Inside Devin: The AI engineer that's set to write 50% of its company’s code this year | Scott Wu

*Scott Wu* is the co-founder and CEO of Cognition, the company behind Devin—the world’s first autonomous AI software engineer. Unlike other AI coding tools, Devin works like an autonomous engineer that you can interact with through Slack, Linear, and GitHub, just like with a remote engineer. With Scott’s background in competitive programming and a previous AI-powered startup, Lunchclub, teaching AI to code has become his ultimate passion. What you’ll learn: • How a team of “Devins” are already producing 25% of Cognition’s pull requests, and they are on track to hit 50% by year’s end • How each engineer on Cognition’s 15-person engineering team works with about five Devins each • How Devin has evolved from a “high school CS student” to a “junior engineer” over the past year • Why engineering will shift from “bricklayers” to “architects” • Why AI tools will lead to more engineering jobs rather than fewer • How Devin creates its own wiki to understand and document complex codebases • The eight pivots Cognition went through before landing on their current approach • The cultural shifts required to successfully adopt AI engineers *Transcript:* https://www.lennysnewsletter.com/p/inside-devin-scott-wu *Brought to you by:* Enterpret—Transform customer feedback into product growth Paragon—Ship every SaaS integration your customers want Attio—The powerful, flexible CRM for fast-growing startups *Where to find Scott Wu:* X: https://x.com/scottwu46 LinkedIn: https://www.linkedin.com/in/scott-wu-8b94ab96/ *Where to find Lenny:* Newsletter: https://www.lennysnewsletter.com X: https://twitter.com/lennysan LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ *In this episode, we cover:* (00:00) Introduction to Scott Wu and Devin (09:13) Scaling and future prospects (10:23) Devin's origin story (17:26) The idea of Devin as a person (22:19) How a team of “Devins” are already producing 25% of Cognition’s pull requests (25:17) Important skills in the AI era (30:21) How Cognition’s engineering team works with Devin's (34:37) Live demo (42:20) Devin’s codebase integration (44:50) Automation with Linear (46:53) What Devin does best (52:56) The future of AI in software engineering (57:13) Moats and stickiness in AI (01:01:57) The tech that enables Devin (01:04:14) AI will be the biggest technology shift of our lives (01:07:25) Adopting Devin in your company (01:15:13) Startup wisdom and hiring practices (01:22:32) Lightning round and final thoughts *Referenced:* • Devin: https://devin.ai/ • GitHub: https://github.com/ • Linear: https://linear.app/ • Waymo: https://waymo.com/ • GitHub Copilot: https://github.com/features/copilot • Cursor: https://www.cursor.com/ • Anysphere: https://anysphere.inc/ • Bolt: https://bolt.new/ • StackBlitz: https://stackblitz.com/ • Cognition: https://cognition.ai/ • v0: https://v0.dev/ • Vercel: https://vercel.com/ • Everyone’s an engineer now: Inside v0’s mission to create a hundred million builders | Guillermo Rauch (founder and CEO of Vercel, creators of v0 and Next.js): https://www.lennysnewsletter.com/p/everyones-an-engineer-now-guillermo-rauch • Inside Bolt: From near-death to ~$40m ARR in 5 months—one of the fastest-growing products in history | Eric Simons (founder and CEO of StackBlitz): https://www.lennysnewsletter.com/p/inside-bolt-eric-simons • Assembly: https://en.wikipedia.org/wiki/Assembly_language • Pascal: https://en.wikipedia.org/wiki/Pascal_(programming_language) • Python: https://www.python.org/ • Jevons paradox: https://en.wikipedia.org/wiki/Jevons_paradox • Datadog: https://www.datadoghq.com/ • Bending the universe in your favor | Claire Vo (LaunchDarkly, Color, Optimizely, ChatPRD): https://www.lennysnewsletter.com/p/bending-the-universe-in-your-favor • OpenAI’s CPO on how AI changes must-have skills, moats, coding, startup playbooks, more | Kevin Weil (CPO at OpenAI, ex-Instagram, Twitter): https://www.lennysnewsletter.com/p/kevin-weil-open-ai • Behind the product: Replit | Amjad Masad (co-founder and CEO): https://www.lennysnewsletter.com/p/behind-the-product-replit-amjad-masad • Windsurf: https://windsurf.com/ • COBOL: https://en.wikipedia.org/wiki/COBOL • Fortran: https://en.wikipedia.org/wiki/Fortran • Magic the Gathering: https://magic.wizards.com/en • Aura frames: https://auraframes.com/ • AirPods: https://www.apple.com/airpods/ • Steven Hao on LinkedIn: https://www.linkedin.com/in/steven-hao-160b9638/ *Recommended books:* • How to Win Friends & Influence People: https://www.amazon.com/How-Win-Friends-Influence-People/dp/0671027034 • The Power Law: Venture Capital and the Making of the New Future: https://www.amazon.com/Power-Law-Venture-Capital-Making/dp/052555999X • The Great Gatsby: https://www.amazon.com/Great-Gatsby-F-Scott-Fitzgerald/dp/0743273567 _Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected]._ _Lenny may be an investor in the companies discussed._

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Our whole team is only like 15 engineers. We use a ton of Devon when we're building Devon. Most folks on the team are definitely working with up to five Devens at once. And so Devon merges like several hundred pull requests into production in the Devon code bases every month.

• 0:12Lenny Rachitsky?

  What percentage of your PRs are Devon versus humans right now?

• 0:16Speaker 00

  It's in the neighborhood of a quarter or so.

• 0:18Lenny Rachitsky?

  Where do you think this will be at the end of the year?

• 0:21Speaker 00

  Honestly, we expect it to be a decent bit more than half.

• 0:23Lenny Rachitsky?

  You guys are so ahead of how companies work with AI engineers.

• 0:27Speaker 00

  AI is going to be the biggest technology shift of our lives. So most of the big tech revolutions that we've had over the last 50 years, like personal computer and the internet and mobile phone, they all had this big hardware component that was a big part of the distribution. Folks who were building for those industries kind of saw their market grow and grow and grow, basically steadily year over year as the number of people with mobile phones increased, right? As the number of people connected to the internet increased. One of the things which is already, I'd say, different in AI is just how explosive the technology can be. There's no weight on hardware distribution. It means that the space is just growing so exponentially.

• 1:01Lenny Rachitsky?

  How is the fact of being an engineer and building changing?

• 1:04Speaker 00

  I think there's going to be way more programmers and way more engineers. A few years from now, pretty quickly, the form factor of what it means to be a programmer, obviously, is going to change. But at the end of the day, of course, the discipline is all about just being able to tell your computer what to do. And so in that lens, I really think that programming is only going to become more and more important as AI gets more powerful.

• 1:20Lenny Rachitsky?

  Today, my guest is Scott Wu. Scott is the co-founder and CEO of Cognition, which makes a product called Devon, the world's first autonomous AI software engineer. Unlike other AI tools that I've highlighted on this podcast, Devon is designed to act like an actual remote engineer that you chat with like you would with any other human engineer through Slack or through its dedicated website. When Devon launched about a year ago, it was very much a junior engineer. Over the past year, they've made a lot of progress, and Devon is now being used by tons of companies in production. We chat about how their engineering team of 15 uses Devens to build Devon, including how every engineer uses about five Devens each to help them code and move faster, how a quarter of their pull requests today are committed by Devens, and that they expect this to be over 50% by the end of the year.

• 2:05Lenny Rachitsky?

  We also talk about how Scott imagines software engineering is going to look in the future and how the role of And engineer changes from a coder to an architect. We also get into the eight pivots that they went through before landing on this path. Why Scott believes AI tools like this will lead to more engineer hiring versus less. Also where the name Devon comes from and so much more. This episode is going to blow your mind. I highly recommend you listen to it if you're at all interested about where engineering, product building and AI is going. A huge thank you to Claire Vo for suggesting a bunch of great questions for this conversation. If you enjoy this podcast, don't forget to subscribe and follow it in your favorite podcasting app or YouTube. Also, if you become an annual subscriber of my newsletter, you get a year free of Linear Superhuman Notion perplexity and granola.

• 2:50Lenny Rachitsky?

  Check it out at lennysnewsletter.com and click bundle. With that, I bring you Scott Wu. This episode is brought to you by Interpret. Interpret unifies all your customer interactions from gong calls to Zendesk tickets to Twitter threads to app store reviews and makes it available for analysis. It's trusted by leading product orgs like Canva, Notion, Loom, Linear, Monday.com and Strava to bring the voice of the customer into the product development process, helping you build best in class products faster. What makes Interpret special is its ability to build and update customer specific AI models that provide the most granular and accurate insights into your business, connect customer insights to revenue and operational data in your CRM or data warehouse to map

• 3:32Lenny Rachitsky?

  the business impact of each customer need and prioritize confidently, and empower your entire team to easily take action on use cases like win-loss analysis, critical bug detection, and identifying drivers of churn with Interpret's AI assistant, Wisdom. Looking to automate your feedback loops and prioritize your roadmap with confidence like Notion, Canva and Linear? Visit E N T E R P R E T dot com slash Lenny to connect with the team and to get two free months when you sign up for an annual plan. This is a limited time offer. That's Interpret dot com slash Lenny.

• 4:07Lenny Rachitsky?

  Many of you are building AI products, which is why I'm very excited to chat with Brandon Foo, founder and CEO of Paragon. Hey, Brandon.

• 4:15Speaker 02

  Hey, Lenny. Thanks for having me.

• 4:16Lenny Rachitsky?

  So integrations have become a big deal for AI products. Why is that?

• 4:21Speaker 02

  Integrations are mission critical for AI for two reasons. First, AI products need context from their customers' business data, such as Google Drive files, Slack messages, or CRM records. Second, for AI products to automate work on behalf of users, AI agents need to be able to take action across these different third-party tools.

• 4:40Lenny Rachitsky?

  So where does Paragon fit into all this?

• 4:42Speaker 02

  Well, these integrations are a pain to build, and that's why Paragon provides an embedded platform that enables engineers to ship these product integrations in just days instead of months across every use case, from rag data ingestion to agentic actions.

• 4:56Lenny Rachitsky?

  And I know from firsthand experience that maintenance is even harder than just building it for the first time.

• 5:01Speaker 02

  Exactly. We believe product teams should focus engineering efforts and competitive advantages, not integrations. That's why companies like U.com, AI21, and hundreds of others use Paragon to accelerate their integration strategy.

• 5:15Lenny Rachitsky?

  If you want to avoid wasting months of engineering on integrations that your customers need, check out Paragon at useparagon.com/Lenny.

• 5:26Lenny Rachitsky?

  Scott, thank you so much for being here and welcome to the podcast. Thanks so much for having me. Excited to be on. I'm really excited to have you here because you are building and you've been building something that is very different from what a lot of other AI companies have been doing for a long time, although they are starting to converge to where you guys are now. We're going to talk about that. And it's also just such a unique point in the history of AI and just the journey of AI. And so it's really cool to be chatting right now. And I feel like we're going to chat again in a few years and be like, wow, we were so right about so much and so wrong about so much. Yeah. And so I'm excited to have you here. Let's start with talking about Devon, giving people an understanding of just what the heck Devon is. This is the main product that you guys build. What is the simplest way to understand what is Devon?

• 6:10Speaker 00

  Absolutely. And so Devon is a fully autonomous software engineer that is going to work on tasks end to end. And so there are a lot of great tools for all parts of the stack of the AI code workflow. What Devon does is it is a full asynchronous workflow. And so you can tag Devon on an issue in Slack. You know, you're talking about an issue and you tag Devon. You can tag Devon in linear, you can have Devon, and Devon will make pull requests in your GitHub. And so it's very much built to work with engineering teams as your junior engineer.

• 6:37Lenny Rachitsky?

  Amazing. Okay. So I remember when you guys launched this, there was like this big pitch of this is your new AI engineer. And it was, it was really good at a lot of stuff. It wasn't great at other things. It's been a year now about since you guys launched, is that right?

• 6:50Speaker 00

  Yeah, yeah.

• 6:51Lenny Rachitsky?

  What's the best way to think about like the level of seniority that engineer had back in the day when you guys launched? And then the level of seniority of engineer today, if that's, I don't know, a measure of how to think about Devon?

• 7:02Speaker 00

  Yeah, and it's crazy to think about, by the way, because you know, a year ago, when we did the initial launch, I mean, people didn't really believe that an agent was possible. And it was a very, I mean, it was a very different time, you know, it's like start of 2024. You know, things with model capabilities were definitely quite a bit earlier on. Reasoning especially was was quite a bit earlier on. And, and yeah, I mean, in the time since then, it's obviously developed a lot. I think in terms of practical skills, you know, we, there are some comparisons we make. Sometimes we kind of say, well, when we got started, it was kind of like a high school CS student. And then as time went on and became more of like a college intern, and now it's like a junior engineer. But, but I would say though, that those are more like rough guidelines because I really like the phrase jagged intelligence, for example.

• 7:46Speaker 00

  Because there are obviously, there are certain things that it is much better at than a human. There are certain things that it's much worse at than a human. And I think over the last year, we've, we've learned a lot, especially about not just coding agents, but agents in general. Just like really building out like how all of us should be working and interacting with agents as part of our flow. And so a lot of the things that we built, I mean, it's, you know, there was no Slack. There was no GitHub integration. There was no linear, there was no interactive planning phase, working back and forth. There was no way to touch up Devon's code. And so a lot of the, the, the features that we built on the product side since then have really been about basically, yeah, figuring out how to, how to make working with Devon and handing off tasks to Devon as smooth of an experience as possible.

• 8:27Lenny Rachitsky?

  That's so interesting. So a lot of the work has gone not into how do we just make Devon the best possible engineer, but it's how to work with this new type of entity that we haven't ever worked with.

• 8:37Speaker 00

  I think it's a 50/50 of both. You know, I think the capabilities obviously have improved a ton and we've seen these get better and get measurably better. But I think the other side of it is everything to do with, yeah, really the product interface and the tools and so on. And I think, you know, I think today, folks generally know how to use chatbots and to work with chatbots, right? And that's an interface that people are familiar with. And, and obviously with agents, it's, you know, it's, it's, it's still like a real curve, I think, to learn how to use them and how to get the most out of them. And so it's, it's really exciting to see a lot of others starting to build and do a lot more in the agent space as well. But I, I think this is the kind of thing that we're, we're all really figuring out together as a space.

• 9:14Lenny Rachitsky?

  What can you share about just the scale of Devon at this point, whatever you're comfortable sharing? And then just where do you think the level of Devon's coding abilities will be in a year?

• 9:24Speaker 00

  So we work with companies of all stages and sizes, you know, on the smallest end, it goes to, you know, startups of just one or two people who are using Devon to, to build out a lot of their kind of like initial prototypes or initial product, all the way up to, you know, big public companies, Fortune 100 companies, or, or, or public banks or things like that, who are using Devon like across their, across their engineering teams. In general, it's, you know, we've, we've seen a huge range of, of the use cases there. And obviously the kinds of engineering work that you're doing at a one or two person startup is very different from the kind of work that you're doing at a, at a public bank. But, but throughout, it's all been, basically, yeah, being, being that junior buddy of yours that, that, that, that makes you go faster and really multiplies you, I would say. You know, I, I think there's, it can multiply you as an engineer, obviously, by just like

• 10:07Speaker 00

  letting you work with your own team of Devins, instead of having to be kind of like fully synchronous on a single task. And then it's also kind of like multiplying your team and multiplying your, your team's knowledge base, because Devon really accumulates a lot of the knowledge from, from working with every member of your team and is able to bring that into each new session.

• 10:23Lenny Rachitsky?

  Awesome. We're going to show people how it actually works later in the podcast. We're going to do a few live demos. But let's actually go to the beginning of the journey. What's just the origin story of Devon? How did this all begin?

• 10:33Speaker 00

  The founding team, I mean, most of us have known each other for years and years and years, actually. And for almost everyone, this is our first time working together, but we've known each other a long time. And we all actually had our own kind of journeys in AI for the last decade or so. And so for myself, you know, I ran a company called this, before this called Lunch Club, which was an AI for a professional networking product. And I ran that for about five years. And, you know, my co-founders, one of my co-founders, Steven, was one of the first engineers at a company called Scale AI, which has obviously grown a lot and done very well. My other co-founder, Walden, was an early engineer at a company called Cursor, which has also obviously grown a lot and done really well. And our whole team was kind of like that. Many of us knew each other from competitive programming and math competitions,

• 11:15Speaker 00

  but we had stayed very closely in touch in the decade since then. And we've all had our own journeys. And so, you know, we had one person who was running teams at Neuro. We had one person who was at Waymo, someone who had their own YC tool startup for machine learning. And we were really excited to build something together. And this was around like late 2023, so about a year and a half ago at this point. And yeah, when we got started, I mean, I think there were a couple of things that we felt really strongly about. And one was that reinforcement learning was really working and was going to be the next big paradigm shift in capabilities. Back then, it was, you know, the initial ChatGPT launch in 2022.

• 11:55Speaker 00

  And those models were, to first order, were, you know, what we would call imitation learning in AI, right? Which is basically, you know, you have the model read all the texts that you can find on the internet and then train it to talk like somebody on the internet would talk, right? And there are kind of, obviously, a lot more details on top of that. But that's kind of the first order pass of what was really done. And it was amazing, right? I mean, it passed the Turing test. It was able to respond and to have encyclopedia knowledge about a lot of things. And I think this new paradigm, which we've gotten into over this last year or a year and a half, is really high compute RL, which is a very different paradigm, right? Which is basically the ability to go and Do work on task and put something together and then be evaluated on whether

• 12:37Speaker 00

  that was correct or incorrect and use that knowledge to decide what to do and to learn from that, right? And so, you know, we felt very strongly that that was going to happen. I think it's for us is code was the natural thing to work on for a couple of reasons. One, because, you know, we're all programmer nerds ourselves and so teaching AI to code is about as cool as it gets for us. But also because, you know, code has this whole automated feedback loop, right? Where you can run the code and that is the kind of automated feedback that really feeds into the RL, which makes these models so great at coding. And then the other thing that we felt very strongly about was that the product experience was going to shift from, you know, what I'll call like text completion to agents, basically, right? And to first order, I would kind of say, you know, there's been a lot of great experiences in text completion.

• 13:21Speaker 00

  You know, it's been used for marketing, it's been used for customer support, it's been used for education and in code, obviously as well as, you know, the GitHub Copilot was was was kind of really the dominant product of that initial wave, right? But I think that the big shift that we really felt we would see is moving from kind of this this text to text model to an actual autonomous system that can make decisions, that can interact with the real world, that can take in feedback, that can iterate and and take multiple steps to solve problems. And, you know, now we call that agents, but but that was what we were really excited about at the time. So it was always coding, it was always agents. And in some ways, that kind of feels like it's it should have been, you know, like been been clear from the start, but even with that, it's, I feel like we've pivoted

• 14:04Speaker 00

  like eight times or something within coding agents, you know, over the last year and a half, so.

• 14:08Lenny Rachitsky?

  I just noticed recently, all the AI, top AI companies, sort of not all, but many of them, the product that is winning is different, has a different name from the company, which is not typical. Cursor, AnySphere, Bolt, Stackblitz, you guys are cognition labs, like V-Zero is yourself. And it just tells me like, these all emerged later in the company's journey and they tried a bunch of stuff and like, oh wow, this thing worked. And it's so interesting that it's so common amongst these top AI companies.

• 14:34Speaker 00

  Yeah, and there's even, I mean, OpenAI, ChatGPT, Anthropic and Claude and Google. Yeah, it's funny. Yeah, yeah, I agree. So, you know, when we got started, it wasn't even really a company. I mean, it's more like a project or a hackathon almost. You know, we got a bunch of, we booked an Airbnb, basically, for a couple of weeks as it was around Thanksgiving time. And, and just got a bunch of people together who were just excited to hack on some projects and build something cool. And it's funny, actually, the first, the first thing that we were building for actually was more like solving like these more like contest programming problems and using like an agentic loop to really do better on that. And so obviously, if you run your code on the test cases, you can evaluate. You know, there's a lot of agentic work that you can do there to try and do better. And, and that, that we spent some time on that initially.

• 15:17Speaker 00

  And then, you know, we, we've kind of gone from, I mean, the, the, the story of the whole company for us in some sense has been going from hacker house to hacker house, you know? And so, so, so after that, you know, we had another hacker house. And that's where kind of some of the initial ideas for Devin came. And, and really building like a software engineering agent and not just like a coding agent and having it interact with a lot of these tools. But, but even then, there were so many iterations and, you know, even like the idea of talking to Devin, for example, was like, you know, it was something that we had to come up with, right? Initially, it was just like you hand off a task and then it works. And then it shows you like this whole finished code, right? And now, obviously, it's like you can jump in at any time, you can get feedback on the plan. You guys can scope out the task together, you know, when you're working with Devin. And, and a lot of these things, we, we had to develop, obviously.

• 16:00Speaker 00

  And certainly, we've learned a lot about the use cases, the form factor. We've made a lot of big improvements and step function improvements on the capabilities and, and Devin's ability to use tools and debug and make decisions. And, and so it's, yeah, it's been a fun journey. I mean, I think like, I, I, I would say that the grounding question for us really is that, which is one that we think about all the time is, is really just like, what, what is the future of software engineering? You know, and, and how, how should we be working with AI to write code? Because I think at the end of the day, of course, that's, that's, that's what underlies all of the, the, the product decisions that we make. So.

• 16:34Lenny Rachitsky?

  I like that you're asking the juicy question I wanted to get to. Before I ask it, just for the history books, when did you guys start kind of hacking around? And when did Devon launch? How long was that period?

• 16:44Speaker 00

  Yeah, so we started in November of 2023, which was in, yeah, it was just like hackathon mode. We officially made it into a company around the start of 2024. And then our initial launch was in March. And so it was like nonstop. I mean, it's been nonstop for the entire last, you know, 17 months. But, but, you know, it's getting to the launch and then obviously working with enterprises and developing the product a lot more, building in, building in and getting it to work for a lot of practical use cases. And then doing, you know, getting it, making it fully available self-serve in December of last year. And now we've rolled out 2.0, obviously just a few weeks ago. And so it's been a, been a very busy time for us.

• 17:24Lenny Rachitsky?

  Understatement of the century. Let me ask this question because you touched on it a bit. This whole idea of Devon as a person and this idea of creating a personality for Devon. It's unlike any other, I believe, AI app. No one else has like a name and like a, you don't think of it as a person. What made you guys decide to go that approach? And just how do you design it to work well that way?

• 17:44Speaker 00

  I would say it's a decision we're pretty proud of, I would say. I mean, I think there's a lot of different product experiences out there. And I think the thing that really makes Devon unique in what it does is that you can really hand off. And, and more and more what we've seen honestly is that, that I think a lot of kind of explaining that the Devon experience to folks is really just explaining to, explain it as, yeah, this is your junior buddy, you know? And, and that goes for a lot of the parts of the flow where in the onboarding, for example, you know, initially I would say like, we've definitely had a lot of users come in and just kind of see the blank screen and not really know. Or, or they'd ask, hey, like, I'm going to do this whole big re-architecture, the whole code base. And, and basically, you know, what, what we've learned over time is to basically get folks to think more like, whoa, whoa, whoa, you know?

• 18:28Speaker 00

  Let's work on getting the repository set up first. Like, let's make sure we hand Devin a couple of one pointer tasks so it can get familiar with the code base. You know, let's get it the thing. If Devin needs to be able to test the code or run the Linter or CI or things like that, obviously, we want to make sure Devin's got its own virtual machine set up to be able to do that. And similarly, I think the usage pattern, you know, I think often it wasn't clear. And obviously, you can sit and just kind of watch Devin do it action by action and work that way. But we found that the, you know, the best workflow really as a team building off stuff was to work with multiple Devens and to run them asynchronously and to kick them off and to only jump in basically as you needed to provide feedback or steer the plan or anything like that.

• 19:12Speaker 00

  And so in many ways, I think it's, I think Devin as a name really is our attempt to kind of capture the soul of that as a product where it really is, you know, treating it like a bit more of an autonomous entity that you can hand off tasks, that you can work with, that you should be teaching and learning with over time.

• 19:28Lenny Rachitsky?

  I want to come back to an area you started us down and then I took us away from, which is impact on software engineering and then how software engineering is going to change. So there's kind of two parts of this, just like when people are using Devin today, say in like this year, how is the act of being an engineer and building changing for those companies? What does that look like?

• 19:49Speaker 00

  You know, by the way, we're all software engineers ourselves. You know, it's like I'm a programmer by training and still a programmer at heart, certainly. And, you know, I think the way that we have always thought about it is there's layers of abstraction and there's tools. And one way I would say at a high level is kind of, you know, I think of AI in general as, yeah, I mean, computers are obviously getting more and more intelligence and are able to do more and more. And, you know, it's possible there may come a day where computers truly do everything that we do and humans are not responsible for any of it. You know, I don't expect that to come particularly soon. But, but, but I guess what I would say is, you know, until that point, for as long as we're still part of the equation, one of the most important things to do, obviously,

• 20:31Speaker 00

  is, you know, for us as humans is to instruct our computers on what we want and what we want to build and what we want to do, right? And software engineering is, you know, we think of it today, obviously, as Python and C++ and JavaScript and all these things. But at the end of the day, of course, the discipline is all about just being able to tell your computer what's due. And so in that lens, I really think that programming is, if anything, is only going to become more and more important as AI gets more powerful. And I think the thing that's really, that's really exciting for us is, yeah, it's like really like seeing that that kind of iterative transformation. And so you asked how, what things look like today. And I would say, yeah, it's, it really is like having like a junior buddy or really a team of junior buddies that you can work with, right? And so every engineer on our team, you know, we use a ton of Devon when we're building Devon.

• 21:16Speaker 00

  And so Devon merges like several hundred pull requests into production in the Devon code bases every month, you know, which is, I mean, our whole team is only like 15 engineers. And so it's a, it's a pretty sizable fraction of all the code that we write. And the way that we use it is basically, yeah, everyone's got their whole team of Devens. You know, if you're going to be like looking through various issues, if you're going through feature requests, if you're going through bugs, if you're going through new paradigms that you want to build, then it is naturally the case that there's a lot of handoff points where you just say, hey, at Devon, here's what's going on. Can you please take a, take a pass at this, right? And sometimes Devon will be able to do the task 100% autonomously and just makes the PR and then you merge the PR and that's great. Sometimes you want to be able to, to, to jump in for the 10 or 20% that really needs your help.

• 21:58Speaker 00

  Maybe there's a few details with how exactly you want to scope it or how you're architecting this feature. Or maybe you want to go and test the front end at the end yourself to make sure it looks exactly the way that you want and give your, your one or two lines of feedback after that, right? But a lot of it is, is really, yeah, it's just kind of like, yeah, learning, learning to, learning to work with Devon to be able to just do more in parallel and build more.

• 22:20Lenny Rachitsky?

  What percentage of your PRs are Devon versus humans right now?

• 22:24Speaker 00

  Yeah, I'd have to look, but it's in the neighborhood of, of a quarter or so of all of our, us. Yeah, yeah.

• 22:32Lenny Rachitsky?

  That's, and then what was it like six months ago?

• 22:34Speaker 00

  Oh, it's, yeah, it's, it's, it's grown a ton for, I mean, we've seen it growing exponentially internally ourselves as well. And, and so it's, you know, it's, it's kind of an interesting one where, again, it's always both the capabilities and the product interface. And so, you know, I think the intelligence has increased a lot. But the other thing, of course, is that, you know, We've spent a lot of time in figuring out how to build and to really kind of build for an interface where you can get Devins value on tasks where Devins is able to do the 80 or 90 percent. So Devins is obviously not, you know, is obviously not perfect and it'll make mistakes and so on. And a lot of the question is basically, yeah, how do you scope out your initial task with Devins and then just kind of set Devins off and have it go and do the things that you want to do? You know, how do you come in at the end and review and give feedback? How do you make sure Devins learns over time? How

• 23:19Speaker 00

  are you able to kind of just check in as needed and course correct if you want to?

• 23:23Lenny Rachitsky?

  Okay, so today about quarter of your PRs are Devins. Where do you think this will be at the end of the year? What would you guess?

• 23:31Speaker 00

  I think by the end of this year, we expect it to be more than half. And I mean, as time goes on, you know, one of the things that we've seen is just, it's you're able to do more and more and more work asynchronously, right? And you're able to hand off more and more. You know, I think the soul of programming, the soul of software engineering has really been about, through all the areas, you know, not just now, but you know, even when it was assembly, right? And even when it was Pascal and even when it was punch cards or whatever. I think the soul of it has really been basically just about defining the problem that you're facing and really thinking through exactly what is the solution that you want to build, you know, thinking through the architecture, thinking through the details, and really kind of mapping out in your mind exactly what you want to build, basically,

• 24:13Speaker 00

  and what you want to have your computer do. And I think that's, you know, that's what makes software engineering really great. And I think that's like the funnest part of software engineering. I think at the same time, that's probably, you know, in the neighborhood of 10% of the average software engineer's time, right? Because 90% of the time is, you know, you've got this Kubernetes error that you've got to debug and you have to see what went wrong and the system crashed, or, you know, you left some port open and this is, you know, messing up, or, you know, there's a bug report that you have to take care of, or you've got to migrate your code, or you've got to upgrade to a new version, or things like that. You know, a lot more kind of like implementation. And one of the ways that we've kind of thought about Devins and building Devins is really allowing engineers to go

• 24:55Speaker 00

  from bricklayer to architect, so to speak. And a lot of it is, yeah, just like getting to the point where you can do the high level directing and you can basically specify things exactly how you want. You know, I think it is very much about still having the human in control and having the human able to do the full specification, but just multiplying the magnitude of what you can do and what you can build, you know, in one day or one hour or however long.

• 25:18Lenny Rachitsky?

  So in the future, say someone is trying to get into software engineering, thinking about becoming an engineer. First of all, do you think people should, you know, classic question everyone's getting these days, should you still learn to code? So that's just, I'd love your perspective there. And then two, for people that are engineers today, what skills do you think will be more and more important? And then less important in this discussion of moving from bricklayer to architect?

• 25:40Speaker 00

  Yeah, for sure. I love this question. First of all, the question of, you know, whether you should still learn to code, my answer would be absolutely yes. I think to a large extent, you know, computer science, when you take computer science classes and when you learn these fundamentals, sure, you're learning a little bit about, you know, how a particular language's syntax works or something like that. But honestly, most of what you're learning really is about the ability to logically break down problems for number one. And two, I would say is just, yeah, the model of a computer and a lot of these decisions and a lot of the abstractions that we've built over time. Right? Like what is a database and how should you think about a database? You know, what is a garbage collection system and how do those work? And all of these different pieces. And the reason I think that's important is because it's the same with a lot of these other, you know,

• 26:24Speaker 00

  arguably, we've already gone kind of gone through these phases in programming. And I think this next one is going to be, you know, somewhat faster and somewhat bigger, but in many ways a similar flavor, which is, you know, when you work with Python today, obviously, a lot of things are already abstracted away from you. And in some sense, you know, someone from 50 years ago might already call Python, you know, you just get to explain in English what you want and now the computer does it for you, right? And that's great. And I think it's really powerful. It's opened it up. I mean, we have far more programmers, obviously, than we ever have before because of that. But I would say certainly, you know, as you're building your skills as an engineer, it really helps a lot to understand the abstractions and to be able to peel the layers beneath, right? And so, you know, folks will use assembly, for example, if they're really performance optimizing a piece of code.

• 27:10Speaker 00

  But also, you know, it's in order to build good systems and to understand these things, you certainly want to understand these abstractions of, you know, how does networking work? What is TCP IP like exactly? Or what happens with this Python code when it gets interpreted or all of these details? And I think similarly, I think we will get to a state where, yeah, you know, with with no experience at all, you're going to be able to build some pretty cool stuff and and to do some pretty amazing work just by explaining what it is that you want. But I think that, you know, for for quite some time, you you really want to be able to to think precisely about the details, to peel back the abstractions, to to be very, very, very precise about what it is that you want to build and how.

• 27:48Lenny Rachitsky?

  And then for skills that you think are more and more valuable for engineers, like, where should engineers today be leaning more and more into and versus like, you know, forget, forget this, I don't need to think about this anymore?

• 28:00Speaker 00

  For sure. And I think architect, I mean, it's, you know, we already have a term for architect in engineering, and I think it is directly the directionally the right term. And I think a lot of it is really, you know, it's, it's, I think, one thing to kind of just do a routine implementation and and write boilerplate code and things like that. And I would say that, you know, in many ways, AI coding has already made us much faster at that, right? But I think a lot of the core questions of of understanding very complex systems and and working in the context of the whole company and thinking about, you know, the product that you're building or the work that you're doing, and understanding, okay, what are the problems that we want to solve? How do we want to solve those problems? What is exactly the solution that we want to build? What are all these key decisions and trade offs that we're going to be making? Basically, I I think folks who are able to do that really, really well are just going

• 28:43Speaker 00

  to be be able to leverage themselves more and more. And so if anything, I think there's going to be, I think there's going to be way more product, way more programmers and way more engineers, you know, a few years from now than there are today. And I think, I think pretty quickly, the form factor of what it means to be a programmer, obviously, is going to change. And in some sense, it already has. But but but I I think there's just going to be so much more for us to build. You know, I think one of the great things, folks talk about Jevon's paradox all the time. I mean, software is truly the the kind of the shining example of Jevon's paradox, where we have always managed as a society to to find more and more things that we want to build software for and build more code for it. And and I really think there's, there's, there's a lot more out there to do.

• 29:22Lenny Rachitsky?

  For people that don't know Jevon's Paradox, can you briefly explain it?

• 29:26Speaker 00

  Absolutely, yeah. So Jevon's Paradox just says that as the price of something goes down, it can still be the case that the total spend on it actually goes up. And so you can think about this with money, you can think about this with time or resources, but the direct version here is, I think, as it becomes easier and easier to program, and as programming becomes more and more effective, I think we're going to have a lot more programmers. You know, I think in a kind of zero-sum view, you might say, "Well, we're going to be 10 times faster at software engineering, and so it means that we're going to need 10 times fewer software engineers," right? But I think in practice, what really is going to happen is actually, we're going to build even more than 10 times as much code. And because, you know, all of the work that we do is so capped,

• 30:08Speaker 00

  obviously, on our ability to actually build and execute and iterate. We're going to have so many great ideas out there, we're going to have so many great products out there. People are going to build a lot more personalized experiences, for example, and there's going to be a lot to do.

• 30:22Lenny Rachitsky?

  Going back to the way you guys use Devins, so you said that every engineer has kind of this fleet of Devins. How many Devins per engineer do you find most people are working with these days at your company?

• 30:32Speaker 00

  Yeah, so it's very asynchronous, and so obviously you can kick them up and start them up and shut them down, basically, as you see fit. But most folks on the team are definitely, yeah, are often working with up to five Devins at once, I would say. And it's a nice flow where it's, you know, you think through, "All right, what are the five things that we want to get done today? 1, 2, 3, 4, 5." You have Devins 1 do number 1, you have Devins 2 do number 2, Devins 3. And the thing about it is, a lot of it is, and for what it's worth, you know, I think it's taken us some time to really kind of like, to adjust to it and get to the point where it's really intuitive for us. But I think it's, yeah, it's definitely a different experience where you're handing off most things asynchronously,

• 31:13Speaker 00

  and the goal for each of your tasks is to be there for the parts that really need your expertise, where either you really, really need to define exactly what it is that you're solving for and what you're building, or maybe some of the more complex parts where you want to steer Devins towards, you know, particularly what kinds of changes you want to make. "You know, I want the class to be set up this way, and I want, you know, we should go and change all the downstream references to this as well," or whatever. But basically, having Devins do the bulk of the work asynchronously with you.

• 31:43Lenny Rachitsky?

  And then how many engineers do you guys have, roughly?

• 31:45Speaker 00

  Yeah, so our engineering team today is about 15 people.

• 31:48Lenny Rachitsky?

  15, one five.

• 31:49Speaker 00

  One five, yeah.

• 31:50Lenny Rachitsky?

  Holy moly, okay. And then each one has five-ish Devins.

• 31:53Speaker 00

  Yeah.

• 31:54Lenny Rachitsky?

  Uh, so there's five times the number of Devins as engineers. What I love about this is this is just like a glimpse into where the future is going. You guys are so ahead of how companies work with AI engineers. And so seeing how you operate is gonna be essentially how most companies will end up operating.

• 32:11Speaker 00

  Yeah, and for what it's worth, you know, we've already seen this shift, I would say, ourselves where it's uh, in terms of the team, obviously, it's, you know, folks don't spend that much of their time just writing out boilerplate or uh, or just kind of doing pure like implementation of features. And uh, and people get to spend like the much more of their time focused on really just, yeah, thinking about the core questions of, yeah, how do we make Devon better? What is the right interface for Devon? You know, what is the right flow? Or the right set of features that's really gonna make this uh, as great of an experience as possible? And that's how we like things.

• 32:45Lenny Rachitsky?

  Have you, when is the point you reach where you're, there's takeoff of this being the by, you know, like your Devon starts moving so much further ahead of everyone else? Like, once you have enough Devins doing all these things, they're just like, we're in the year 10 years, 20 years, 30 years, 100 years ahead.

• 32:59Speaker 00

  Honestly, I think as a community, you know, I think the, the, the, kind of all of us as engineers around the world, I think we're gonna have to think about this and build for this and kind of adapt to these new technologies. But what I would say is, is, yeah, I think more and more, and especially as capabilities get better, but certainly, you know, even in steady state today, I think, you know, I think more and more, I think things are going to shift towards this kind of asynchronous flow. And one of the reasons I would say for that is,

• 33:27Speaker 00

  in the real world, you're just capped by real world constraints, right? And I think that one way to put it is, is kind of like, and don't take these numbers exactly, but, but you know, it's kind of like, the first order of math of it is, Of course, you know, being able to write files or to complete this function or complete this line or things like that, you know, it helps a ton. It's a really great experience, right? There's a lot of parts of building software that obviously are almost not that at all. Right? It's, you know, you have a bug that you're trying to fix. And so you, you, you spin up the local server. You click around on your own products on the front end and try to reproduce the bug yourself. You know, once you have the error, you, you take a look at Datadog and, and you see what happened and you try to find other errors in the logs. You know, you look at those files and you see what went wrong.

• 34:10Speaker 00

  You make some edits, maybe you go and like rerun the whole process again now that you, you know, to just make sure your change looks right. Right? And, and that's a lot of, you know, what it means to be a software engineer. Right? And, and you know, these are processes that take real time. I, I think we're going to shift more and more towards this agentic workflow because, you know, that's in some ways, it's kind of like the, the way to really get to that, you know, 200%, 500%, 1,000% gains that, that, that we'll be getting to with software engineering over the next few years.

• 34:38Lenny Rachitsky?

  Okay, enough talk. Let's show people what the heck this actually looks like.

• 34:41Speaker 00

  Let's do it.

• 34:42Lenny Rachitsky?

  You've got a couple of demos prepped that show a few use cases that you found helpful.

• 34:47Speaker 00

  Yeah.

• 34:47Lenny Rachitsky?

  So you're going to pull up your screen and then it will

• 34:49Speaker 00

  Let's do it.

• 34:50Lenny Rachitsky?

  Kick it off and then we'll talk as it's happening.

• 34:51Speaker 00

  Yeah. And so, so the whole process, obviously, of working with Devin is working asynchronously. And so I, I, I thought it'd be cool for us to actually just watch Devin a little bit in action and then, you know, we can, we can go through some other examples of, of work that Devin's done or things that Devin does for us, even on our team, for example. But, but, but then we can check back in asynchronously with our, with our Devin after.

• 35:12Lenny Rachitsky?

  I'll do it.

• 35:13Speaker 00

  And so I'll share this real quick. And the, the key thing I, you know, that I would just emphasize here is a lot of it, obviously, is really just about, yeah, thinking about as a software engineer or as engineers ourselves or engineering teams, engineering teams, PMs and so on, you know, what are the, what are the things that we would want to build that we would want to hand off? And so, you know, we have Devin set up with our own Devin code base, for example. And so I'll, I'll go ahead and kick off a Devin for that. And so I'll just say, hey, @Devin, I'm on with my friend.

• 35:45Lenny Rachitsky?

  Hi Devin.

• 35:47Speaker 00

  Can you modify Devin Web App to... Let's feature your newsletter as part of the Devin.

• 35:58Lenny Rachitsky?

  Let's do it. On the real Devin website.

• 36:03Speaker 00

  Lenny's site.

• 36:06Speaker 00

  And so we're going to kick this off. As you can see Devin gets started instantly and goes ahead and respond. And again, you can work with this asynchronously, you can work with it synchronously as well. For this, we'll just kind of go in a little bit and see exactly what's going on. But as you can see here, Devin's going through files and taking a look through a lot of stuff. And so we can follow here basically as we need to and see what makes sense. You can see Devin's already called out a few particular pieces, right? Where there's the sidebar, which we have implemented on the front end. And there's pieces there. And we're going to have a new component. And that component's going to link to Lenny's website. That all sounds good. Devin's asking us any questions, if there's anything that we have here. Same story here where it's kind of, you can let Devin make its own decisions and hand off.

• 36:51Speaker 00

  Or you can go ahead and be, kind of give some more thoughts, right? Should the button open in a new tab or within the application? I'll say, "Let's open it in a new tab."

• 37:02Lenny Rachitsky?

  And you could answer these at any point? Like, is it waiting for you to answer?

• 37:05Speaker 00

  You can answer these at any point. You can hand off, hand back off.

• 37:07Lenny Rachitsky?

  But it's not going to be like, "Just goddammit, I just wrote it this way."

• 37:11Speaker 00

  That's right, yeah. One of the big pieces with Devin is, Devin will always be enthusiastic. You know, will always be ready to put in the hours.

• 37:19Lenny Rachitsky?

  Thanks for changing scope, thanks guys.

• 37:23Speaker 00

  And so we'll give Devin a chance to work and it's going to go through these files. And it'll make a pull request for us and we'll see and go from there. But I thought it'd be fun to show some other examples of Devin in action as well. One of the examples, actually this morning, which I just used Devin for, is I asked Devin to help me brush my own facts up for this podcast. And so, obviously a huge fan of the podcast and the newsletter. I asked Devin, "Hey Devin, going to be on the podcast, could you please research everything you can about him? And make a nice website quiz for me so that I can make sure I know my facts, right?" And so Devin, this was just this morning, I asked Devin to do this and I'll kind of just show what Devin did. It looks like, yeah, went to Wikipedia first.

• 38:05Speaker 00

  Unfortunately, it's not a page on Wikipedia, which is, Lenny, we'll work on that, I guess.

• 38:12Speaker 00

  They did you dirty. I mean, we need that. We need a waitress. And so then, you know, then it went and found it on Spotify.

• 38:19Lenny Rachitsky?

  So you're watching what it's researching live?

• 38:20Speaker 00

  Yeah, yeah, yeah. So this is, this was this morning, obviously.

• 38:23Lenny Rachitsky?

  And this is a playback of what Devin did. This is, this is part of Devin. You could just like, watch what it did.

• 38:29Speaker 00

  Yep, yeah. And so, especially when you're building engineering projects or something like that, you can see kind of like each of the steps that Devin was doing. Or if Devin tested the code locally, obviously, you want to be able to go and look and see, you know, what Devin was cooking around with and testing or things like that. So it found the newsletter. It's going and looking at this, right? And it's going and reading all of this. And then it says, okay, let's get started with that, with putting the code together, right? And so it says, hey, I've researched, you know, it's going through and writing all of this, putting the app together. It plays its own quiz itself, actually, which we should just, we should just play this quiz, actually. Let's, let's see, let's see how much I know. What is the name?

• 39:08Lenny Rachitsky?

  What is the name of the podcast? Lenny's podcast?

• 39:12Lenny Rachitsky?

  Let's, for people not watching, so to say, approximately how many subscribers? A million? Very good.

• 39:17Speaker 00

  Yeah, yeah.

• 39:18Lenny Rachitsky?

  What is, what are three main topics Lenny's focused on? Oh, product growth and career. Very good. It's a good quiz.

• 39:27Lenny Rachitsky?

  What does Lenny's do besides podcasting? Okay.

• 39:30Speaker 00

  Writing, angel investing and advising. How often does Lenny publish? Once a week, right? And so, yeah, so we can go through all of these and do all of these. And I took this quiz, by the way, obviously, to make sure that I was well prepped. But, yeah, this is kind of one of the more fun examples, obviously, of just like.

• 39:46Lenny Rachitsky?

  Scott, how many, how many, how many subscribers do I have in my newsletter?

• 39:49Speaker 00

  Over a million, actually.

• 39:53Speaker 00

  And then one, one last one I'll show, and then maybe we can come back to our initial run after. But is, you know, like I was saying, like, a lot of this is really built to work with all of the existing code workflows out there. And so, you know, for example, we were doing some exploration with the DeepSeek repository on GitHub. And we imported it into Devin and we got our own fork of it set up in Devin. And a couple of things I just wanted to show here, you know, one is Devin sets up its whole wiki with all of its internal understanding. And so when Devin indexes the codebase, obviously. Building a representation of the codebase and learning it and improving it over time is one of the big things that Devin does. And funnily enough, we found that naturally, humans really are interested to understand this codebase representation as well.

• 40:36Speaker 00

  And so Devin Wiki is something that we built here, and you can take a look at all of these different pieces and see each of these different things. Here are the FP8 operations, here's an SG lang integration, there's diagrams of how the different layers are built and put together, there's deployment operations, there's a lot of details about the architecture as well. And you can ask questions about it as well. And so, for example, you can say, how does DeepSeek handle multi-token prediction designed for spec deck? And it'll go through and it's able to kind of search through the entire codebase and give you an informed answer based off of that. And so we use this a lot, and it helps when you're scoping out a task for Devin and doing an initial prompt. It also helps, obviously, just in a vacuum, like you often have questions about your codebase that are really nice, right?

• 41:20Lenny Rachitsky?

  This episode is brought to you by Atio, the AI-native CRM. Atio is built to scale with your business from day one. Connect your email and calendar, and Atio instantly builds a CRM that matches your business model with all of your companies, contacts, and interactions enriched with actionable insights. Sync in your product's usage, billing info, or any other data sources, and Atio's flexible data model will handle it all without any rigid templates or workarounds. With Atio, AI isn't just a feature, it's the foundation. You can do things like instantly prospect and route leads with research agents, get real-time insights from AI using customer conversations, and build powerful AI automations for your most complex workflows.

• 42:05Lenny Rachitsky?

  Industry leaders like Flatfile, Replicate, and Model are already experiencing what's next for CRM. Go to attio.com/lenny to get 15% off your first year. That's attio.com/lenny.

• 42:21Lenny Rachitsky?

  Something that I've I've learned as I've been talking to more and more AI building companies and apps is there's a big difference in how large of a codebase they could integrate into.

• 42:31Speaker 00

  Yeah.

• 42:31Lenny Rachitsky?

  And that's a big deal for companies that are existing versus startups, people that have large existing codebase. What's the, how should people think about what kind of codebase Devin can plug into?

• 42:41Speaker 00

  Yeah, yeah. So we go all the way to to the biggest codebases possible, right? And one way I'd kind of put it is, you know, how the way that that that we as engineers would think about a large codebase is certainly, you know, when you're making changes or when you're thinking about a particular task, you're not, you're not bringing in every single line of the codebase at once, right? You have a high level abstraction that that you're able to think about and look into, right? And then you're obviously able to zoom in and get to kind of higher resolution on each of these different things, right? And so Devin works in much the same way where, you know, the first thing it'll do is it's going to kind of figure out like the high level architecture of of what's going on here and what this is built for and so on.

• 43:21Speaker 00

  But within each of the components, it's obviously also going to be able to to zoom in and and give some more detail about each of these. And so here's, you know, FP8 to float 16 and how exactly a lot of that is set up, right? Here's each of the the different parts of the codebase. And so similarly, it's, you know, we've built this to be scalable.

• 43:38Lenny Rachitsky?

  It's essentially coming back to the engineer as architect is now it's helping you understand the architecture.

• 43:44Speaker 00

  Yeah.

• 43:45Lenny Rachitsky?

  Kind of circling back to that.

• 43:46Speaker 00

  Yeah, yeah, exactly. And one of the fun use cases that we've seen actually with folks is is they'll often actually use Devin, get Devin's help to to onboard new engineers on the team, right? And, you know, when you're new and you're joining, there's obviously a lot of questions that you have about the codebase or about how things are set up. It also sometimes can be a little bit awkward to, you know, to ask your mentor or your manager to the questions. And if you're worried that they're going to be really dumb questions, right? And so it's nice to just be able to ask Devin and to to go through Devin's Wiki and to understand these internal representations, right?

• 44:14Lenny Rachitsky?

  I think that's really interesting because it comes back to your point that Devin is not just a junior engineer. It's what you call a jagged, jagged engineer.

• 44:21Speaker 00

  Jagged intelligence.

• 44:22Lenny Rachitsky?

  Jagged, jagged intelligence where it like, it's almost like a staff engineer at understanding the codebase. Usually you have to ask an engineer that's been there a long time, what does this do? Where's this thing? How's this work? And it feels like Devin's very good at that.

• 44:34Speaker 00

  Yeah, yeah, yeah. Obviously, in the retrieval and kind of processing a lot of code and a lot of tokens at once is, you know, something that language models are really great at, right? And so basically, being able to get those gains in the places that you need them is really great. Yeah.

• 44:49Lenny Rachitsky?

  Sweet. All right. You've got a couple more use cases.

• 44:51Speaker 00

  Yeah, one last flaw I'll show is just, you know, we just rolled this out last week, actually, but it's a full kind of Devon automation setup with Linear, right? And so, you know, if you have tasks that you're doing on the DeepSeek repository, for example, and it's all set up, all you have to do is you just add the Devon label, and Devon will come through and it'll give you this, right? And it's going to give you its thoughts on what the task looks like. And, you know, you can take a look at each of the particular files that you see, or it'll point out snippets that it thinks are important. And from there, if you feel good about, if you feel good about what was built, or the conclusions that we came to, then you can just start off a Devon session that will go and actually do that work. So.

• 45:30Lenny Rachitsky?

  That is insane. Like, that sounds like such a simple idea. But essentially, what you're saying is there are tasks in Linear that are fixes and features, and now Devon just goes off and can just do them for you.

• 45:43Speaker 00

  Yeah, yeah. And so it's definitely like, it's a hands-on process. You know, you certainly want to be involved when Devon is scoping out the task or giving you its thoughts. And the nice thing, too, by the way, is Devon will give you its confidence level. And, you know, here's how likely I think I am to really understand this piece, or that piece, or whatever, right? But, uh, but it helps make things a lot faster, right? And to your point, you know, it's like, a lot of product managers, for example, obviously, love to be able to use Devon in Linear to understand things better, the codebase better, or things like that. And, you know, Claire Vo, for example, from Launch Darkly, is a big Devon user. And she loves basically going and scoping out tasks, or asking data questions, or asking, hey, what's, you know, what's going on?

• 46:27Speaker 00

  Or like, is this merged into production yet? Or, you know, is this a feature flag right now? Or what percent of people are getting this or that feature? And it's a clean way, basically, to make that intelligence much more accessible.

• 46:40Lenny Rachitsky?

  I love just like with the integration with Linear that you can still keep it really simple. You know, you add a little ticket like, hey, this link to this homepage with do this and Devin will be really good at understanding what you mean and then show you here's what I'm thinking. Is this right?

• 46:53Speaker 00

  Yeah, yeah, cool. Okay, so yeah, so Devin did finish working. It seems like there's something going on with CI and it's debugging that right now, but it went ahead and put up the initial first pass pull request and we can take a look.

• 47:04Lenny Rachitsky?

  Let's do it.

• 47:04Speaker 00

  And it's, uh, this is the Devin website, obviously, in this custom deploy and we have Lenny's newsletter right here.

• 47:10Lenny Rachitsky?

  Let's ship this to production. Let's go. We'll be so confused.

• 47:15Speaker 00

  Yeah.

• 47:15Lenny Rachitsky?

  That's amazing. Okay, show it again real quick. So just added it to the homepage of, of Devin's.

• 47:22Speaker 00

  Devin obviously has access to our Devin codebase. It does a lot here and so it's super familiar with all pieces here.

• 47:28Lenny Rachitsky?

  Beautiful.

• 47:28Speaker 00

  And it said, yeah.

• 47:29Lenny Rachitsky?

  I like how that looks.

• 47:30Speaker 00

  We've got Devin search, we've got Devin Wiki and we've got Lenny's newsletter.

• 47:33Lenny Rachitsky?

  Dry some grapefruit. I'll link to your site. You link to my site. We'll get some page rank going.

• 47:37Speaker 00

  Yeah, yeah, yeah.

• 47:39Lenny Rachitsky?

  Okay. Is that a good example? Oh, there it is. What a beautiful website for my newsletter. Is that just like a good example of the kind of thing Devin is very good at? Like here's a very specific thing to change on the website. How does ship people think about what Devin is very good at and maybe where it starts to fall apart?

• 47:54Speaker 00

  You know, the way that we often describe it is I think Devin is best when it is working on tasks that are well defined. You know, it's one way to put it is you want to be giving Devin tasks, not problems, right? And a lot of these things, you know, like what you just saw, which was kind of like a quick front end feature request or a bug fix or adding testing and documentation or, or things like that. You know, one of the things that, that makes a loop really nice, obviously, is a quick way to iterate and test. And so with something like this, obviously, super easy for us, for example, to just go pull up the preview and see that the link works, right? Obviously, would be easy for Devin to do as well. Devin will often go and log into Devin and start a Devin session and make sure it's, you know, when, when it's working on our own codebase, which is kind of hilarious. But

• 48:38Speaker 00

  yeah, you, you generally want something that is kind of like is easy to verify and easy to test is the main thing. And you can work on bigger projects or bigger asks as well, obviously, but in that case, you should certainly expect to, to need to steer Devin more to make sure you're really, you know, to, to make sure it's, it's going the right direction.

• 48:54Lenny Rachitsky?

  That's interesting because that's very similar to the way people talk about synthetic data and reinforcement learning, creating data that's very easy. There's like a very definitive answer, yes and no.

• 49:03Speaker 00

  Yeah.

• 49:04Lenny Rachitsky?

  And it's very clear.

• 49:06Speaker 00

  Yeah.

• 49:06Lenny Rachitsky?

  Yeah. Okay. Let me ask you this question. What's something that you guys debated a lot as you were designing and building Devon?

• 49:14Speaker 00

  I'll give a couple that comes to mind. You know, one I would say is, um, yeah, a question of, I'll call it like how opinionated we should be. You know, we had the workflows that we used to Devon for, which was very much, as you can see for, you know, basically integrating to our Slack and GitHub, making pull requests for us in our repos, responding to issue reports or things like that. And naturally, you know, we've, we've had certainly a lot of other, you know, kind of different things that have come up that folks have tried. I mean, we have, we have folks who like order their DoorDash with Devon, for example, even. We have folks who, who certainly, you know, a lot of people who, who are kind of building cool, cool websites from scratch or, or working on things like that. And yeah, I mean, it's, it's been an interesting trade off for us where I think

• 49:56Speaker 00

  the way that I would describe it is, you know, in our products, certainly, you know, the, the large bulk of the features that we build are for this kind of like, you know, making pull requests and engineering teams use case. But I think, uh, basically our, our kind of general stance with all the others is obviously if, if folks want to use Devon for that, that's great. And we want to just kind of make sure that they're, they're fully aware about the limitations and about where things get caught up. It's, it's, it's funny with, with AI and especially because, you know, I would say one of the, I would say the most common pieces of startup advice out there, I would say is, you know, focus on a really niche cohort, you know, do things that don't scale, you know, make, make, make one use case. That's really great. Right? And then you grow from there.

• 50:36Speaker 00

  And I think that's, uh, you know, I, I, I, I think that's great advice across the board. But yeah, it's kind of interesting because, you know, I think with generative AI, you, you naturally see this where a lot of product experiences can turn out to be more general. Right? And, and so it's, it's an interesting trade off for us. You know, this is something that we still always go back and forth on and how much do we want to, you know, yeah, to, to, to, to do more to, to support all the other kind of use cases out there and to, to handle other things that, that folks might want to do with Devon. I think another one that comes to mind is how much Devin should be, let's say, like a single comprehensive project experience versus like a suite of tools. And as you can see here, you know, we have, we have Devon's search, we have Devon Wiki, you know, we have the linear ticket scooping. And certainly, you know, these, these tools interact with each other.

• 51:21Speaker 00

  But I, I think as time has gone on, we have, we've, we've seen it more and more as, as really building this suite of tools. And I think that, you know, I think the core agent experience and the core kind of agent that will go off and build each of these, build things for you, for example, is always of course going to be, you know, that's Devon and that is like the core piece, I think that will always be what's really special about, about our work. But, but I think that all of the other features out there, that, you know, the, the, it's, it, the, there is a complex suite of, of work that's required for real world software sharing. And, and engineering is just messy at the end of the day, right? And so, so I think there are a lot of different flows and a lot of different use cases that make sense. And, you know, an obvious thing to point out is, is you could ask the same questions to Devon's search as you could to Devon, right?

• 52:05Speaker 00

  And Devon will go through and it'll do the same thing. It'll go through and look through the files and give you an answer and stuff. But, but with that said, you know, on the one hand, I think on the capability side, there's certainly a lot you can do to really optimize things for very specifically question, answer about this repository. And that made sense to, to really kind of build into a specific kind of feature. And then on the other side, I would say, uh, we found that users actually really, uh, really like having this, this access of control, right? Sometimes you, sometimes you have a, a task that you're thinking about, but you actually don't want Devon to get started on the task just yet. You want to ask Devon and understand what parts of the code base might be relevant, right? And so you want to be very direct about saying like, this is just an ask and I just want to see the snippets of code base that relate, right? Or I just want to look at the Wiki and understand the existing representation.

• 52:49Speaker 00

  And so it's kind of on, on both the capabilities and on the, the UX side, we've, we've found that that's kind of what, what's naturally made sense over time.

• 52:57Lenny Rachitsky?

  Let's talk about the landscape then of just other companies in the space, which is something a lot of people are always thinking about. There's all these different approaches. You guys are going full on AI engineer. There's obviously IDE companies. There's also just like models being built that are really good at engineering. Everyone's kind of starting to build agents now. You guys are ahead on this in a lot of ways. Like OpenAI just recently said they're going to build a software engineering agent. Anthropic's got something there. You know, Curse and WinSar have their own little agents and Replit. Thoughts on just kind of where you guys fit in in the landscape? And then where you, how you think you win long term? How do you think about that?

• 53:31Speaker 00

  Yeah, yeah. And for what it's worth, you know, I think all of these are incredible teams. I think, uh, you know, really smart and really forward thinking folks who are building a lot of great products out there. And it's, uh, I, I, I think there's, there's, there's a lot to do, honestly, you know, over the next few years with, with the advent of AGI or whatever you want to call it. You know, I think, uh, one, one of the quotes that I love is, is in 2017, if you asked if we had AGI, the answer is no. And in 2025, if you ask if we have AGI, the answer is, well, you have to define AGI. And, you know, it depends on your subject. Yeah, right. And I, I think it does kind of get to the point of, of, I mean, there, there is a lot of really amazing stuff happening. You know, I, I think that it's easy to underrate, I would say, just, just how, how big of a shift it is that we're seeing, right? Where I think there are a lot of great products out there.

• 54:17Speaker 00

  For example, over the last 10 years, 20 years, 30 years that have made each of these kind of like, uh, kind of these different niches of, of the, the, the life cycle of building a product a little bit easier. For example, right? There's, there's great products out there for instant response. There's great products out there for logging. There's great products out there for billing. There's, you know, all, all of these different tools, right? And, and the obvious thing is, you know, what we're seeing with AI is all of these spaces are, are going to be moving multiple times faster. You know, and this is going to be like an order of magnitude shift, if anything, right? And so I, I think from our perspective, you know, we've obviously had a very specific lens that, that we've bet on this whole time. And that is, you know, autonomous coding agents. And there's, there's a lot of problems to solve there, to be honest, right?

• 54:59Speaker 00

  Like the, the, there's still a ton to do on the core capabilities, certainly. And, you know, we see cases all the time where it's like, wow, why did Devon make that decision? That seems, you know, no human engineer would have ever done that. You know, there's, there's all sorts of spots where, you know, with the product interface, there's obviously a lot to think about. And I think it's, it's, by the way, not just like a single thing that, that we're working towards, but something that will change with every addition of capabilities. Like I kind of think of it as like, There's 20 generations of agent product, you know, agent coding experiences to come. You know, I think that I think the one that we'll get to over the course of several years is probably something where you don't even look at the code at all, right? And you're actually just looking at your own product and you're just able to look and specify and say, hey, you know, this button should be a little bit rounder, let's do that.

• 55:42Speaker 00

  And by the way, let's add a new tab here and maybe we should save this information. Let's start up a database table and let's index it on X, Y, and Z columns. And you're just, you know, basically working with your products in real time and having your agent build out those things for you. Obviously, there's going to be a lot of generations, you know, in between here and there. But I think the product experience itself is going to change every single time. And then obviously, you know, there's all of the practicality of just getting it out there in the world. And so, you know, folks obviously need to learn how to use the new technology. There's a lot to do to deploy into all of the messiness of real world software. You know, there's a lot of COBOL out there still, there's a lot of FORTRAN out there still. There's, you know, there's lots of kind of abstractions and details that folks have done.

• 56:26Speaker 00

  And so I think from our perspective, you know, we have, we have been, been since the beginning, have been laser focused on agentic coding. And that is the one thing that we've really believed in, it's the one thing that we've designed for. And, you know, that goes all the way to even the revenue model with ACUs and having the usage based setup. It goes into obviously all the product experiences of thinking how, okay, like where do you want to talk to Devin? You know, you want to be able to talk to Devin in Slack. You want to be able to spin this up from your issue tracker, or you want to be able to, all of these things. And then of course, the capabilities. And so I think it's, I don't think there's any one easy answer. I think it's obviously a combination of things, but this is really the, this has been the space that we've lived in and spent all of our time in for the last year and a half.

• 57:11Speaker 00

  And it's going to be that way for the next five or 10 years too.

• 57:14Lenny Rachitsky?

  Along these lines, a big question everyone always has in AI is moats and defensibility. It's a question I've been asking every founder that comes on. How do you just think about how to build a moat in the space when it's so much easier to build? And these models are, you know, so much is built on these models that are themselves advancing so quickly?

• 57:30Speaker 00

  I'd give one slight kind of tweak on that, which is I think it's often less about moats and more about stickiness. And what I mean by that is, you know, moats are in some sense, typically what folks mean by a moat is something that means that a competitor couldn't even enter, you know, the market. And I agree that at a high level, you know, a lot of different folks had different layers of the AI spectrum. You know, the the the foundation labs or the application layer or so on. You know, I don't think there's any kind of like hard barrier that would prevent others from entering. I think what does exist is stickiness, which I would kind of define as, you know, once you have a product experience that you really like. Are you excited to keep using that experience? Or is there a kind of like, you know, i- is there an effect where it is just as easy from now on to just switch on to a new one and learn a new one and so on?

• 58:15Speaker 00

  And I think from that perspective, I think there's a there's a few things that are really great about coding agents in particular. You know, one I would say is there is a lot of just inherent kind of stickiness and learning and buildup over time. Which is that as you use Devon and as your whole team uses Devon, it's the same thing with with an engineer, right? If you're joining on day one versus, you know, since you've been at the company for five years, you know, you wrote half the code yourself. You you've touched every file, you've built every single piece, right? You know, all the engineers. And so similarly, it's like Devon will really learn and build its representation of of your code base and of your stack and of your process over time. And we'll be able to do a lot more with that. And then the other piece of it, which I think is really is really exciting, I'd say, is

• 58:56Speaker 00

  there really is a lot to do of what I would kind of call like a multiplayer aspect of of code. Which if you think about it, is how a lot of things get done in the real world, certainly, right? And so, you know, it's it's one thing to have, you know, your own experience, which you use yourself as just an engineer. But for example, ourselves, like we see this all the time where some engineers are working with Devon and teaching Devon things. And as I mentioned, like folks will have Devon onboard their new engineers and and kind of convey that knowledge to them, right? Or similarly, it's like, you know, I'll start a session with Devon in Slack. And I'll say, hey, you know, it'd be cool if we could do this thing. And some other engineer will chime in and say, oh, by the way, like, the reason we did it initially was X and Y. And so Devon, just make sure when you do this change that you, you know, still support that workflow. And Devon will say, okay, sounds great, right?

• 59:41Speaker 00

  Or Devon will make a PR, you know, I'll be working with Devon, we'll make pull requests in GitHub. And somebody else will be reviewing that PR or give some comments and Devon will work on that too, right? You know, you'll be in linear. And so, so all these kind of spaces, it really does just kind of set up for an experience where. Basically where Devin can just grow in the value that it can provide for your whole work over time. And so I think from that perspective, like if anything, you know, it's we want there to be a lot of innovation and a lot of new products and so on. You know, I don't think that the goal is to try to lock other people out of building, you know, there's a lot of stuff to build and I think there's going to be a lot of different experiences. I think from our perspective, what we think about is more like, how can we make Devin more and more and more useful as you're using it more?

• 1:00:27Lenny Rachitsky?

  It's very similar. We had Michael from Cursor, the CFO of Cursor on the podcast, and he had a similar point of just he thinks smotes are just kind of like consumer, like Google is the way he thinks it's like Google, where people can easily switch, you just have to stay the best. And that's the answer.

• 1:00:43Speaker 00

  Yeah.

• 1:00:44Lenny Rachitsky?

  And it feels like you're adding to that of just like, but also if you can create some stickiness where it is very hard to leave because it's so good at what it's doing and it's built knowledge and integrated to your workflows that builds on that.

• 1:00:56Speaker 00

  Yeah. And I think one of the things that's, that's, that's, you know, that's nice about our space too, is software engineering, for better for worse, is, is, has a very clear tie to value. And what it means is, I guess one way to put it is, is there is always kind of like a clear next level, at least for the next while, you know, I think there, there could be some point where you're just like, all right, just build the entirety of YouTube for me, you know, and Devin just does the whole, it's like, there's probably been like a hundred million hours of human engineering time built, building YouTube, building the algorithm, building all the infrastructure, all of the, the everything, every little detail. And like, you know, maybe there's some time where Devin just does that out of the box, you know, that that's obviously going to be a long time from now. I think on the interim,

• 1:01:38Speaker 00

  on every level in between, obviously, it's, you know, it makes a difference, the, the quality of software engineering. And I think one of the cool things with developers, obviously, is developers are really willing to, to, to, to learn new experiences and to put in effort if it means that they're able to have a higher and higher quality experience. So.

• 1:01:57Lenny Rachitsky?

  Awesome. I'm going to spend a little time on the tech that enables Devin without divulging. Trade secrets, just what allowed you to make Devon so good? Was there like an unlock with a certain model? A lot of, some folks have shared like 3.0 and 3.5 was a huge unlock for a lot of their products. Just what, what's kind of the key to the way you've architected or built Devon that makes it work so well?

• 1:02:20Speaker 00

  We obviously, you know, we've, we've been betting on agents for a long time. I, I, I think that agents were, uh, were doable and workable like a lot earlier than most folks might have thought. But certainly I think as the, as the community has really rallied around it, I mean, you see the impacts of that in the pre-training. You see the impacts of that in, uh, in, in, in a lot of the work that's, that's done with these models. I, I actually don't think there's been any, like from our perspective, I don't think there's been any single, like step function base model shift or anything that has been kind of like a night and day difference in Devon. But I certainly think that the curve of, you know, every, every point on the chart, I mean, there's a new model that comes out every like, every week now, has, uh, has, has, has obviously made a big difference in terms of what we've been able to do.

• 1:03:04Speaker 00

  And then obviously on top of that, you know, we work with, with, with the research teams at all these foundation labs to, to, to do a lot of our work on top. And so I, I think that my, my hot take here, which I would give is I think the, I think in terms of base intelligence, we're honestly basically already there. And, and, and I think a lot of what we see actually, and what we spend our time on, uh, is less so. Obviously we, we don't pre-train our own models or things like that, you know, it's, it's, is less so like increasing the base IQ of a model, for example, and more about kind of like teaching it all of the idiosyncrasies of real world engineering. Right. And, uh, and thinking about here's how you use Datadog and do this. And, and here's how you might diagnose this error. And here are the different things that you could run into, and, and here's how you handle each of those. And when you're ready, here's how you make GitHub PR.

• 1:03:49Speaker 00

  And, you know, this is true in engineering, it's true in every other space as well. I mean, there's so much detail and idiosyncrasy to, to the work that we all do, obviously, uh, day to day. And, and a lot of it is kind of like, Like teaching the model to mirror the complexity of the real world, I would say, rather than rather than kind of like getting it to some some higher fundamental level of problem solving, which I think the foundation labs are doing a really great job.

• 1:04:15Lenny Rachitsky?

  There's something you shared when we were chatting before we started recording around the growth of previous kind of transformative technologies were very hardware oriented and they there was like a limiting factor to their growth and AI is not that. You just share that insight.

• 1:04:29Speaker 00

  For a number of reasons, I think AI is going to be the the the biggest technology shift of our lives. But but I think one thing which is what we were just talking about before this, which is is is, you know, most of the big tech revolutions that we've had over the last 50 years. I mean, I'm thinking about like personal computer and the internet and the mobile phone and so on. You know, they they all had this this this big hardware component. That was that was a big part of the distribution, right? And so, you know, you had the internet and initially it was just these universities that were talking with one another. But obviously, over time, we got the whole world plugged into the internet and it took years and years and years. Same thing was true with mobile phones, same thing was true with PC, right? And that, you know, the the the thing that's interesting about that in particular, which is I would say we're we're already seeing the effects of that is,

• 1:05:15Speaker 00

  you know, in these hardware distribution regimes, you're obviously there's a lot that depends on real time, right? And so, you know, folks who were building for those industries kind of saw their market grow and grow and grow basically steadily year over year as the number of people with mobile phones increased, right? As the number of people connected to the internet increased, right? And and and many of those businesses, it's it's it's still crazy to think about. But but many of those businesses got started right in the beginning. I mean, like Apple and Microsoft started like right around the same time, you know, and the same is true for a lot of the great internet businesses or or wherever. But but but certainly it was kind of like a it was a it was something that touched the whole world, you know, with time or or a large fraction of the whole world. And and it had a really massive impact, but but it it took place over several years, right? Because of of the time that it took.

• 1:06:00Speaker 00

  And I think one of the things which is already, I'd say, different in in AI is Just how explosive the technology can be. You know, once, once AI could, you know, and I, and I think we're firmly in the, you know, in, in past the inflection point in AI could, right? Where it's, as an engineer, you know, if you're not using AI at all, right? Good. I mean, you're, uh, you know, you're falling behind, honestly. And, and, and it is a technology that everyone should have and should be using. And, and there's no kind of like, uh, there's no weight on hardware distribution that, that is causing that. And it means that, that it, it means that the space is just growing so exponentially, basically.

• 1:06:36Lenny Rachitsky?

  Michael Ballin has this interesting point that, uh, cliches are cliches because they're so true. And that's why you, they're like cliches are like, I heard that a million times. And I think it's like, people hear this like, yeah, I know, but like, it's actually insane what is happening. Yeah. That's what, that's why you're here to help us through this transition.

• 1:06:52Speaker 00

  Yeah, no, I mean, it's, it's a fun time and, and, and I think there will be, uh, you know, real, real investment and real work that it takes. But I, but I, I think from the perspective of us as engineers, for example, I think it just means it's, it's, it's so important to, to, to stay in the loop with everything that's happening. And, and it's, you know, as we're seeing, it's not only because of your learning and your ability to work with these technologies. But it's also, you know, about basically like teaching, teaching the AI, you know, what, what there is to know about your code base. In order to make it really effective at building with you and, uh, and, and, and doing more of the things that you would want it to do. So.

• 1:07:26Lenny Rachitsky?

  So along those lines for company, people listening that they're like, hey, we should be using Devon at our company. What are, what are things you've found to be helpful in helping an engineer at a company get adoption and be able to use Devon? Either culturally or logistically?

• 1:07:42Speaker 00

  So, so a pattern which we often see with folks is there will be a few folks at the team who are really excited. Uh, and want to try out the new thing and they want to put in the, the, the investment and, and, and are really excited to get it going. And they'll go through all the setup, you know, they'll give Devon the repos, they'll teach Devon how to run the lint and the CI and, and all of those details, right? And they'll start off by, by giving it those initial tasks and kind of like. Help Devon build a foothold, basically. And as time goes on, eventually, folks will see, wow, Devon's writing all these PRs. Devon's doing this.

• 1:08:13Lenny Rachitsky?

  Who's this Devon person that just joined the company is just knocking out PRs?

• 1:08:17Speaker 00

  Yeah, and they'll see that and then naturally they'll get on and they'll get an account. And one of the cool things, of course, is by the time they join, Devon already knows a good amount of detail about the repositories that they're already working in and they're working with that. And so, so one of the really cool things which we often see is, yeah, that the early adopters themselves can really pave the way, I think, for everyone else on the team. But, but yeah, I think the main thing I would just kind of call out is, yeah, it really does take, it's a very different product experience, right? And I think it's, for what it's worth, I think there's still a lot more that we should be, you know, that we can do to, to make it as intuitive and as clear as possible to folks like how to use Devon and what the right steps are and how to really maximize value out of Devon.

• 1:08:58Speaker 00

  But I think that, yeah, it's the kind of thing where if you, if you put in the investment and understand exactly, you know, what it takes to get Devon to be successful, it's like, you know, we've, we've found ourselves that as time has gone on, we just use Devon more and more and more with, with every, with every kind of, every next update, so.

• 1:09:16Lenny Rachitsky?

  So let me follow that thread. There is a question I ask every AI app building founder, which is if you could sit next to every new user of Devon and whisper something in their ear to help them be successful with Devon, like one or two tips. What would those tips be?

• 1:09:31Speaker 00

  I, I think the biggest thing I would say is it, it really is just, you know, treat Devon like your new junior engineer. And I think that's, that's the biggest thing. I think folks come in and, you know, they, they see the blank, the blank page and they think of all sorts of kind of like various things that they want to try out. They think of lots where, you know, I, I think typically the flow that we see that works best is. Obviously, you know, you can try demos, you can, you can do things, but, but a lot of it is just like, yeah, let's, let's figure out what tickets we want to get done today or this week and let's have Devon get started on those. And, you know, let's start with the, kind of the, the easier ones and then work with Devon and understands like what, what things Devon needs to get set up to be able to test its own code and do this well.

• 1:10:15Speaker 00

  And then let's, let's scale up over time. And then obviously it's, you know, as you work with your engineer, you understand better kind of how to communicate with them or, or what, what are the right tasks or projects to bring them in on. But I, I think that's, yeah, that, that really is the one liner for us.

• 1:10:31Lenny Rachitsky?

  Okay. Uh, there's a question I've been meaning to ask. I just want to get back to this because it's something I think a lot about. With, with Devens, everyone's going to have five Devens, let's say 10 Devens. Everyone's kind of turning into a, basically an engine manager with a bunch of junior engineers.

• 1:10:46Speaker 00

  Yeah.

• 1:10:46Lenny Rachitsky?

  Which isn't necessarily the best job in the world. It's just a bunch of review. At least you don't have to do performance reviews and one on ones. But you know, it's like sitting around checking a lot of PRs all day. There's a sense of you become an architect and which is a kind of what every engineer wants to become eventually, right? They're all like, I just want to think about the architecture. I don't want to code all these stupid fixed bugs. So I get that that's, you know, there's a good part side to that, but just how do you, I imagine you're thinking a lot about this, just like, how do you make life pleasant and fun and enjoyable as basically an engine manager of say 500s Devens in the future?

• 1:11:19Speaker 00

  Yeah, I can just imagine the performance review. You know, it's Devon, you've done a really great job on your task and I really would like you to be more proactive in the team meetings. I just, yeah, it's, no, so what I'd say, it's funny actually, because it's something that, you know, in terms of the wording that we thought a lot about as well. It's just, you know, we, we've used the term like manager of Devens in the past, which, which of course I think is, is a big part of it. But, but I, I think that the, the only thing I would point out here is I, I do think, I, I think that the bricklayer versus architect is closer to the experience than being a manager. Because I think a lot of the difficulty of, of, you know, management or, or, you know, the, the reason that, you know, that, that, that people shy away from it is, is more because of,

• 1:12:01Speaker 00

  you know, a, a lot of the kind of various, let's say like, there's, there's kind of like all of the kind of like the context and the ownership and kind of like the responsibility and stuff. And then there's also kind of all of the, the, the emotional aspects of it, right? Where I think working with Devon is a little more like just being kind of like having.

• 1:12:22Speaker 00

  More is like having an interface to hand off tasks and build tasks, right? And so, you know, the, the, the parallel that I would kind of draw is, you know, when we invented Python, obviously, like, we, we didn't, you know, it's, it's, it's like, i- i- in many ways, you know, the description of the, and the outlining of tasks is, obviously, it was like a different paradigm, but, but I, I think it certainly was, it was nowhere near, you know, what, what folks typically think of as kind of like management bureaucracy today, right? And I think that with Devin, a, a lot of it is just kind of like, it, it's, it's more like finding the right levels of abstraction that you could work with Devin on and, and just kind of like finding the workflows that work really well.

• 1:13:03Speaker 00

  And, and, and the obvious thing to say here is, is it's, it's a very, you know, it's, it's like you can always have Devin take a first pass at things, right? And so, you know, you, you can take the first pass, you, you have Devin take the first pass, you know, if it's great, you merge it right away. If it's, you know, if it needs some touch up, you can obviously give that feedback, for example. But, but, but a lot of it is, is like, it, it's more about basically like making Devin part of your flow than it is, you know, losing control, which I think is the, is the, is the main thing that, that folks are scared of with, with, with management.

• 1:13:34Lenny Rachitsky?

  Are you thinking about a manager Devin, like a Devin that manages other Devins?

• 1:13:37Speaker 00

  Yeah, yeah. So, so for what it's worth, Devin can start other Devins through the API, right? And so, so we, we've seen this happen quite a bit of times where naturally, if, if you have some big task that you want to do, like, you know, Devin will do this all the time, it'll, it'll chunk up and, and then I'm paralyzed into smaller Devins. And so, it's the kind of thing that you need to give Devin the credentials to be able to do that. It's not currently something that is kind of like default enabled, but, but I can certainly imagine as time goes on that there's more and more of that.

• 1:14:03Lenny Rachitsky?

  Devin's all the way down.

• 1:14:04Speaker 00

  Yeah, yeah. I, I think the thing that's kind of interesting too is like, you know, with humans, the way I almost say it in, in, in, in technical terms is like, there's this coupling of a context and a thread. And what I mean by that is, is like, basically, each human can only operate, you know, single threaded on, on the work that they do, and they have their set of contexts. And then there's other humans, obviously, who can do other stuff at the same time, but they have their own context, right? With agents, one of the cool things is you can have an agent that's doing multiple lines of exploration at once, but is sharing all of the context of everything that they find.

• 1:14:41Speaker 00

  And so I think that this is very early and I think we'll see this, but folks obviously love to talk about basically like systems and agents communicating with one another. And I think that there will be a lot of new paradigms to build for once we get there.

• 1:14:55Lenny Rachitsky?

  And it's so interesting what you said about the decision between having one Devon and only one Devon do all the things and you just tell them things and they kind of fire off jobs versus you have five Devins and they're each doing individual things. It's such an interesting decision to make.

• 1:15:09Speaker 00

  Yeah, yeah, yeah, for sure.

• 1:15:12Lenny Rachitsky?

  Okay, two more questions. What's maybe the most counterintuitive thing you've learned so far building Devon that maybe goes against startup wisdom, common startup wisdom?

• 1:15:21Speaker 00

  Something I've thought about a lot lately as we've built this is, you know, this is not my first company, actually for a lot of us, it's not our first company. Like I think of our 26 or 27 people total on the team, like I think 18 of us have started our own company before this. And yeah, like one of the things I think about is, you know, there's, actually your point about cliches, I think really spoke to me as well, which is there's kind of the really common things which you hear all the time in startups where she's like, you know, you gotta move fast or you gotta hire great people. It's like, okay, well, obviously you do, you know? I wasn't planning on not hiring great people, you know, I wasn't planning on going slow. And similarly, it's like, yeah, you really had to build something that people want, right?

• 1:16:04Speaker 00

  And there's kind of these like three to five things which are always repeated and they're always the common wisdom in startups. And I definitely had this idea as a founder when I was starting initially that, all right, so those are the kind of the three to five basic things, but as you get really deep into it, you spend a lot of years into it, you know, you learn all of the thousands of other things that you have to learn to be, you know, to build a company, right? And I think to some extent, that's of course true and there's lots of little details that you'll get into with all these different things, right? Including team building and product and strategy and engineering decision making and fundraising and sales and every other component, right?

• 1:16:44Speaker 00

  But I also realized that as time has gone on, more and more, I felt like building companies well, sometimes just comes down to doing those three to five things just. Even more than you could possibly expect. And so with us, it's like, you know, it's, everyone says to go fast, you know, but it's like, yeah, we had a hackathon in November, we had another hackathon in December, we started the company officially in January, we like got the prototypes out to initial users in February, we did a launch in March, we got our first customers in April, you know, it's just like, basically like truly pushing the pace in every spot where we possibly could, has really made a difference for us. And similarly, it's like, yeah, everyone always says, you know, you should hire great people,

• 1:17:24Speaker 00

  but I think that the truth, within that truth is basically like, you should fight to, to all ends, basically, you know, to, to, to get the folks that you really want to, to, to bring in. And it's, you know, one of my favorite stories to share is we had, we had a candidate who came and interviewed. He was a junior at MIT, so he was very, very young and we gave him our interview. He, he did way better than almost any of the full-time, like the, the, the full-time candidates that we had ever talked to. And so we said, hey, you know, what do you think about taking some time off of school and, and working with us and building out Devon? Like, we really think you're just going to be able to come in and just have a ton of impact already from day one. And he thought about it for a while, he came back, he said, you know, I, I, like, I, I'm down, I want to do it,

• 1:18:06Speaker 00

  but my parents really want me to graduate from school and I, I, I'm just not sure there's a way to make it work. And so, and, and, and so, so we talked to him more and kind of just understood the situation. And then, you know, and then we, we flew to North Carolina,

• 1:18:23Speaker 00

  went straight from the airport to, to his parents' house, had dinner with him and his parents. We talked a lot, you know, it's a really, really nice Gujarati family. Kind of gave them some gifts and just talked to them about it and tried to understand, right? It's like, what, what, what would it take and what, what will we need to make work? And they just said, you know, it's, it sounds like a great opportunity, but we really want our son to be able to graduate, right? And, and we talked that through and we figured out a, a, a setup where basically where he could work for us, essentially full-time, but then come in for his required classes and, and do what he needed to do to get the diploma, basically, but no more than that. And we talked that through and then, you know, we got to a point where, where, where, where everyone was happy with that and then, you know, went straight back to the airport and flew

• 1:19:06Speaker 00

  right back, basically. And that was, you know, that was, that was the first and only time that I've ever been in North Carolina. It was just a great trip, you know, and it's the kind of thing where it's like, you know, hiring great people is one thing, but truly just never, never giving up and, and, and really giving it everything that you can to, to make it work for, for people who, who really makes sense to be on the team. And, you know, he's been with us on the team for, for over a year now and he's been an incredible, incredible engineer and we wouldn't be here without him. And similarly, we had someone else who was, again, really, really talented candidate, you know, did amazingly well, very young and, and had a lot of great offers at a lot of other companies. And, you know, we were talking to them about, you know, he, he, he wanted to start his own company someday as well. And we were talking to him about, you know, certainly, you know, a lot of the obvious things, which are kind of like having him meet our investors or work with, you know,

• 1:19:52Speaker 00

  get to do work with customers or see a lot of these other components so that when the time came, you know, that, that he would have all the experience he needed to start his own company. But the other thing that, you know, that one of, one of the other things that was big is like, he really, you know, he, he, he was talking with a lot of great companies already. He didn't want to burn any bridges. And so we actually worked with them and, and basically hand wrote all of his rejection responses to each of the other companies and kind of worked with him on it to say like, you know, here's how you should say it in a way that's, you know, good, gonna come off as like, you know, that, that you really did appreciate the time with them and that you obviously, you know, you want to remain close with them and stay in touch. And, and it was the kind of thing, obviously, where it's, it's like, look, obviously, it's our, our job is to make sure that he's happy enough that, that he, he doesn't want to leave anytime in the near future. But I, I

• 1:20:36Speaker 00

  think it's the kind of thing where, you know, the, the way that you put together a really, really great team is by, is by really what's, what's, by, by fighting for, for what's right for them too. So.

• 1:20:45Lenny Rachitsky?

  Wow. Those are incredible stories. And it makes so real, these, you know, as you say, cliches, hire the best people. Like, this is what it sounds like to hire the best people. This is what it takes.

• 1:20:56Speaker 00

  Yeah, no, and I was just saying, it's, yeah, it's just like, you know, a lot of things, yeah, we've, we've, we've fought very hard to just kind of like, yeah, like reimagine things from the ground up because it's, you know, a lot of it really is just thinking about like, yeah, like where, where do we think the technology is going over the next five to 10 years? And, you know, what is that the place that we want to have in the future? So.

• 1:21:16Lenny Rachitsky?

  I wonder if people are going to be fighting for the best devins someday.

• 1:21:21Speaker 00

  I'll give you overtime pay benefits, you know, free healthcare and everything. And then the devins like,

• 1:21:28Lenny Rachitsky?

  straight devins like Magic the Gathering cards.

• 1:21:31Speaker 00

  Yeah.

• 1:21:31Lenny Rachitsky?

  And then just going back to your three to five things. So essentially, this is incredible advice. Essentially, it's like you always hear hire the best people, move fast, build things people want.

• 1:21:41Speaker 00

  Yeah, build something people want, you know, stay as close as possible to your customers, right? And then I think the other thing is just always think about where things are going, not where they are today. I feel like those are kind of like the five things, which is, you know, especially in AI with things moving so fast and there's so much great talent. You know, I feel like a lot of these are even more true where it's kind of like, you know, it's not just thinking about where things are going to be in 10 years. It's like thinking about what's going to happen next week, you know? And it's, it's obviously things are moving very quickly and it is very hard to predict. But you really have to, you really have to be very, very rigorous with yourself, I'd say about like, thinking through those things and evaluating all of the kind of the decisions that you make in that lens.

• 1:22:25Lenny Rachitsky?

  And staying focused is the big takeaway to me here is like, it ends up feeling like there's a thousand things you should do, but it's always these five things.

• 1:22:31Speaker 00

  Yeah.

• 1:22:33Lenny Rachitsky?

  Scott, we covered a lot of ground. We went through every question I had, which is great. Is there anything else that you want to share, anything else you want to leave your listeners with? Maybe a final nugget or something really you want to double down on that we said before we let you go.

• 1:22:49Speaker 00

  The biggest thing that comes to mind for me is, you know, there's, there's a lot of different perceptions about AI, right? There's, there's, I think every basically every emotion under the sun right now, you know, there's, there's a lot of fear, for example, there's also a lot of skepticism and you know, we're very skeptical types as well. And we always want to kind of try it ourselves to really see it and believe it. And I think the main thing that that comes to mind for me is, you know, I, I, I'm honestly really optimistic about what we're building here with AI and, you know, not just with code and with Devon, but, but, but. The whole space and everything that's getting done. And I think one of the cool things that is really actively happening is just the ability for everyone to multiply themselves. And that's how we've always thought about it. It's how we've thought about what we're building.

• 1:23:33Speaker 00

  And it's, you know, I think the there is a lot more to do out there in the world. You know, I'm not too worried about us running out of things to do. And from that lens, it's, it's, I think that the thing that we've always been most excited about is, is how can we all do more?

• 1:23:52Lenny Rachitsky?

  I hear you, Scott. Well, with that optimism, we've reached our very exciting lightning round. Are you ready?

• 1:23:58Speaker 00

  Yeah, let's do it.

• 1:23:59Lenny Rachitsky?

  Okay, here we go. First question, what are two or three books that you find yourself recommending most to other people?

• 1:24:07Speaker 00

  In terms of nonfiction, I think for folks in startups, I think one of the things that I've really enjoyed is just learning and understanding the history of Silicon Valley. And there's, you know, it's all these things that we think about. Somebody invented them. I mean, it's, it's one of the great realizations, I feel like, is like, you know, it's somebody invented the idea of a seed round, right? Somebody invented the idea of venture capital. Somebody invented the idea of like product market fit. You know, and all of these different principles that we talk about. And so for that, there's a book called The Power Law by Sebastian Malaby, which I really like. It basically is just kind of like, yeah, a tour of many of the great businesses and the great products that have been built over the last 60, 70 years in Silicon Valley, which I really love.

• 1:24:49Speaker 00

  I think in terms of fiction, it's a, I actually have always really liked The Great Gatsby by F. Scott Fitzgerald. It's one of my personal favorites as a fiction book.

• 1:24:57Lenny Rachitsky?

  Do you have a favorite recent movie or TV show that you've really enjoyed?

• 1:25:01Speaker 00

  I have to admit, I have not watched, I can't think of a single movie or TV show that I have watched in the last while. So I'm sure there's, I'm looking forward to watching a lot of great ones post AGI.

• 1:25:17Lenny Rachitsky?

  That's gotta be in the trailer. That's great. I like that. And that just shows how hard you're working, just how much it is going on and how fast everything's moving. Do you have a favorite product you've recently discovered that you really love? Could be an app, could be something physical, could be toothbrush.

• 1:25:32Speaker 00

  One I would say is, you know, I have, I got an Aura Frame recently. It's just like a, you know, a frame that shows photos and you can show a new photo every day or every hour or, you know, every 15 minutes or whatever you like. I've actually, I've, I've really enjoyed it a lot. I think it's a, it's a, it's a nice way to just have, basically to have picture frames that come up. And then the other thing I would say as, as like a general purpose thing, you know, I, I, it's, it's not particularly new, but I would say, I think AirPods are actually extremely well built and well designed. I realize now that it's like, I, I basically use them for all sorts, you know, I, I'm taking calls on a walk and I'm using AirPods. I'm, I'm obviously I'm like doing work at my computer at my desk and I'm plugged into AirPods and, and it's,

• 1:26:13Speaker 00

  it works quite well, I would say, for, for a lot of different situations and it's, it's, it's, they're, they're very comfortable. They're, they're very consistent.

• 1:26:21Lenny Rachitsky?

  I'm gonna double click on the, or double down on the Aura Frame. I also, I got one of these for my mom and my mother-in-law and they're so great for just like sharing photos of your kids with your family. And people have like, you know, they've heard of picture, like digital picture, picture frames, but the Aura just does it really well. And it's really easy to add photos and they're just really nice looking.

• 1:26:39Speaker 00

  You can imagine, you know, not that long from now, we'll have the Aura Frame accepted, you know, Studio ghibli flies every photo that you have in it and then, you know, it's a, yeah.

• 1:26:46Lenny Rachitsky?

  Or just imagines things you've done that are really cool. Sweet life. Yeah, cool. And it's Aura, it's A-U-R-A, I believe is how you spell it. Folks who want to check it out, we'll link to it. Not affiliated. Okay, two more questions. Do you have a favorite life motto that you often come back to and find useful in work or in life?

• 1:27:05Speaker 00

  Yeah, you know, something I've thought about a lot is,

• 1:27:09Speaker 00

  A lot of the, a lot of the proverbs out there are actually contradictions, right? It's like, you know, birds of a feather and then you also have like opposites attract, right? You have, you know, and it's kind of funny because it's, you, you feel that both of them are true and often they both are true and a lot of it is about like understanding why. And, and one of those that, that I feel like, especially in the world of startups that I think about like all the time is, I think it is very important to be focused and driven and to really kind of maximize your potential. And then at the same time, it's also very important to not let your own personal emotion get tied up in your success or failure. You know, and, and I think especially with startups, because there's always ups and downs.

• 1:27:54Speaker 00

  Honestly, even in the most successful companies ever, like it is, it is just like, you know, it's, it's a rocky road. There's, there's a lot that happens and a lot that, that goes down. And I think one of the things which I've, I, I've thought a lot about is that somehow it's, you know, you, you really want to do your best and put your, put, put everything you can into it and, and, do everything you can to, to, to, basically you, you want to put it all out on the field, you know? But at the same time, you want to be okay with, with, with both wins and losses, right? And you want to be able to, to, to, to, to, to move on and go into the next one with each time.

• 1:28:34Speaker 00

  And, and something, yeah, I, I mean, it's, it's funny, but what I've found personally is that, obviously it's, uh, you know, it's, it's really important for, for your, your own emotional state and mental state to be able to do that. And we've had lots of mistakes and you know, I've had a lot of, you know, I, I had my first company, which is obviously, which was cool. But, but you know, there were a lot of like tricky spots there and then over the course of cognition. I mean, it's been, feels like it's been already like eight years compressed into like one year. And you know, it's still going at that pace, but, but it's, it, it's somehow it also actually makes you. More successful, I think, too. You know, it's like you are just more able to to give it your best and and to do the things that will lead to success if you're not tying it up in your own personal worth.

• 1:29:18Lenny Rachitsky?

  So. That is so interesting. I just had a podcast recording recently where with an executive coach, Jerry Colonna, that I think will come out before this, might be after this, that he that's one of his big pieces of advice. And it's a it's a very Buddhist approach of just not a clinging and attaching to to an outcome.

• 1:29:35Speaker 00

  Yeah.

• 1:29:36Lenny Rachitsky?

  Okay, final question. I'm curious if there's a story here, but we could keep it short. Is there a story behind Devin as the name? And or or is there another contender for Devon being the agent?

• 1:29:47Speaker 00

  Devon was the name from pretty early on. We were interested, I have to say, you know, we were working on coding agents from the beginning and my co-founders are Steven and Walden, for example, and we had this idea, all right, let's get started. And, you know, let's not, let's try to kind of like, kind of like, expand the box as much as we can. So have everyone kind of think out of the box and do their own thing. And let's have everyone do their own thing first for a bit, and then we'll kind of like consolidate and take everything that we've learned. And so, you know, Walden made a virtual, you know, developer version of him, which was called Dev Walden. And then Steven made one of him, which is called Dev Steven. And, you know, we had all these. And then and then we were kind of combining it all into one thing. And we're like, okay, you know, it's Devon. And that was the thing. And so Devon was like, yeah, Devon stuck for us like quite early on, I would say.

• 1:30:30Speaker 00

  One thing which we did have a big decision on there actually is what the what the image of Devon would be. And so as folks know, there's the the hexagons. And then people might have seen this more recently, but there's actually also an otter, like a little otter with a laptop and in its lap.

• 1:30:47Speaker 00

  That that is that is Devon as well. And and we had this debate over over what to go with and what not to go with and stuff. And it was, it's, it's been a while now, but somehow we still we still have both the hexagons and the otter.

• 1:31:01Lenny Rachitsky?

  You skipped over where the Devon is like, did you just have just?

• 1:31:04Speaker 00

  Oh, so dabbling is it's it's a dev. Yeah. And so it's kind of like when we were consolidating all the names, it just kind of seemed clear then that this would be the universal dev that we all like to work with. Yeah.

• 1:31:18Lenny Rachitsky?

  Incredible. Scott, this was so much fun. Oh, my God. I learned a ton, which is always a really good sign. Two final questions. Where can folks find you slash Devin slash anything else you want to point them to? And how can listeners be useful to you?

• 1:31:29Speaker 00

  Awesome. Yeah, no, we're at we're at app.devin.ai. And, you know, you can you can find us as well on Twitter or a lot of other social media. We'd obviously love to hear any feedback you have about the Devon product. Like, there's there's so much to figure out. And I think the like, like I said, I think we're all still like 20 steps away from really the the future of software engineering. And so so it really means a lot to hear what folks think about the product as they're trying it out. And so please, please let us know anytime if there's things that we can do to make it better.

• 1:32:00Lenny Rachitsky?

  Scott, thank you so much for being here.

• 1:32:02Speaker 00

  Thank you so much for having me. I had a great time.

• 1:32:03Lenny Rachitsky?

  Me, too. Bye, everyone.

• 1:32:07Lenny Rachitsky?

  Thank you so much for listening. If you found this valuable, you can subscribe to the show on Apple Podcasts, Spotify, or your favorite podcast app. Also, please consider giving us a rating or leaving a review, as that really helps other listeners find the podcast. You can find all past episodes or learn more about the show at lennyspodcast.com. See you in the next episode.