I see it? Does it mean that I can click around it and anything actually?

actually happens. And so I think for a very long time, we had this almost nebulous way of thinking about page load times. And the team felt like it was finally time to come up with a more nuanced perspective around how we reason about performance. And so if you break it down, there are a number of key moments across the user's journey that they care about. Is it happening? Is anything loading? You know, do you see a header? Do you see a spinner? Do you see anything at all? Is there something useful there for you? So maybe that's a header image. Maybe it's a hero image. Maybe it is a hero video. Maybe it's like the core piece of content on the page. Is it useful? Is it usable right there? And all of these different moments can correlate to these different metrics. So for things like your hero image,

you can think about that as your largest contentful paint. And that's not going to generalize across every page. In some cases, the image may not be the most important thing. It might be, you know, the article text. There may be cases where, you know, you want to be able to interact fairly quickly with a page. I can remember many times over the years

when I might be shopping. And whether it's on my phone or on my desktop, I will click like the Add to Cart button and just crickets. Nothing will happen. Because JavaScript did not load or the event handle or the or maybe the event handler, was not attached because not all elements finished loading. We know as engineers what's happening, but as a user, it's like...

Yeah, as a user, like, wait, what's happening? And this stuff can happen where you just tap, tap, tap, tap, the event handler gets attached, and now you're adding it like twice or three times, but you don't know. Yeah. Humans are shockingly simple. You know, if you think about the experience you have with somebody that's just trying to cross the street, If the light doesn't turn, you know, it doesn't say they can walk fast enough, they'll just keep hitting that button. That's the same experience they have on the internet. I think that there were other aspects of user experience that I think we acknowledge we're actually kind of problematic.

One big one was over the years, obviously sites tried to monetize as heavily as they could. And so you would see not just Bannerat, but you'd see modals, you'd see all of these things thrown up in front of your face. and even if you set aside, you know, maybe there's some validity around a business needs to monetize, those things shouldn't cause a really bad experience. If I'm on a page that has a bunch of ads, I shouldn't start reading an article and then suddenly everything gets pushed down, right? Just because the ad is finally loaded. And so that's where cumulative layout shift kind of comes from.

It's this idea that, hey, we should be trying to keep that page stable so the user has a good time. there was a lot of iteration around how do we define these metrics in a way that captures a few of these different use cases that are very nuanced because the internet is not all that homogenous. There are lots of different ways that a person can think about the value of a page and what's important. And so the team did a lot of experiments, experimented with lots of different ways of thinking about these metrics and worked very heavily with both the standards community and developers to validate like, hey, do you actually believe that these things line?

up with how you would say you think about the value of your pages. One of the things that I always find fascinating is there are some companies where, you know, they have thought from the ground up, like if you start from a blank white screen, what is actually important to the user end to end? And then there are many companies where they haven't, for whatever reason, time or they just think about it, they haven't gone through that journey. And so Cora Vitals allowed them to finally get a more nuanced conversation going about, like, hey, what's actually important to us?

How can we make sure that whatever key action the user has to take, they can do it pretty quickly and be guaranteed that they're not going to have a bad time. You spent 14 years inside of Google. Most of it was inside a Chrome organization. Later, you moved over to Cloud AI and work with Gen. AI as well. We've done research before on Google's engineering culture. But can you summarize what it felt working there in terms of what,

and especially comparing to the startups that you worked before, You also talk with companies now outside of Google. What were things that are uniquely Google? As part of my Google journey, there was a lot of work that I did on the developer side. There's also a lot of work that I did on the consumer side. So working on Chrome Performance, for example. And when you're working on something that goes out to billions and billions of users, which is the case for many Google products now, the way that you think about engineering

culture, velocity, experimentation is very, very different, I think, than sometimes how a startup might approach things, especially if you're trying to move very fast. When we try to make a change inside a browser that has a global audience with a lot of people, there's a lot of experimentation that has to happen. And a lot of experimentation that also requires just like testing out, well, hey, does this problem not have one solution, but actually a couple of different ones, depending on what market you're in. And how do you evaluate success when maybe we have 20 other experiments

or 100 other experiments happening at the same time? And so the AB testing culture, I would say, was a very big thing. And kudos to the Chrome team for having what is now, I would say, a fairly stable and rigorous process for being able to try those things out in the real world. I also felt that,

even though sometimes from the outside it didn't necessarily always come across, zoomed out at the Google level, I did feel like there were many people that cared a lot about developer goodwill and developer sentiment. But when you have a very large company, obviously, you're not, you know,

it's going to be very challenging to have every group talking to every other group. Impossible. We always made best efforts to try, you know, getting to a place where we were doing the right things for developers as best we could. But I was glad to see that sentiment and that level of care for the community and for our users. I also appreciated that Google was open to change.

So I would say if I had to summarize my one big change contribution to Chrome's culture, it would be meeting the developers where they're at. And that embrace of people are going to use whatever tech they want to use. You can't tell people what they use very often. They're going to use whatever they want and your job is to help them be successful on your platform and to help their users have a great time. I think that there were a lot of decisions we made over the years that helped make that a little bit more possible. And, you know, we had good collaborations with different framework teams. We took their feedback about APIs they would like to see in the platform.

It became a lot more of a collaboration with the community rather than kind of guessing what we thought, you know, the community needed to be successful. And so I was very happy to see that happen. I would also say that Google was very good at allowing different parts of the company to share their learnings towards some point of convergence. So for example, the software engineering of Google book, one of my favorite books, I was very happy to see different flavors of that over the years internally at the company. Because you work at such a big company.

you're always curious, well, what is best practice? Right? Like, is there a best practice? So they were like in general writing, like, here's how this org is doing some parts of software engineering or building or experimentation or whatever. Yeah, one of my favorite things to do was, you know, I was curious, well, my team might have a perspective on testing or user experience.

But how does the YouTube team think about it? And are there parallels? Are there things that we could learn from each other? And there certainly were, you know, Even looking at how other people think about the world can sometimes lead to collaboration opportunities. We actually worked with the YouTube team to improve their core vitals at one point, you know, and they were excited to see that they were just more refined metrics and ways of thinking about experience. I mean, I guess it's just important to point out that this collaborative nature is not a given in any,

in all large companies. There are some companies don't want to name names right now, but where organizations don't feel that they're incentivized to work with each other because they might have different goals. And it's not that they hate each other. They're just like focused on themselves. And it can feel a lot more, I guess, political in that sense. Yeah.

We talk a lot about high agency these days. And I think that sometimes when you see those collaborations happen, it's because there are people with enough agency on both sides that they want to make it happen. And they see the mutual value in collaborating. Because exploring, you know, how to improve the user experience for something like YouTube, it was extremely nuanced, extremely educational, very nuanced, but also took a very long time. And we just felt like the value was there. I was glad that we could make it happen, you know. Can we talk about your specific career path inside of Google? So you spend 14 years there, which is a very long tenure.

And I'm starting to develop a bias for like, it's nice to have long tenure somewhere at some point in your career. There's a lot of values you were just talking with Simon, the founder of TurboPuffer, about this earlier. What level did you get in? How was your career progression? At what point did you become a manager? And how did you think about things like career compensation, growing? Yeah. So I started my Google career back when I was living in the UK.

Oh, nice. So he joined Google UK? Yeah, I joined Google UK originally. And I believe I joined at a level four. Yeah, that was the mid-level software engineer. Back then. And I was a developer relations engineer. So a person that's in Devrel,

but you're a little bit more focused on, you know, the builder side of things. Over the years, I kind of got promoted in that role to like level five and level six. I became a manager within Devrel. When you were at level six at the staff level. Yeah. And then I was leading part of the Devrel team.

And at some point, maybe five or six years in, I started to feel like, you know, I loved doing developer relations. But I'm very much a builder at heart. I love, I love engineering and I love product. I love all of it, you know. But I get it. I was very curious, you know, what would we like to be on the other side of that? Because I'd been in engineering prior to Google. I hadn't been in an official dev rel position prior to that.

And I was interested in going back down that direction. And so over the years, I transitioned back into kind of software engineering and specifically like an engineering manager role. That gave me the flexibility to both do like engineering work, but also manage teams. But you just had a smaller team at that point. At the start, had a, um, had a, smaller team and then it grew out. I would say the average at one point was probably in the 45s to 50s. I think that depending on where you are in your leadership or manager journey,

success means different things. And not success from a career perspective, but just success for the organization. Because ultimately what you want to get to is a place where ideally the team is almost self-sufficient. And I write about this a little bit in my book, Leading Effective Engineering Teams, but you want to get to a point where, you know, your machine, your org, is self-sufficient enough that, you know, you just need to occasionally tap the blimp, make sure that things are working. You can course correct if it's not, but that frees you up to then focus on the next important sets of problems that the org needs to, you know, tackle heads on. And that allowed me, for example, to really get deep into thinking about, okay,

well, model quality is starting to get better. What does that mean for developers? What does that mean for developer tooling? What does it mean for how we think about benchmarks and collaborations with third-party vendors and all of these other things that are part of developer success? And so I was glad that I had that time. And then I could take those learnings back to the team and work with them to evolve us into this moment where we could help developers maximize how useful dev tools can be.

DevTools and Chrome can be for agents. So do I understand correctly that you were an individual individual contributor, you were going up the career ladder, which is somewhat expected at a large company like Google with the right mentors and the right structure? And then when you became a manager and you switched, but you decided to build a bit more, you then focused on, you still had a growing

and increasing a large team and 40 people. That's not a small team. But you try to help the team, fix any issues, help them mostly run by themselves, so that you would have some time to actually do some individual contributor like work so you can keep your hands dirty but also help the team. Yeah. So it seems like, do I understand that you just prioritize to have that time to build?

Because of course, when you're a manager, this could easily suck up all of your time. Oh, yeah, absolutely. And I don't want to make small of all the work it takes to get to that point because a lot of management is trying to work towards that point. You need to build out a team structure like. And in some cases, you have managers, managing managers, right, of other teams. And we had a global team of people. Of course, that comes with navigating time zones and coordination overhead and communication

and all those things. And so I think that we were fortunate that we were able to get to a place where the team was largely pretty effective. And we were able to create more of the space. And then I take those learnings and I try to help some of my other managers. Like, how do you create the space now for you so that you can also help us this journey of modernizing for the AI moment. So I went from L6 to L7 to director in my...

Is director L8 or L8? Director's L8? Oh, wow. So that's kind of, well, congrats. It becomes, every level becomes somewhat harder and harder, as I understand, but did you care too much about the actual levels or was it more about the work and things just followed? I think for a very long time, it was about the work. It was about the work.

But also, like, as you get to a point where you feel like the organization is in a healthy place, you do start thinking about, okay, well, next level of my career, taking on different kinds of problems. Is it more like a next challenge? Yeah, the next challenge. And so I was very much wanting to go for a director kind of promotion for quite a while, and I was working towards that. And I think that, you know, for anyone that's gone through career changes or promotions,

you know that you kind of have to be. doing the job for a while before you get it. And what kind of got you where you are is when it's what's going to get you to that next level, right? It's a different set of challenges. And so I was excited to, you know, get to start experiencing those kinds of challenges and working more across Google, you know, working more with our VP and SVP layers to try figuring out, well, yeah, what is the next couple of years or what does the next year look like for Android, for Chrome, for our different platform teams? As we're going to, you know, through these kind of revolutionary moments.

We're trying to rethink everything. I did want to ask because we have a lot of pretty experienced viewers and listeners. What is the difference in becoming a director at Google? Specifically because director, it's the first executive level. I mean, different companies call it different, but it's the first one which it might be included in terms of responsibility, wait on your shoulder, because it does feel like that feels in the management chain,

that is the biggest jump at a large company. like this. I think that a good way to think about it is when I was coming up through the ranks, your director was very often your first point of contact, as you said, at the executive level. They would be the ones who would be keeping you on the hook for making sure that any of your annual goals, quarterly goals, any of that was on track. They'd be the ones that you'd be looking to sponsor any large programs, any new projects, things like that. If things were going way off track and you were, you know, being held accountable,

the directors were often the ones that would be having review forums regularly to make sure that that whole ship is actually still steering in the right direction. And so there is an increased feeling of accountability at that level. You have to pay attention to the details. I think that you can't be successful in that role if you're kind of just letting go. And when I say like you want ideally to have a self-running org. It's not about letting go entirely at all, but it's about having enough of a system in place where you get the information you need, any decisions, any blocks that your teams are running into are surfaced quickly to you so you can help them unblock them. I think that that's really one of the biggest pieces, like making sure that the business goals

get done and making sure that people who perhaps sometimes don't necessarily understand how to connect the tech that's being done back to the business goals, like see that through line very clearly. I remember that, you know, I was doing the director role through my time working on Gemini and Cloud AI. I was responsible for some of our, like, one of our top goals for the year. You're expected to report on that every week or two and be held accountable. So you need to do, to make sure that everything happens to keep those numbers and those goals moving in the right direction. So there's a lot of accountability, I would say, that comes with that level. It sounds like it's almost like if you're juggling stuff, you're given like two extra balls,

which is like now you both the accountability, communicating upwards with XX, owning the business goals while doing everything else in terms of like running a now probably larger team, being able to deep dive into the details of keeping yourself to update. So yeah, well, I guess it kind of makes sense that there's a trajectory where if the longer you work in an organization, the more context you'll have, the more ready you often. Absolutely, absolutely. And I think an interesting anecdote that I think is worth sharing is, and I don't think this was specific to Google, one of the things I found most exciting in the last couple of years was seeing as model quality has gotten better and harnesses and tools have gotten

better, how many people that were directors or VPs or SVPs or any of these levels were actually rolling up their sleeves and trying things out. And that was, that was all. awesome to see because every week you could then have conversations with people like, hey, what did you build at the weekend? What models you're trying out? Like, what are you running into friction with? What workflows are you using? And that's not something that was happening before. Exacts were very typically, you know, focused on big company problems or big work problems. Yeah, but that's been changing in the last couple of years. Which is very nice thing to the next topic, which is how AI in your observation and experience is changing software engineering.

right before we started talking about one question that comes up to from a lot of people and you're also thinking about is this idea of like cognitive surrender let's get into that yeah so there's two pieces here the first is cognitive depth so the more that you

use AI it's sort of the erosion of your ability to have good memory and have good understanding of the problems that you're working on and the natural follow-up to that is cognitive surrender which is where you know you blindly give in to whatever the AI says as your answer.

Its answer becomes your answer. And so you start to really let go of critical thinking and your ability to solve problems just goes to the wayside. I think that that's something we want to avoid because, you know, I'm personally, I'm a big fan of the evolution curve we're seeing with harness engineering and loop engineering and software factories and all of these things.

I'm very excited about them. but at the same time, I think that we still need to understand enough about how things work so that if something does go wrong, we're actually able to fix it and not just hope and pray that the agent is able to figure things out. And it was about a year ago where you wrote about the importance of when you're working with an agent, and this was before they were as capable as today, but when you're working with an agent, re-through what it has, think through, and then when it generates a go read through that code, make sure you understand.

So, like, you're kind of, like, doing a review. Now we have a lot more powerful agents. We can now, some people work, like, multiple agents. What is your thinking on the kind of the reading, the going at the same pace of the agent? And, you know, like, because there's a friction of, like, it's now so much easier. So, like, not let go because you want to let go and have cognitive depth. It's just, like, they're faster and it's pretty good for the most part. with many challenges people run into in life,

there's a lack of intentionality around wanting to avoid them. And this is one of those places where I see this happen quite a lot. And my thinking on this has changed a little bit. A year ago, you know, maybe you would have, you know, like one thinking message from the agent saying, hey, I'm thinking in the background, and you'd expand it, and you would see a trajectory and you'd see the summary of like all the things that are happening. And it was like in speed where you could follow as well. It's like every few seconds, something coming.

Yeah. And now, if you're using quad code or codex, it's very possible that 20 or 30 subagents have fired. I am not going to click through 30 of those things to read through their trajectories, but I do make sure that I do two things. The first thing I do is I try to make sure that if there was a summary at the very end,

peer all the decisions that were made, I will read through that end to end. if there hasn't been, I will prompt for that decision process. And you have to be careful because you don't want a model to kind of BS you about the decisions that were made. Because sometimes it can just like make things up, right? It runs. And as we know, it's not deliberate necessarily, but it runs out of context window.

Exactly. There's limitations to these things. Exactly. And that goes on to the second thing. I'm a really big fan of this idea of mutual amplification. If you are working with an agent, a coding agent, there are a lot of things that you can do to make sure that the agent is getting better every day

and you as an engineer are getting better every day. There are simple things that can play into that. Things like even within the session or within this project, can you log your learnings from the session? Can you log any decisions that were made, any friction that you ran into, anything that you think is unique about how you've approached this problem that I should just keep in mind.

That's intentionality. That's like I want to understand how things work behind the scenes. And as long as you have that curiosity and that thirst for at least being just a little bit curious, I think that, you know, you can work with models in a way

where you're still preserving a little bit of your cognitive understanding about how things work. One new building block that's coming up in genetic engineering is this idea of loop engineering and Peter Steinberger wrote about it, Boris Churny wrote about it,

about running loops. A lot of us are trying to figure out what loops exactly are. You also wrote a post about loops. What do you think loops are? How should we think of them? Or is just something that is useful for a few people?

Where are you at with that? A good way to think about. So loops are part of this journey we are on to effectively create software factories or, you know, some people. A software factory meaning like a thing where you give some instructions. You're like in a factory, like,

I would like to produce a car, and then there's a fully automated factory, and the car comes out. So instead of focusing on purely the prompting towards getting an outcome, you're building the system that can do the prompting and generate the outcome, do the testing and verification for you.

And it's effectively the next step of, you know, every phase of software evolution is just like a rising tide of abstractions. This is the next abstraction. And it comes with a lot of nuance because I think that, you know, if you tell someone, yeah, create a system that will just do all of your work for you,

anyone that's been in the industry for a while are going to have obvious questions. What about quality? What are you actually, how are you making sure things aren't going off the rails? And so I think that you have to be very intentional with, okay, well, what are the parts of this where you're keeping the human in the loop?

Are you having your system flag to you that, hey, there are changes that were touched that actually, you know, are hitting a pretty critical part of the system. And you probably do want human review on this. But simply just having your loops build everything without having some guardrails around the blast radius without having guardrails around how you think about quality, I think is a recipe for disaster. I hear the analogy of self-refracture a lot of places. And, again, and of course, dark factory as well, dark factory, meaning it's, fully on in factories, lights are turned off because the robots don't need to see and you save energy and money. But one thing that I keep thinking that is off on this analogy is like, okay, in a factory

you produce a thing. It could be a car. It could be a screw. It could be something. It's there and it's done. But with software, specifically SaaS and most software that we do, it's not done. Like when it's finished, we release it to production. And that's where it crashes, the bugs come out.

So I wonder if this whole idea of like, okay, we'll have a factory that produces. the software and it does all the testing. If in production it's not connected to how it's running and having that feedback, you see what I mean? Like it's a different type of factory that we're talking about. So you hit the nail exactly on sort of the next phase of that. If you can have a system that can sort of decide what needs to get built, how to verify, how to test and all of those things, there's nothing stopping you from then connecting that up to your telemetry, up to your other systems, up to user feedback, up to any other signals that can help build out the product. You can connect it up to the product backlog. And you can potentially see a world

where you then have this system that has access to all of these different signals for how the product can be improved to a point where maybe it even could get proactive. Yeah. And we're seeing there's so many examples that you can plug it up, for example, if you're using Century, Century has automations where like if an error fires in Century that is net new, you could have a hook that kicks off your favorite coding agent where it one shots a fix and it puts you in your review. Now, of course, you could take it further and you could allow it to automatically do it, which sounds like a bad idea today, but you could do it. And I wonder, is when we're talking about loops, is this, for example, a loop that we say? And maybe the loop is just not a good word.

for it. Maybe it's, I heard workflow. I heard, like, or if I say feedback loop, okay, that might be a better word. Maybe is it just a wording thing where like we're a little bit confused with the. Yeah. I mean, I think that given how fast things are moving, we are very likely to see new terminology sprout out every month. And some of them will be good fits and some of them will continue to require some refinement. So I could totally see workflow being a better fit than loop. But from a visual perspective, I do, I personally do see it as a loop. Workflow also works. But, but then can you give me examples of loops that you've, you've used or you have seen people on your team or people in the university use? Yeah. So, um, I was just mentioning being able to connect multiple signals up to,

you know, your software factory or your production, from production. May that be logs or errors or all those things. So, um, I have one app where, um, I, um, I allow, you. allow people to submit issues to it if they run into any problems. And historically, yeah, like a bug report. And historically, I would, you know, manually go through everyone and whenever I had time and then make a call in terms of like, okay, well, I only have time to address so-and-so. I can't go through the full backlog. You can now connect up so many other sources of data.

You can connect up your Google Analytics. You can connect up, you know, if you're deploying to a certain hosting provider, there are all kinds of logs that you might get from those sessions. as well, you can connect it up to that. And then you can end up with a system where it's able to make decisions and prioritization. And then, of course, do the implementation based on not just one dimension of feedback. So for example, if in my product, it's noticing that there is a particular view that is really, really slow.

But it now knows that that's happening for users in India, but that I'm getting a lot of traffic from people in India. It can influence the priority of how much I care about that. Now, how much does priority matter these days when an agent can go through your whole backlog and implement everything? I think it still depends if you care about having to go in and manually do some work to like take a look, okay, well, you said you improved performance. What do you actually change? How much do I have to manually test this thing on these kinds of devices myself? Because I can tell you to go and, you know, do some emulated testing. I'm sure it'll help.

But for me, it's just about being able to make more refined product decisions without having to sift through all the different signals myself. I do see more and more people experimenting trying to put these things in place again, like from the one-shotting, the buck fix. There's really no excuse to not act on errors, on logs. Open source projects, popular ones now have things like when people submit an issue, there's a bot that tries to reproduce it, all of these things. so I see them as loops. One question that does come up, though, is, okay, well, we are, this is a lot of stuff that software engineers used to them. We didn't have all the time for it, but we did a lot of it.

And what this means for the future of the profession. Ryan Dahl, the creator of Node.js, wrote, and I quote him, this has been said a thousand times before, but allow me to have my own voice. The era of humans writing code is over. Disturbing for those of us who identify as software engineers, but no less true. That's not to say software engineers don't have work to do, but writing syntax directly is not it. And a lot of our time spent, I remember when I interviewed people at Uber, I would tell them like, well, we're going to spend at least 50% writing code.

So we're testing you on writing code. This is kind of vanishing. Yeah. What do you see replacing it? And what do you see the essence of software engineers, builders, AI engineers, however we call them B? I always go back to what is alpha. So my definition of alpha. Alpha meaning advantage.

So my definition of alpha is advantage, right? So what is the current thing that models are not very good at doing? Alpha is going to decay in some way with every model release or every series of model releases. So it's going to change over time. So for software engineers, we very often say that your alpha is in taste in terms of, are we building the right thing? Where are we putting our energy? Is the thing that we're building actually good?

And good, you know, sometimes people say, yeah, but an agent can tell you. tell you if it's good. I push back on that. An agent can tell you if a thing looks correct, if it's matching a spec. It doesn't necessarily mean it can tell you what's good. I think that good can mean good from a user experience perspective, could be delightful, could be something that a person will actually want to come back to. And it is still something that is sufficiently nuanced that I think it's going to take time for models to actually catch up to a point where they can replace that fully. We tell people that judgment, verification, all these other aspects continue to be important.

And I do believe that. But even if you follow through and you say, okay, well, maybe a year or two from now, models will catch up these different aspects. We still need engineers to be answerable for these different systems. Accountable, right? Yes, accountable, answerable. And that's something that doesn't just happen overnight. That happens when you understand a system.

People trust you and you have that expertise. An example I've been telling people this week is back when I worked on Chrome, chromium is massive codebases, one of the largest code bases in the world. And it's sufficiently complex that for every key part of that system, you will have a directory with an owner's file. And that owner's file is going to contain a small number of people who are effectively accountable for that part of the system. They might not have written all of the code for it in the same way that, you know,

We may not have written all of the code. Our agents may have written some of the code, but they're the person that's on the hook for understanding, for gating, for making sure that someone is deciding what ships, what's blocked, what do we defer? And so I think that that is something

that engineers are going to continue to be valuable for. And that's going to help us to make sure we're building stuff that is stable, reliable, people can actually, you know, use it with some confidence. I do agree with this

because I think accountability is some, that's why so many businesses are, are working. That's why, you know, lawyers always have a job because the regulation is there and you can look about all the court cases and you could understand how the law is interpreted, but they've done this and they often take some level of accountability. In fact, if they grossly not do their job, you actually have an option to, for example, take legal action against a firm if they would have be proven to actually just like ignore what they're doing. And I guess, you know, like that's a good example where like in software and anywhere where there's value, this will be valuable.

Like again, if you're renovating your house, if it's not a big deal, you might do it yourself. If it's a big deal, you just call a professional. Yeah. Yeah. And I think there's two related notes to this topic. You know, every time that we've made it easier to create software, we've exponentially created more of it.

So the total addressable market for builders is happening right now. It's happening right now. We're seeing in the stats and iOS app releases, websites, all of that. Yeah, it's going through the roof. And that's not without nuance. That's not to say, you know, that every single app that's being created has the same value, right? Yeah. We, of course, have these conversations about, like, yes, if your app is like a prompt away from somebody else copying it, you know, it's a different world that we live in.

But that still doesn't change the fact that we have a much larger number of people that can build. now, and that's a lot more potential businesses and startups that could potentially thrive. Yeah. I continue to be very excited about the profession from that aspect. I also think that every point in time in human history when automation or a form of automation has come into the picture, we've automated away certain kinds of jobs and then replaced them with other kinds of jobs. And so I think a big question for the future is, what are those jobs going to be in this new

knowledge economy. We may not necessarily have exact, you know, frames for what they're going to look like just yet, but I do think those are going to come. Yeah. And I wanted to talk to you about your writing as a fellow writer to a fellow writer. You've been a really prolific writer in terms of books released. Just in the past few years, you've written the short book, Software Engineering, the Soft Part, a free book, about 50 pages, a really good read.

you've written leading effective teams two years ago and last year vibe coding. I wanted to ask, and on top of this, you regularly write long form on social media, LinkedIn, your blog, your newsletter. You write a lot for someone who actually has a full-time job, and I can tell you when my full-time job often involves writing. How has your workflow changed in writing when it comes to now, especially we have AI tools or other tools? I would say that now that it is very easy for anyone to use an agent to create a body of text,

I think it's more important than ever for us to make sure that the ideas we're putting out into the world are actually worth people reading. Because if you're asking somebody to spend five, 10, 15 minutes reading a thing, actually put some effort into it. My workflow has changed quite a lot in the last couple of years. I've now published, I think, 18 books. I've worked with O'Reilly on many, many titles over the years. I think the agents have helped me the most probably

with just being able to reason about the thoughts in my head and especially try to connect those back to how other people are thinking about related problems. So on any given week, we can take loop engineering as one example because I was recently putting together a piece on that. When I'm working on a piece these days, I'm always curious, like, what are other people thinking that's related to this? And so I can fire off a ton of, you know, deep research agents to go and check out, you know,

hacker news or Twitter or other places. And just give me a sense of what are things people have tried out? What are things where people have particularly strong opinions either way? What is considered contentious? What are people excited about? And what do they have big questions around? And that's not to say, hey, agents now write the text for me. It's about forming a thesis about what people are struggling with

and what educational content could be useful for them around that. And so agents have been very useful for me in my research. When it comes to writing itself, this is a very interesting one. I think that a lot of people struggle with like, how should we be using agents and these tools these days? I will very often do two things when I've got an idea for a piece. I will start to write out a personal kind of handwritten version of a thing. And I'll also have an agent or different models write out a version of the text as well. And I'll compare sort of, okay, well, I started out with a thesis. How did those other agents reason about this thesis? Did they take it in a very different direction to what I was thinking about? Or did we all kind of converge on the same thing roughly and there's

not really a lot of value that they're offering me? Once I actually feel like I've got the ideas then pooled for my piece. For me, readability is important. And so even if I've handwritten a thing, I will often put that through a model to try improving readability. And that's a hard thing sometimes because I still feel like models are sometimes not the best at writing human looking, even if you're editing something, writing human-looking text. I remember the other day I was trying to play around with, hey, can I improve my workflow? And I feel like I easily wasted three hours of time because no matter what I did,

one of the models I was using continued to generate text that looked like it had triads and these patterns, you know, of AI written text. And I really struggle with that because it feels like, you know, is it diminishing returns trying to use these readability tests? Specifically on loop engineering, so Navi, aka neat code. He did a video where he looked at the loop

engineering, specifically your post as well, and he was reading it. He was reading the part automations. This is the heartbeat, and he kind of read a few paragraphs, and he was saying it felt abstract. It felt that there were like terms that an AI would have done. And he said that, well, either this is AI generated or it might be someone's thoughts,

but then an AI put it out. And when I also read it, in that specifically that loop engineering piece, like I missed the specifics. Right now we talked to, about like, all right, here's the things that you have been doing. And I was wondering on like, how did you write this? And how do you feel about that, that specific piece now?

For that piece specifically. So I started off with a handwritten piece. I did a number of like editorial passes myself. I then handed it off to a model to try improving the readability pass. And that's where I start to struggle because I'm a fan of structured writing. Yeah. I know. I'm a big fan of very structured writing.

I am not a fan. I remember the kind of writing I was writing 10 years ago, maybe even. And I remember, you know, you were mentioning people who like to write, struggle with time. I would very often write articles in the 15 minutes I had before, you know, my next meeting. And I just try to add more paragraphs in. It wasn't as structured or as high qualities I'd like. And so I sometimes struggle with, are people looking for, authenticity even when it's not that structured.

So for example, I might have the version of loop engineering I started out with, even after a few iterations, did it have a good enough line through or thread through the whole thing that made sense? Probably not, or at least that's how I felt at the time. But using an agent to try helping rework that. So it did have a clearer line through it. I felt better about the piece, but somebody else reading it may felt like, okay, well, actually, I would have been, I would have felt better if it wasn't a structure. If it was the moment more raw that you did not feel that good about.

Yeah, yeah. And, you know, you can, you can say the same thing about, you know, typos, about, oh, well, hey, is the article following a consistent structure or beats compared to a final piece? So that's something I struggle with. Yeah, because the final piece, don't give me wrong. Like it, you know, when we look at views and comments, a lot of people appreciate it. And when you read through, again, I'll link it in the show notes below to read it. It did have a clear top level structure. To me, it felt that it was maybe more wordy than it needed to be.

And it just lacked the specifics. But I do see by other people experimenting with this as well. I talk with Michael Novati, who was criticized for a post, which he actually worked a lot with, but it sounded very AI because in the end he did it. And later he wrote another post, which looked a lot better and asked him what he's changed. He said, like, oh, I'm actually just like tweaking the output a lot more because he's also a big fan of dumping his thoughts, getting some help for structure. And actually, you know, like behind the scenes spending a lot of time, like, will this be worth reading? Yeah. And I think that even with access to better tools these days, very often if people see an article that I put out, I very likely spent probably at least three to seven days just trying to.

to work through it. It's just kind of like brewing, the ideas. Yeah. If something comes out very, very quickly, it's probably because I had a very clear, a surprisingly clear vision for what I wanted to say, but very often it takes a while for something to bake well. And I do end up going through every line of text very often before publishing it a few times. And I think that for those of us that are working with tools, with AI tools,

you start to question, well, am I being influenced by the way? Yeah. That the models, because the models are going to, in some cases, I think, provide a homogenous take on what writing looks like. Yes. And you start to feel like, wait, what was my writing style, you know? You feel you're kind of in this middle right now a little bit? Yeah, I very much do.

And there's a part, you know, you take it to the experimentation phase. And there will be, you know, maybe there are people who will say, hey, you should train a custom model on your old writing. I was a different person when I did my old writing, and I had a different set of perspectives, a different set of nuances that I cared about. And so I wouldn't, I would feel, I would feel a certain way about that person writing, you know, these new pieces too.

So I think that we're still learning what the best practices around this are. And I also, you know, I started, I remember the other week, I was just curious, like if people are checking out, out these posts using Pangram or GPs or any of these things, how does that change my workflow? And I was just getting very frustrated because I would literally type out like human sentences or human paragraphs and I'd paste it in to Pangram and be like, no, this doesn't look human written. I'm like, wow. And that's not to say anything bad about Pangram.

It's just to say that I don't, I think that there's opportunity for tools to help writers, you know, flag things and then help them understand. like, okay, well, how do you get back to your human way of writing? Yeah, so as closing, you've just closed down 14 years at Google. You've announced a big decision last year leaving. Congratulations. I know it must have been like a big one to decide on. What is next for you?

What are you looking at? What are you excited about? What I am most excited about right now is helping developers and businesses kind of meet this next moment of software engineering. changing. I think there are a lot of open questions. Every single company I talk to has got so many questions about what the future is going to look like. But there's also a lot of opportunity in there to help and to figure it out with them. So I'm excited about that. I'll be sharing the next couple of months, what my next thing is. But I'm definitely going to be

staying very much in this space. And I'm someone that enjoys working with developers, working with the ecosystem. So I will very much still be staying in a world. that allows me to do that. So right as you're exploring your next career step, you know, may that be joining another company, an exciting role, who knows if you'll do something yourself? Clearly, you're thinking a lot about your own career. What advice would you have to someone who has some experience in the industry,

working at a software engineer or engineering manager, and they might be in a similar shoe where they are like, all right, it's time for me for a change. I want to set myself up for success looking ahead. What skills would you advise that they invest in? what activities, how to think about their network. What do you think will be important in the next couple of years to stay at the front, like the meat of the industry?

What we're very likely to see happen next with engineering careers, as well as product and other roles, is the unbundling of these careers, where we unbundling, where we begin to see more of these roles converge. So the engineer that also has product sense, the product person that also has engineering sensor, Ux sense, the Ux person that also cares about product. So the guidance that I would give people is think beyond just that narrow lens of engineering. There are many people, especially if you were senior, that have already had to think about these different aspects of success. If you are not someone that has had a chance to think about, you know, product or technical

evangelism or about any, or go to marketing or any of these other aspects that are generally different puzzle pieces, how businesses are successful, think about the non-engineering things. I think there's a lot of value there. And if you can show employers that you are not just a builder, but you're someone that can help them as these roles start to become a little bit fuzzier, I think that you can be successful in these times. Don't just be an engineer. So it sounds like it's one of your core values. Go back to being curious. Learn and see where you can help beyond just building. Yeah.

Be a lifelong learner, be endlessly curious, and I think that there will be roles for you in the future. Adi, thank you very much. Thank you so much. This is great. Thank you for having me.

I really enjoyed this chat with Adi, and I hope you did as well. I do feel that Adi's career shows that working hard and always going a layer deeper pays off over time. When he was a teenager, Adi already built a web browser

from scratch, which is a massive project. He never stopped being curious about web browsers, then developer tools, and today he brings this same curiosity to AI agents. A concept I liked that Adi mentioned was this idea of cognitive surrender.

The more capable AI agents become, the easier it is to let them do what they do. For example, a year back, you could still follow along how an agent worked step by step. But today, if you were multiple subagents in parallel, there's no way you'll keep up with every step. This creates this weird paradox. AI makes it easier than ever to build software, but it also makes it easier than ever to lose understanding of the software that we're building. Adi had a really good counterpoint to this, which was mutual amplification.

You want to amplify your own understanding as the agents get better. So have the agents record decisions, document what it learned, and explain unusual choices. It's just no longer feasible to understand how or why every single token was generated, but you want to keep understanding the important decisions that any of your agents make. Finally, I liked our conversation about what happens to software engineers when writing code is a smaller part of a job. Addie's answer is that accountability remains the job. For example, inside of Chromium, specific software engineers owns parts of the code base.

They obviously have not written every line of code in that part that they own, but they understand the area, they decide what matters and what doesn't, and they are accountable for their part working well. I think it's reasonable to assume that AI will push this kind of accountability to be more visible for any and all software engineers. Do check out the show notes for later the Pragmatic Engineer Deep Dives on Google's Engineering culture and AI engineering. If you've enjoyed this podcast, please do subscribe on your favorite podcast platform

and on YouTube. A big thank you if you also leave a rating on the show. Appreciate it and see you on the next one.