AI Coding Agents

“I think a lot of companies have skewed in that direction where they've seen this new, you know, agentic efficiency and power as a way to optimize cost structure. You've saw some layoffs, you saw, you know, companies shrinking OpEx. And our belief is that it's …”

“Even now with coding, like, the agents are not yet they're not human level at being coherent over long periods of time. That's obvious because they can't code like a junior engineer on a project for two weeks. So they can't, they're, that's worse than a human …”

“The ontology of your code base, it always mattered for engineers. It matters just as much, if not more, for really good agents over time.”

“The importance of specifying what you, what it is you want has actually gone up, because before you'd be handing it off to a very intelligent human who maybe has context or can ask you follow-up questions and agents can sometimes do that, but I think clear spe…”

“I actually still think, understand, like, it's always double clicking on that layer that you depend on. Like maybe that to me is a matter, like it's always take that time to learn about your dependencies. Cause this way, when your dependencies change, like you…”

“AI coding agents that we know have totally, you know, reached escape velocity.”

“What we saw from our customers was that they were all trying to figure out how to do versioning. Everyone is doing it in different ways. There were some really weird ways where people were doing that. And the reason was that GitHub as is Was an overhead. Like …”

“And so like the branching and forking stuff, like it's not different. Like we're just moving a thousand times quicker than we used to. And so some of these things like look like you really need like something massively, massively different, but it's just, you …”

“And I think things that are hard and new is still something that the models need humans. Yeah. Drive. Yeah. But I think those other quadrants are largely solved, given the right scaffold and the right thing that's going to drive the agent to completion.”

“And to some extent, I think that market has been so demand constrained for great software engineers that suddenly adding supply can 10 X that market, right? In other words, I think the market for software engineering and coding is dramatically bigger than anyb…”

“The art of having them help you build software, you could deploy to a million people. That's not, that's never going to be easy. That's never going to be trivial. That's always going to require a great deal of depth of experience in what software and how softw…”

“The problem is the people in the middle. Like if you're mid career, if you haven't made it to sort of super senior engineer yet, but you're not sort of new either. That's the group, which ThoughtWorks resolved work probably in the most trouble right now.”

“I think it's a huge mistake if you drop tests in exchange for speed of development, because Very quickly when you're working the test, you find your development speed goes up. The existence of the test lets you move faster because you don't have to constantly …”

“If you get them to write the tests first. You do get better results because they're much less likely to forget to test something or to add bits of code that aren't necessary. And so you could tell them, Write this using test, make sure that you write the test …”

“Now with coding agents that are there, It's going to be very different. We're going to see much more of this. So I think, yes, industry there is going to be much larger in the future that we have these models.”

“It turns out being an engineering manager, as long as you stay very close to the code and are able to continue to craft it yourself, is actually a great skill profile for being able to make agents work for you and for your team in this in this age.”

“Even if they don't work, I think to a large extent, you feel like it's a skill issue. It's not that the capability is not there. It's that you just haven't found a way to string it together of what's available. Like I just don't, I didn't give good enough inst…”

“It's just like you can move in much larger macro actions. It's not just like, here's a line of code, here's a new function. It's like, here's a new functionality. And delegate it to agent one. Here's a new functionality that's not going to interfere with the o…”

“I thought, when I talked to Lex last summer, that it was going to turn everyone into a project manager of the old type. The kind of project manager who's not really doing the things, just telling other people what to do, and then you got this little shh churn,…”

“If you give your agents the same in front during the build time and the same in front during the deploy time, Then the sort of like during this like deployment phase, you don't encounter those many problems.”

“We have found that in this new world where agents can end to end write much more code, reviewing the code is one of these new bottlenecks that, that crop up. And so reviewing a video is not a substitute for reviewing code, but it is an entry point that is much…”

“A database tool and like a knock on effect for that for YC company is Superbase has just seen like an explosion at the demand for databases, right? And the age was interesting is the agents are choosing Superbase as a default tool to like set up and host their…”

“Like, because if you like go out and read the documentation online, like Superbase has the best documentation is reasonable for the agents to assume that that's like the best tool to use.”

“A lot of the time when the coding agent is not doing what you want, it's usually a problem with context and just, like, information that you've given it. It's just either underspecified or there's just not enough information around how to do something availabl…”

“Those who are able to prototype in this way, it doesn't mean that whatever your vibe coded into a weekend suddenly turns into a hundred million dollar business, right? But it's a way to communicate with your teams, your intention. So as long as you have good i…”

“And I think it's going to be very strange as, like, these individual teams of, like, one person are like, hey, that team over there isn't doing the right thing, like, let me just build a prototype that, like, works better. I think at some point it's going to s…”

“In general, I think that kind of the more senior, senior you are, the more you benefit because the agents are so good at taking some sort of idea and then putting it into action.”

“I mean, I still think context window is like probably the number one limit. Like if you look at cloud code executing, it's delegating to all these different context windows. At the end of the day, when each one comes back, it's like getting some sort of summar…”

“I think you need to be curious. I think you need to have agency. But I think if you have those two things, which you probably do, if you're watching the show you can do this now. It helps to be technical, right? There's a couple of things that are useful, but …”

“And I would say like that tool calling, I think really only became reliable about a year ago, like last October, November, when the models that shipped were suddenly really good at calling tools. And I think that then changed everything, right? And you see tha…”

“We feel pretty strongly in like high structure allows for agents to work autonomously for longer. And so our default stack is TypeScript front end TypeScript back end with a shared file where, or a shared folder where all of our shared types and schemas and th…”

“They're kind of like two problems as these things get better. One is like, how do you specify what you want? And the other one is how do you verify that what you got is what you're.”

“It's like watching John Carmack on cocaine.”

“It is actually, I would say it is faster, but not that much significantly faster. It's not at computer speed, right?”

“Would you rather have access could you rather have, give everyone on the team, like very expensive. Coding agent subscriptions, or you get an extra head count, right? Let's say it's like maybe like and almost everyone could say the managers could say head coun…”

“Over time you know, over the next couple of months, you're probably gonna end up in a situation where you only need to supervise the models every, you know, 10 minutes, 20 minutes or so.”

“Right now you need to intervene quite frequently, but it's usually on questions of taste rather than it is questions of, like, raw programming ability.”

“That's going to be blown up with async agents when they're running 24, seven concurrently in the background, then you can have 10 or a hundred times as many, and that's going to dominate inference. That's going to dominate the output you get.”

“The failure mode of outsourcing the thinking, but not the typing, which I think it should be the opposite. You still have to know engineering. You still have to know how to program. You still have to know your application and its architecture, how it's deploye…”

“In the future, we'll be looking not just one to five steps in the future, but 10, 20, 30 steps into the future. It'll be writing unit tests before you've even finished defining the function. It'll be performing code-based-wide refactors on multiple files based…”

“I think memories right now for the large part are mostly useless.”

“I mean, today you might have, like, call it, thirty million developers. That's the number that Stripe always quotes. Maybe that actually will expand to like 50 to a hundred million developers. ... And then on top of that, like it would be perfectly rational fo…”

“We're just going to see these things get deployed and they're going to be broken. So there's a lot of like AI coding agents out there. There's Cursor, there's, I guess, Windsurf, Devon, Copilot. So all of those tools exist and they can do things right now Like…”

“We had the view that instead of pure text interfaces, there was going to be A lot more full interaction where, you know, AI systems could not just read texts and answer questions, but actually just go and interact with the real world and encode. Obviously that…”

“90% is going to be the min bar for broad adoption and saying this is now established technology and we need to look for the next big thing.”

“I'm seeing us heading in the direction of highly integrated, very vertical end to end monoliths, you know, and I don't want to name names, but it's just, it's a, it's definitely a market trend.”

“As long as you see humans and AI writing it, like maybe there's a world where it's only AI's maintaining a code base and the assumptions change, but the moment you start to break that fourth wall and a human's coming in, doing code review, deploying the code, …”

“For agents, I don't think you have really had to tell code style. It looks at your code base and just writes code that's consistent to that. Whereas like a human's not going to take its time sorry, their time to go through the code base and you know, follow al…”

“When you ask the coding agent, when do you think today is? It's always like, 20, 23. And then all the specs that we'll give you are from, like, 20, 24 at best, depending on when the knowledge cutoff is.”

“I think we have a clear line of sight between where we are today and like improvements over the next three, six and 12 months. They're going to have quite stark consequences for software engineering, I think.”

“I expect that a lot more people are going to start doing things like this, like writing your own libraries or just shipping every feature.”

“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. 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 bu…”

“Each tool has a slightly different naming convention, but I know founders who've written hundreds of lines of instructions for their AI coding agent, and it makes them way, way, way more effective.”

“And so I think one of the big things, honestly, that, that that we're solving as a space is, is actually not just the capability itself, but just solving for a lot of these practical constraints and getting the technology to the point where it works for everyo…”

“Being able to run multiple agents and not just one is going to be the way to unlock Honestly, most of the value out of these agents, and that's what we're working toward.”

“I think that's the part where we're far away from agents actually being good enough to take a very rough idea and break it down to small pieces without you as developer or as architect, or even when planning your travel, constantly getting questions back of wh…”

“So now we're looking at, holy shit, we spent the last five, six years building all those Lego blocks for knowledge work. If we're just putting it, AI coding agent on top of it, you can have any kind of knowledge, customer software, customer agent for whatever …”

“Like Devin's trying to create that right now where like I could just give them this idea for an app and then I could go eat pizza and come back and It's just done after many iterations. And so that is like the full, that's where I think this is ultimately goin…”

“If the agent there has to always get human involvement to keep on fixing itself, it's probably not ready to become a full end-to-end automated system, because then we're just going to turn into a linter where, like, it produces a bunch of things and no one loo…”

“I wouldn't go all the way and suggest they should pivot, but I do think companies that are building AI coding agents or AI program engineers are potentially have stuff to think about here, because it seems like O-One in particular is like outperforming on just…”