Building OpenCode with Dax Raad

Dak Sarada is the co-founder of OpenCode, the most popular open-source coding harness. He's also very down-to-earth when it comes to AI, which can be a bit surprising when you consider that he built such a widely used AI tool. Today, we talk about the rapid growth of OpenCode to closer to 10 million active users in less than a year. The memo Dak sent to his team admitting they were shipping too many features, taking on too many hacks, and AI usage not helping them move faster. Why Inferent is one of the most profitable businesses in tech right now, and why even OpenCode is bottlenecked by GPU supply and many more. If you'd like to ignore the hype on social media around AI, and instead talk about where it helps or hinders productive engineering teams, this episode is for you. This episode is presented by Antasys. Verify your system's correctness without human review or traditional integration tests, and avoid bugs or outages. I'd also like to mention our season's sponsor, TurboBuffer. You've probably heard someone say RAG is dead these days, but it's not. It just doesn't mean what it meant in 2023. Back then, retrieval was pretty straightforward. The human asks a question, your code embeds it, you hit a vector database, top-k results come back, those get stuffed into context, and the LLM answers. Now look at what's actually happening inside something like OpenCode, or any serious agent product in 2026. A human sends one prompt to an orchestrator agent. That agent fans out to sub-agents. Each sub-agent is hitting separate systems, a vector index, a full-text index, grabbing the file system, running CLI commands and SQL against OLTP and OLAP stores, reading and writing a memory system, re-ranking results, looping, and calling more tools. One human prompt turns into dozens or even hundreds of searches across totally different shapes of data. In practice, this means a lot more complexity, a lot more cost, and a lot more potential performance issues, especially when you need to scale up the system. This is exactly what TurboBuffer is built for. It's a ridiculously scalable, fast, and cheap search engine. It's built on top of object storage for a reliable and scale, with smart caching on NVMe SSDs, so it's very fast. It's priced so you can let agents loose with proper ag in 2026 without seeing your bill explode. Check it out at TurboBuffer.com slash Pragmatic. This itself will not get us to better software. It's a weird feeling because a lot of the people who are decision makers, CEOs, often hands-on people, like hands-on CEOs, CTOs, founders of companies, they kind of think, Oh, look, we've got these tools. Coding used to be the hard part, right? Like, objectively, it took us so much time, and it still takes, you know, to get into the zone if you're going back to coding by hand. So if that's faster, because that's where we used to spend most of our time, it should be faster. Like, everything should be faster. But why do you think this is not the case? Or like, what is getting in the way of, like, just shipping high quality software faster or better, right? Yeah, I mean, there's different life cycles, different companies. There's like pre-product market fit. There's achieved product market fit, which is kind of where we are. And there's companies that are like, have had product market fit for like a decade. And I imagine that things look very different across these three. For us, pre-product market fit, to me, it doesn't really help that much because you're trying to figure out what you should be doing. And yeah, like maybe it helps you swing a lot. But I've always thought it's better to think a lot instead of swinging a lot. I think you can eliminate a lot of ideas or directions just by, you know, spending a lot of time in your head and with your team talking. Obviously, AI doesn't speed that part up. We're at the phase where we've achieved product market fit. Now our task is to kind of hit the potential that we have. And the issue for us is there's a million different directions we can go in. There's all the obvious stuff we can do. There's all the stuff that our users are telling us that we have to do. There's stuff that our competitors are doing. And it's very easy to just one-to-one do each one of those things because we have a problem, prompt the agent. Competitor has a feature, prompt the agent. If you add that up, you think, oh, we shipped a thousand features now that adds it to a good product. It actually adds it to a horrible product. Like a Frankenstein. Yeah. Nothing's cohesive. You look in there. You're like, we shouldn't have shipped this. The moment you ship something, you're suck supporting it forever. And by supporting, it means any future feature you build is going to like interact with it. So you still have to be very conservative with what you put out there. It's hard to undo anything just because we can ship 10 times more doesn't mean we have 10 times as many good ideas to ship out there. So in a lot of ways, my struggle has now been, how do I like slow everyone down? And like understanding that, yes, our process can look very different, but should it look very different? Like we know we've done in the past six months, we've kind of operated very differently than we ever have. A lot of stuff went wrong because of that. So now we're pulling back and figuring out what from the old world still makes sense. Yeah, we're like figuring out what we should be doing. And I definitely don't feel like, oh, yeah, we're like killing all our competitors who are using AI so much better than everyone else. And by the way, none of our competitors are crushing us either. Like no one out there is using AI so well that they just like we can't even compete. Right. And we're in the coding space. Our competitors are super into AI. So you would think in our space there would be like a huge gap, but there just isn't. So I want to rewind back to the very beginning of how, you know, before AI, before a lot of these things, how did you get into tech and software engineering? Yeah. So I grew up, kind of cliche story, I grew up programming as a kid. My dad was a software engineer, so a little bit easier for me to get into than for other people. Then just started working out of high school, founded a company, thought it was cool, thought I knew what I was doing. Looking back in hindsight, like, wow, I didn't know what I was doing at all. But eventually got acquihired as a small acquirer and ended up in like the real tech industry. Bounced around as a consultant, founded a few companies, and then ended up doing open source pretty much the past six years full time. But going back to the very beginning, I found or saw some references to you working on Minecraft, Minecraft servers. Yeah, yeah. Back in the beginning. Can you take us back a little bit? Yeah. So, so Minecraft, obviously everyone knows what Minecraft is. And again, this is another cliche story. You talk to a bunch of people in tech, they have a similar backstory. There was a modding framework for Minecraft that came out. I ended up working on the framework itself. I ended up making a bunch of mods with it. I found that I liked creating like interesting sandboxes. I never like, I played the game a little bit, but I didn't play the game that much. I like had a server that like 100 people would play on, and I would just use these mods to create like interesting situations to try to like, understand like how people would behave under certain scenarios. I found that like fascinating. But yeah, that required a lot of like programming Java stuff. What's interesting is that community, obviously I was like very new to programming. It was all done over IRC, a community existed on IRC. But there was some like very senior, very good programmers in there. The people there, I felt like were people that weren't particularly career motivated. They were probably in a comfortable enough situation where they worked like two hours a day. And they were talented, but they just didn't have any like desire to like career chase at all. So they funneled it into the Minecraft stuff, and I got to talk to them and learn from them. So I feel like in like the couple months that I was doing that, I learned a lot. And then you went to the startups, you founded a startup. And then after being the founder at Iron Bay, I saw, looking back at your history, you became a head of engineering at Wright Health. Can you tell me a little bit about what was up like that was in 2017 or so, like pre-COVID? Yeah. So that was a company, the transportation, the healthcare space, it was just me and the co-founder originally. And that company grew to like 20 people or so. That was my second swing at doing a startup, I would say. And it got further than my previous attempts. But like it kind of ended up in a disaster. I did end up meeting my wife there. She was head of product, I was head of engineering. We got together after a year. So better than a startup exit, I would say. I learned a lot. But yeah, it was one of the situations where everyone was super young in their 20s. I think there's this stereotype of startups that, oh, yeah, it's a bunch of like super young people, you know, building stuff. After that experience, if I ever end up investing in companies, I'm not going to invest in companies that with a bunch of young people, because we were all just like, our brains weren't fully developed. We're all insecure about various things still. And I played out with like company politics and dramatics and stuff. So yeah, that cliche of like, oh, yeah, it's a bunch of young people. I think that's like the exception, I would say, looking back. So like a bunch of young people succeeding is probably the exception. Yeah, yeah. And of course, we have like famous stories of that. But you know, like on average, like for me, I felt like my brain didn't finish developing until I was like 26. I think. So prior to that, you know, I don't know if I really should have been running a startup. And when you say like, stop developing, is it just kind of like getting enough experience to like understand how like a business actually works or like professional relationship? In what sense? Yeah, I think for me, it's like startups are so intimate, because it's just you and a few people. It's very intense. Like you are this is the thing you're doing. Like, you're not really this is your hobby. It's your job. It's kind of everything. If you're not like, fully developed as a person, like if you're trying to prove something to the world, if you're still insecure about certain things, all that shows up at work, especially in such an intimate situation like that. So fighting, conflict, all that stuff, the way I perceived the situation, even my own understanding of what was going on. So it's very easy to look at anything exciting that's happening and think, none of that makes sense. I'm not going to participate in it. But usually what happens is, a few things in there make a lot of sense. And if you just completely sit out, you just miss out on that. I think we've been through a few waves of kind of doing that, where we saw the AI thing and we're like, okay, a lot of this stuff is stupid, but there's definitely a real value here. We need to be doing something in it. And we took a few swings at a few ideas and like a lot of them we didn't even fully launch because we just discovered they didn't make sense while we were working on it. And then eventually we started to use Claude code as a team. It was the first AI coding tool that stuck for us. It like directly solved some of the workflow annoyances that we had. And we were like, this is great. Obviously, this should exist. At some point I asked, why weren't we the ones that built this? Like, we should feel bad about that. And then we realized, okay, maybe there is still an opportunity to do something. Given our experience in open source, we kind of saw, I think it was what I was saying earlier, like, you don't have to just ship a million products to figure out something that works. If you sit and think, you can figure something out. And we kind of looked at it from a positioning point of view. Like there's a market, there's a bunch of coding agents out there. For some reason, no one has grabbed the open source territory. There was no coding agent that was like, we are the open source option. And that obviously is a super valuable territory. Every single dev tool we use, whether it's databases, compilers, whatever, eventually the open source option becomes the default option, right? That combined with the fact there's heavy, heavy competition for models, like, sure, Claude was popular, but there's billions and billions and billions of dollars invested. Like, they're not just going to let Anthropic win. There's gonna be push from OpenAI. There's going to be push from the open source side. So given that we saw that chaos, we saw that was really valuable to have the open source positioning that tries to work with all the models. So the initial push for us was to kind of ignore whatever was going on in the market and just make sure that we claim that open source spot, which we were able to do. And then, yeah, like our numbers have been pretty crazy since then. Can you tell me about the growth? Like you launched in June 2025, how the growth was both for usage, but also for the team. Like when you started, how big was even the team? Was it most of the, the existing sort of animality labs working on this or just a small? Yeah, no. So we were just three people at the time. So it was just the three co-founders. Yeah. And then we hired one of my friends who was also interested in working as a, and he helped us build like the initial thing, but he joined, uh, so it was four. And then we convinced one of our, uh, a really good designer that we had always want to work with to join us as well. Uh, but that was after we launched. So that was more like in the fall. But yeah, so we, we launched and the growth was really good, like immediately. It was better than anything that we'd ever done. But by December, we hit uh 650,000 monthly active. And at that point we were like, wow, this is great. We, uh, back in the fall, we kind of, we're kind of telling people our goal was to hit 1 million by uh next, early next year. Everyone thought we were crazy. Like that was like, they're like, oh, okay, sure. Then in January, we did 2.5 million monthly active. Uh, so like went from 650 to 2.5. Uh, last month we're at 6.5. I think this month we're still halfway into the month, so I'm not sure. Maybe close to eight. Our next goal milestone was 10. There was a massive jump. So you went to 650 in December and 2.5 in January. What was that jump? Is that the winter break jump where everyone started to realize that these models are really great? Yeah. So having been in dev tools for a while, we knew that in January is always a bump because like, I think people take time to learn new things in December with the time off and they have time to try new stuff. So we, what we typically see is we see a dip into the holidays and like a giant spike in the first week back for this. We saw growth into the holidays, which we've never seen with any other product before. So like, despite the fact that people were off, it was higher usage than ever. And then January came around and Anthropic helped us helped us a lot by uh, you know, they, they like wanted to ban Anthropic subscriptions in open code. Uh, that blew up into like a huge thing. We barely even commented on that, but like just the user base was so upset. Anthropic accidentally put us and them in like the same sentence, which we don't deserve because they're a much bigger, more successful company. But that week that kind of happened by accident and that like spiked our numbers like crazy. So, so I guess in hindsight, because what happened is Anthropic silently banned being able to use cloud code subscriptions inside of open code, which, which was every tool, including open code did that because it was a bunch of other third parties, but they didn't allow open code to do this. And then this led to this, like, outrage. The thing with them is saying that they're kind of new to working with developers. Um, it's okay to do things like, of course, you need to do what you need to do to make your business sustainable. It's totally fine. But randomly dropping a block at, at like 9 p.m. at night. That just sets you up for like people to hate you. Uh, doing like a phase communicator rollout over a month. I think they would have, Giving a heads up. Yeah, yeah, yeah. I think people would have still been upset, of course. Everyone's going to be upset no matter what, but it wouldn't have been this concentrated moment of like everyone being, being really uh really annoyed. This reminds me what we were talking about how AI allows you to do things really quickly and fast. Do you think in this case, Anthropic might be, you know, stepping in this trap of, of they can do things really fast and they do things really fast. But for example, in this case, they can just implement a block like this, you know, like it, it, the PR probably took like what, like a few seconds or a few minutes. Whoever did that might have not thought through the implications. I think it's just a consequence of any kind of fast growing company. Uh, you forget the amount of leverage you now suddenly have. Like you do one small action and it ripples through millions of people. Like we're doing with this ourselves. Like we've never worked at this scale before. We put out a bug the other day where um almost everyone has a terminal in dark mode and we open open code, it opened up in light mode. So we like flash banged a bunch of people. And I'm like, in the past, that would have been like a hundred people we hit, but like I did this like a million people this week. So uh. Yeah. But, but in, inside this block, obviously we know it worked out well in hindsight, but when it happened, I mean, at the time Opus 4.5 or 4.6 was the most powerful model out there. Best for coding. And you saw that Anthropic just blocked, you know, like cloud code subscriptions before you knew that this press would happen. Like, was it seen's reaction? Was it just like, stay calm, keep going? Yeah, what's weird is we knew this day would happen at some point. And for some reason when it happened, we all just felt excited because I think we were kind of like thinking about this for a while and we knew this would happen. We also knew that like, we live in this crazy bubble, like especially on Twitter, where everyone has a $200 cloud max subscription. At that point, we were at 650,000 uh monthly active. There's no way 650,000 of them have cloud max subscriptions. Like, it's crazy for the average person to spend $200 a month on anything. So we knew it was like a smaller subset. Um. And also at the time we had been working on deals with pretty much every other company to officially support this uh their subscription in open code. So the previous weeks leading up to that, we got Microsoft to agree for uh GitHub Copilot to be officially blessed by open code. We got a bunch of different companies in the works. We hadn't announced any of them yet. And the big one we hadn't gotten or we haven't even approached was OpenAI. So when this happened that night, I forget what it was. It was Thursday night. I don't remember exactly when I got like a hundred tags on, on X being like, Oh, they, they banned it. They banned it. And I was like, all right, it's go time. So I messaged OpenAI being like, Hey, tomorrow, uh, everyone's gonna wake up and everyone's gonna be really angry at Anthropic. You guys have a chance to score like a PR win by taking the opposite stance and officially supporting OpenCode. The next morning they All that became really popular. That business is growing a ton. I think a couple of months ago, we announced that that hit 50 million run rate within like five or six months. Wow. And the margins there can be pretty good because the open source models, you can host at a decent margin. That is growing like crazy. We didn't really expect that, but that's a big part of it. The other side of it is extremely boring. If you are a company that's using OpenCode and you have a thousand engineers, you can't just tell them all to go download OpenCode and like add an OpenAI API key. You need some kind of control plane to like set up all the providers, permissions, budget controls, rate limits. So we have a product there. We're going to make that publicly available soon, but right now it's just been like enterprise deployed. So just, if you're a company that's using OpenCode at scale, you need some administrative software to to run it. You can't practically use OpenCode at scale without something like that. That's also open source, but you know, most people just pay for our hosted version. The other thing is, I think it's finally, the time has finally come where people are looking at how much they're spending on LM and they're like, what are we doing? Are we actually getting anything any more done? Like we, so like companies are now looking at their costs and trying to figure out how to optimize it a little, little bit. It's great timing because open source models are now very competitive. Uh, they are 10x cheaper. Blending that in and having good inference for open source models is becoming a part of our business as well. So these big companies, you know, they need the control plane, but then we kind of just give them inference access as well to the, these other models and they end up just kind of naturally starting to use it. If that ends up being a main part of our business, we might stop charging for the control plane itself and just charge for the inference. Dax was just talking about the boring but essential work to get enterprises on boarded. SSO permissions, control planes, all the stuff every serious company eventually needs, which is where I need to mention our season sponsor, WorkOS. Sooner rather than later, you'll need to get around building these enterprise features, not just control planes, but things like auth for apps and agents. WorkOS handles it. SSO, SCIM, fine-grained authorization, built for how agents actually operate. The fastest growing AI companies, Entropic, OpenAI, Cursor, Perplexity, they already trust WorkOS to solve these problems. Check it out at workos.com. I'd also like to talk about our presenting sponsor, Antithesis. We just talked about slowing down to speed up, thinking hard about what to build, so you're not sprinting to the wrong destination. But quality is part of the destination too. You don't want your product to flashbang a million people like this team at OpenCode did that one time. Antithesis is a property-based testing platform that enables you to express the properties your system should have, then verify that those properties will hold in the chaos of production. With Antithesis, specification and thorough verification becomes a seamless workflow, giving you clarity so you can deliver quality. Check out antithesis.com slash pragmatic to learn more. And with this, let's get back to Dax and OpenCode. We had a recent tweet about how inference is actually really, really profitable. Like you were quoting someone who was saying like, oh, you know, like these AI model providers are, you know, like having, might be having financial difficulties. Can you explain to those of us software engineers who, you know, we don't, we don't do inference. I mean, we use these models and we just assume that this, this must be our business. How can it be profitable? Why is it profitable? What are you seeing? Yeah, so I think this is a, it's kind of the different parts of the business. So if you look at the pure inference part of the business, if you think about what's the floor on the cost, the floor is a cost of electricity. There's a capital cost to acquire the hardware. Once you have it to deliver a token, the cheapest it can get is the electricity to power it. And obviously there's like other infrastructure. There's like operations staff. There's stuff like that. But we have seen models that we look at the sticker price of it. And we know like the, because we rent GPUs at scale to run the models and we still use middlemen, by the way. So we're not like going all the way down to the, down to the floor. Even for us, there are some models, the sticker price and the cost to us is like an 80% margin in there. And I think the other thing that people don't notice is the prices have gone up. It's confusing because it seems like they haven't, but they've gone up from the point of view is we used to all use Sonnet as our default because Opus was too expensive. Then they've made Opus cheaper so that we started to use Opus as our default, but it was still way more expensive than Sonnet. So the prices have gone up and the cost to host these models haven't changed. So that's one aspect of it being really profitable. And Anthropic, of course, they have an open AI crazy scale. They have the biggest GPU deals that they've done. So I wouldn't be surprised if they're looking at like 90% margin at current prices. I don't think that's like a defensible margin long-term. That's crazy to be able to make that much with the amount of money going through as well. It's interesting because when Brian Cantrell was on the podcast, he used to work at building a cloud service that would compete with AWS. And he said that back then, this was the same thing. AWS back then hid their financials. Everyone thought, and they told everyone that cloud is a terrible business and it's like your red blood everywhere. And then he started to do it. And he said, actually, it's a really frigging profitable business to run a cloud, but it's kind of a well-kept secret because why would Amazon or any other provider advertise the business that is printing money? There's always negative sentiment that exists for any business that's getting hyped. They have no incentive to correct it. So again, it's complicated because I know the training costs are a big part of it. The R&D department is hugely expensive, but long-term inference makes sense as a business. I think it always will. This being said, you also said something in public about GPUs, about you, I'm quoting you, there are just enough GPUs. It's crazy that even a company our size is being bottlenecked by this. What does that mean? Yeah, so across the whole stack of GPUs, so everything from like producing the GPUs to supporting hardware to like labor, everything, everything is like super tight right now. The demand for inference is growing. So like, I don't think it's linearly growing. I think it might even be exponentially growing, but we haven't made our production of GPUs grow exponentially. That's like kind of a linear process. So as those lines intersect, there's going to be a tightening. So for us, like there's, we have GPUs that we need to reserve. We have to pay a lot upfront. Everyone is now hoarding because everyone's kind of expecting this crunch to kind of continue. It's very hard to get capacity for inference. And the other thing that's crazy, I think I posted about this. You know, we see things like, oh, a company has raised $2 billion or whatever to do something in AI. And that feels like a crazy amount. Like, wow, that's a huge amount. Like you have to be like a crazy startup to do that. The big tech companies are spending like tens of billions in a year. Like Amazon, Meta, whatever. Like they dwarf anything that's happening in the startup space. So they are just vacuuming up like all the demand. Any company that is in the supply chain, they don't want to talk to you because they're busy trying to get something with Amazon or Microsoft or Google. So yeah, it's very tight times. I think it'll get resolved. I think any, in my whole career, anytime I've seen any kind of shortage, there was a tense period and it was met with like crazy oversupply. It might be different this time, but generally that's how, how I see things go. But right now it's tight. I want to talk about the, the hype of what productivity gains these AI tools, especially AI agents are giving to engineering teams and the reality. And you wrote a now very heavily quoted tweet, which, which was, I'll quote just some parts of it. Everyone is talking about their teams. Like they were at peak of efficiency and bottle neck by the ability to produce code. But the way things actually look like is, and you listed a few things like your team, your org really has good ideas. People are not using AI to be 10X more productive. They're using to churn out their tasks with less energy to spend and so on. So like this was a few months ago, I think two or three months ago when you wrote it. Yeah. I think that there's so many dimensions to this. So the thing I was talking about in that post is the majority, again, we forget how big this offer engineering industry is. Like every company in the world employs software engineers to some degree, right? Um, the majority of these environments, aren't like the most motivating, exciting environments. Most people there are trying to do their job, go home to their kids, like have a, have a uh, a reasonable life. You give them a button that lets them do their work faster. The natural place for them to do is hit that button as much as possible to it. The system doesn't exactly support the feature, so your options are rethink the system from first principles, redesign it, so it supports that feature, or just absorb the hack temporarily. And you can make a judgment call on which one you do, depending on how bad the hack is, depending on how valuable it is to the company it is to get this feature out. You make the judgment call. That judgment, that ability to have that judgment is so distorted right now because the agent will just do the hacky thing for you. The agent will kind of deal with the hacky problems that come down the road. And it's way easier to be like, oh yeah, it's a temporary fix. So we're shipping way more hacks in places where we should have just rethought the whole system from ground up or like redesigned it and like refactored it to make it more flexible. So I think our judgment is just off. Does this have to do with that when I, as an engineer, you know, pre-AI, like I'm making a hack. I know I'm making a hack. I'm thinking about it. I feel bad about it. I feel bad. But I do it anyway. But you know, I spend time thinking about it and there's kind of like a little bit of a prickle there. And then when I do a second hack, I remember the first one and I feel even worse about it. And I can still justify it, right? But after a while, there's feelings that, especially when you're someone who cares about, and the reason you care is you have an experience, you've been burned. You know, you're, you're, you're placing landmines for someone else, maybe even for yourself. And is it just that the agents, A, I mean, they just do it. They don't have feelings. And they also suppress the effort, suppress the thinking. They don't even tell you I'm doing a hack. It doesn't even know it's doing a hack. It's just following whatever the training data is, which is pretty low quality code on the internet, right? Yeah, exactly. I think the way you put it is exactly right. That prickle, that feeling that you get, it's like muted now because someone else, it's kind of like you've made someone else deal with the problem. The problem is still there and the landmines are still going to blow up on you eventually. But like, you're not, you don't feel that bad feeling as much anymore. So your judgment is skewed. You're not getting that feedback loop. I guess this is like, you know, like there's always this like very relatable story of the CEO who just delegates stuff and then like doesn't understand why things are terrible on the floor. And then like one day goes down and like gets into like doing the actual work and realizes, oh my gosh, these conditions are terrible. Yeah, exactly. Versus the CEOs who are hands-on and they try to stay in touch and do, I don't know, simple stuff like, or CTOs doing coding in the environment. Like I think Stripe CTO did this like once for a week every few months and then felt like, oh, this is painful. Let me do that. Yeah, exactly. Like you need to, I mean, just like you need to be using your own product, you need to be also like, you need to feel the pain that the users are feeling. Same thing with your code base, same thing everywhere. So yeah, I think all of life is about having the proper feedback loops in place. And it's very easy for those to go away. And then the third thing that you said in this memo was related to this one is we need to spend more time cleaning things up. How do you deal with that? And I mean, because you're also a founder, how do you justify it? Because, you know, there's this thing of like, especially when you're a startup. Okay, you've just found product market fit, but there is this pressure to move, move quickly and cleaning things up. It will not get you more customer love or revenue or any of the stuff that you care about as a business. Yeah, it's really hard because every single day we wake up, there is a thousand people yelling at us, telling us to do X, Y, Z things. There's a thousand people telling us we're doing everything wrong. Every single day there is like a competitive new product that shows up, uh, very overstimulating. If we let ourselves just get pulled by those forces, I don't think it results in anything good. And I think what's also cool is cleaning stuff up is easier than ever. Like you think of a new way in the past, I would realize, Oh, there's like a new pattern that we should be using. And we would just start to use that stuff for stuff going forward, but it was too much work to clean up all the old stuff. But now you can clean up all the old stuff. It's like, you can ask the agent to go implement a new pattern everywhere. It's very easy to clean up tech debt. It's very easy to like find new patterns and implement them across the code base. Very easy to clean up like dead old patterns. And yeah, you're right that there's no like direct uh result of doing that. I think you can be a successful company without ever doing that. The way I think about it is there's a million ways to be a successful company. There's all these different companies that are successful out there. If you had your pick of any company you could work for, you probably wouldn't pick 99% of them. So I want to make sure we build a place that we're happy to work at five years from now. Our day-to-day is happy. We feel good. We feel good working there every single day. It's not this thing where it becomes miserable to work there. We can't get anyone good to join us because it's mostly about slogging through like legacy stuff. And in this memo after you listed all of these things and you know, you were basically saying, right, we're shipping a bunch of stuff that we, we don't need. We're not cleaning it up. We're not thinking. You actually said something really interesting. The I'm quoting you again, the worst part about all of this is I don't think we're trading this off to move faster. I think we're moving at a normal pace. Right. Yeah. It feels like we're going fast, but then I look back and I'm like, like, I don't know if we actually are going that fast and I don't think we're going any slower than our competitors, but we're certainly not going any faster than them. So if you're trying to look at productivity, it's so easy to trick yourself into thinking you're being more productive. And when you sit down and really look at it, oftentimes like, it's not as crazy as you, you expect. I guess what you're saying is, you know, don't be complacent and accept, but like, just be critical and look at, is this working? Like, should we, should we slow down to speed up? Should we focus on the invisible stuff, those kinds of things. I really believe in just like preparing a lot and like setting the foundations right. And then then when you spring, you spring with like so much more force than you would if you just forced it earlier on. One thing I like about you is you, you do call out BS when it's a BS, especially when it's really trending on social media. Again, you're, you're a lot on X. This happens a lot specifically. And here's a tweet that I'll, I'll read to you that you, you'll remember. It went very viral. So many people as you know, VC folks that all said like, yeah, this is the future. And this is what it said. The 24 to 29 year old engineer will soon become the most valuable asset in technology because they have pre-AI principles and post-AI speed. And it's an undefeated combo. And people are saying like, yeah, this is the future. Like this generation who is not too old to have the old things, they, they will be killing it again. They have no preconceptions of what used to be possible. And you did call BS on it. Can you, can you talk, tell me like what you're thinking? Well, it's, it's funny cause like, I'm just so tired every single day. I wake up and I open the feed and just prediction after prediction, the future is going to be like this. The future is going to be like that. The future is going to be that. And we're just like making stuff up, right? That one's funny because that, that's a very classic post where it's like, person like me has all the advantages. Person like, not like me has all of this advantages. It's like, everyone is just saying mantras to themselves because the root thing that's going on here is we are experiencing a moment of great change. Everyone is very nervous about what that means for their own position in it. A defense mechanism is to confidently assert a future in which you're a winner. And that's almost what every single prediction that you see is happening. You almost always face it down to companies like mine will be successful. Other companies will fail. My job won't be replaced by AI, but everyone else's job will be replaced by AI. And everyone has some like rationalizations for this. But the root thing that's happening here is everyone is scared and worried and not sure about where things are going. And we are just bombarded with predictions and protecting their own psyche. Yeah. I'm just tired of predictions. Like, yes, we're going to have time of great change. I just focus on like the next day. Like, what can we do today? What can we do tomorrow? I didn't know I was gonna be working on this a year ago. I don't know what I'm gonna be working on a year from now. I'm just trying to do the thing that makes Yeah, but good ideas are simple, very, very difficult to actually live. So it's very difficult to actually have good taste. And it's like a lifelong, yeah, one, it can be learned. It's like a lifelong thing that you're going to work on forever. I think the root issue is, a lot of people will say that the whole taste thing, but do you actually believe it? Like, do you actually believe that your product has to be good? There's so much, like, there's so much out there now, that's like, the code doesn't have to be good. The product doesn't have to be good. Like nothing has to be good. It's just this other thing. You can still be successful. And they point to companies that have crappy products that have crappy engineering, but still make a lot of money, right? So there's like a thing in the air about maybe all that stuff doesn't matter. The moment that gets in your head, you, like, nothing, like you're not going to have, you're not, you're just not going to ship good products. Fundamentally, you don't believe in it. And I feel like the number of people that like vocally believe that craft is really important, making an irrationally good product is still something that you're going to do because most great products, they could probably be like 50% less good and have no material impact on it. But it shows up in other ways that are really hard to directly draw the line. It's if you start to be lazy in one place, you start to become lazy everywhere. It's like an infection. So my thing with the whole taste thing is like, yeah, you're saying taste matters, but do you really believe it? It's like a very, very high bar to be someone that says, I really care about good products. For me personally, I care a lot about it and I am nowhere near achieving my own bar. Like I'm like so missing my own bar and what I think, what I believe. So when you, when you hear me talk about quality and stuff and using my products, you're like, oh, it doesn't, like he's like kind of ahead of what he's saying. That's because like, I'm like still trying to get better at it, you know? So I look at products that are really good. I'm still very inspired by them. I still have like heroes that I think just kind of do a great job at certain things. And I know I have a long way to go to get there. Can we talk about the, these heroes, the, the products and the engineering teams that you look up to and why? Yeah, yeah. So I think in my space and dev tools, I think Mitchell Hashimoto is like an obvious one. Our company is very similar or trying to be similar to theirs in that all their products are open source. They became mass adopted. Things like Terraform became the default, you know, it's very hard to do something like that. And it's well executed across the board in the microscopic, in the macro, the business model, uh, you know, his work with ghosty has been really great. The architecture of it cares about every little detail and it shows up, uh, when you use the product. So, um, and he's very good at product. And I think he, he has a, he made a clip that's a very similar thing. We were just talking about where every feature you ship, it's not about the features of how it interacts with every existing feature. And his work as a product person is to make sense of all that. Um, and he's very good at doing that. I think he's probably one of the best for being also a good programmer. So I think he's someone that I admire a lot and I hope that we can kind of be as good as that one day. I sense as we're talking about taste, we started to talk a lot about quality. Could it be that quality is one of the last few things that these days, a startup, a small company going up against Goliaths has left to, to hang on to? Yeah, yeah. And I think the, the flip side of it is, uh, it's easier than ever to rot your product. I think it's, uh, with these agents and everything. So you see with big companies, big companies products are rotting faster than ever. Even startups products. I was saying this the other day, like now the product is a year old. It's probably already kind of going to shit. And I think it's because of, of like all these agent workflows. So yeah, I still believe quality is a huge differentiator. It's not just something you can decide to do. I think it needs to show up every single aspect of your company from like, you have to do things that are irrational. I think that's kind of what quality comes from. Like you do a bunch of things and like 50% of the things you didn't have to do. And I think very few people are willing to operate that way. There's like a cold logic these days to programming and to software and to products. It's like, I'm like a business guy and I care about business, which means I only do things that are hyper, hyper rational. And a lot of people think that's what being good at business looks like. Um, and of course that can work, but. Yeah, I think quality is like a huge differentiator. Um, I mean, even if you look at our story, when we first launched open code, uh, cloud code was the only other real thing we were going up against. A big initial differentiator was that our terminal experience just felt better. We spent a lot more time on, like we built our own terminal framework. Like building your own framework is like the first thing to tell you not to do. Right. It's like the thing that no engineering team should do. It's irrational. Yeah, exactly. It's irrational. But like it did, we looked at it and we're like, we couldn't achieve the experience we wanted. Like we were people that use terminal tools. We look at tools like NeoVim and enjoy them and know what is possible. Like, uh, I mean, again, going back to Mitchell, like he worked on making terminal stuff as good as possible. Like he knows what's possible with it. Once we know what's possible, how are we going to ship something that's like not pushing those capabilities to the max, right? Uh, and very initially, a lot of the reason people were, uh, using us when people were talking about us compared to cloud code was how janky cloud code was or how much it flickered or how much it did whatever. And it didn't matter. Like there's a hugely successful product, but we irrationally focused on some of the quality stuff that helped us go up against a much larger product company with much more funding. What's your work set up? My work set up. I've now switched to a framework desktop. Uh, nice. The, the one where you can replace. Yeah. Yeah. The, the, the little like tabs in the front and stuff. Yeah. So, uh, that, uh, running arch Linux on a not ultra, I guess it's a 5k display. It's more than 5k display. Uh, I use Italian window manager, which I've been using for 10 years and that's roughly it. Yeah. Got my SM7B as well, the mic and I use my iPhone as my camera. That's about it. Yeah. And then you use mostly terminals, of course, open code terminal, right? Yeah. So I use a, oh, I guess my sub is actually a little bit more complicated. So that is my physical machine, but I do all my uh work on a remote machine. So I SSH to a much bigger, beefier computer, uh, that has many team sessions going one for each project. NeoVim is my editor and then open code. It's usually split half. So like NeoVim on the left, open code on the right. Um, I'm going between the two. So yeah, Tmux, Arch, uh, NeoVim, open code. I wanted to ask you how you think engineering leadership has changed with AI because you've, you've been an engineer, founding engineer. Then you, you've led teams before you're technically leading a team now as well. And, and also like when, when you talk with other, you know, you're now talking with a lot more like CTOs and, and like-minded folks. What's different is, are people being more, more hands-on? Uh, is this, is that even a good thing? Yeah, I think, uh, I'll tell you something that I've heard. And I think on one hand, this makes sense. And on the other hand, I'm not too sure about it. I think these teams are now looking at themselves as, okay, what's the role of an engineer now? If, if you're not going to write the code. What do you do? Your role maybe is to figure out how to make it easy to ship code that is to safely ship code, right? Um, set up guardrails so that don't prompt the agent to do something. It's not introducing a bug. Like make sure, make sure your testing story is good. Make sure there's like proper conventions and patterns in your code base that agents can follow. So they're not like adding something that's really crazy. So your, your role ends up being more like, how do I set up the right guardrails to make it so someone that is using an agent can kind of blindly ship something that, that works well. Whether it's another engineer, it could be your marketing team that is uh trying to ship a change to your website. How do you make it safer to, to make changes? And this is like the novel way that everyone is kind of looking at engineering teams. The thing that I find interesting is that that's not novel. This has