How To Build Superintelligence Inside Your Company

Building superintelligence inside a company isn't about adding AI as a feature. It's about making it the operating system the whole organization runs on. In this episode of the Lightcone, we sat down with YC's Pete Koomen to talk for the first time about how he led the effort to build YC's internal agent infrastructure from the ground up. We cover how giving agents unrestricted access to one database changed everything, the self-improving skill loops that get smarter overnight and why he thinks we've arrived at the personal computer moment for AI. Chapters:00:00 — Intro00:39 — YC's AI Stack02:15 — The Finance Team Problem That Started It All05:07 — SQL Access Changes Everything07:20 — One Database to Rule Them All09:14 — Jevons Paradox 10:07 — Denormalizing for Agents (G-Brain)12:15 — The Single-Player Era of Agents14:16 — 350 Tools and a Shared Registry16:24 — Skillify, DRY, and MECE Resolvers18:23 — The Self-Improving Dream Cycle20:26 — The Two-Sentence Pitch Skill23:06 — How Super Intelligence Compounds25:10 — Recording Everything as a Building Layer27:10 — The Shared Organizational Brain29:18 — Trust-Default Culture as a Requirement30:44 — Raising the Floor for New Employees32:35 — Horseless Carriages Essay Explained34:24 — Why Chat Is the Best Interface for Agents36:10 — Garry's List → G-Brain Rewrite38:50 — Just-in-Time Software40:49 — Centralizing vs. Decentralizing AI43:32 — The Personal AI RevolutionApply to Y Combinator: https://www.ycombinator.com/applyWork at a startup: https://www.ycombinator.com/jobs

• 0:00Speaker 00

  How do you build superintelligence inside a company?

• 0:02Speaker 01

  Part of the key thing is not to just use AI as a copilot. This is the thing where you use it as the building layer for everything. And you need to start recording all the artifacts.

• 0:14Speaker 02

  It's like a shared organizational brain. It's like the closest thing to us being able to like connect our brains.

• 0:19Speaker 03

  If you frame this as a way for everyone in an organization to get better at what they do, using the like collective skill and instinct of the people they work with, it's incredibly powerful.

• 0:39Speaker 00

  Today, we have a real treat. We have a special guest, general partner at YC, our partner, Pete Koomen. He created Optimizely, which was one of the first and one of the best ways to do A/B testing for apps and websites. And since then, he has gone on to create all of our agent infrastructure at YC. So literally all of our harnesses and how we use AI internal to YC. Pete, welcome to the light.

• 1:07Speaker 02

  Thanks, Gary. For the last few years, since ChatGPT, YC has been funding mainly AI companies. And we've been, we've gone through like many different like versions of advice for them about how to build AI native companies that build like mainly AI products. And we've gone on a crazy journey with them learning all of this. I think a lot of people don't realize that internally, YC is actually building and using a lot of the same stuff that we're helping our startups build and use themselves. And it's been, I think, a very powerful symbiotic relationship for us to actually be adopting these tools and like transforming our own organization, which was started way, way pre-AI, into a super AI native organization ourselves.

• 1:52Speaker 02

  And Pete has really been leading the charge for that. And so I'm really excited about this episode because I've actually been wanting to talk publicly about all the stuff that we've built internally. And this is the first time that we're doing it. So Pete, perhaps to start off, can you sort of go back to the beginning and like? Talk about like, there was a particular like moment when we really started adopting these AI tools internally. It was really you who got us started down that path.

• 2:15Speaker 03

  Sure. Happy to, happy to tell the story here. And it's, I like framing it that way because it was a project that I and a few engineers got started about a year ago, maybe a little more, but that has since snowballed into just the whole infrastructure layer that's made it possible for us to use AI internally at YC in lots of different ways. And that's actually been one of the neatest parts about this is watching the whole engineering team and many partners also just dive in and contribute to this, this infrastructure layer. We started building our own harness inside of YC or kind of YC specific agents about a year ago.

• 2:54Speaker 03

  And the original impetus for the project was some of the work that I and a few of the software engineers at YC were doing with our finance team. Just for a bit, a bit of backstory, so YC has, for as long as it's existed, as far as I'm aware, run mostly on our own software. In this era, just given us a huge advantage, right? And so with that context, back to this, this moment, maybe a year ago, we were sitting down with the finance team, talking through a set of tools that we were going to build for them, just to help them run through some of their finance workflows. Booking journal entries, logging priced rounds, like all the sorts of things that, that make YC run, really.

• 3:38Speaker 03

  I was seeing kind of two things at once. Like on one hand, we, you know, we had this sort of loop going internally, right? Where we'd sit down with the finance team, the finance team would describe to our software engineers how, you know, this complicated financial workflow worked. And then the software engineers would go and build some purpose-built software where there was a deterministic workflow encapsulating everything that they had been told, and then hand it back to the finance team and so on. And it felt really inefficient. And then, at the same time, this was right around the time when agentic tools were really, agentic coding tools were really catching hold, right? And so you had kind of the first generation windsurf and cursor that were well established by this point. I think this right around when Claude Code was introduced.

• 4:23Speaker 03

  It felt like this was giving me superpowers, right? And then kind of watching this sort of old classical way of building software in YC and then watching how I was doing things on my own machine, this, it just felt like a bigger and bigger divide between those things. And so the original impetus was, why don't we try to build some tools at YC that we could use to run agents that would give the finance team control over their own software, right? Like, remove the software engineers from this crazy loop where they have to sort of understand these complicated workflows and give the finance team the tools that they could use to encode their own workflows, not as, you know, not as Ruby, but as English with prompts, right?

• 5:04Speaker 00

  What's interesting is like, we all funded companies, maybe even like two or three years ago when LLMs were out, but like agentic coding wasn't a thing yet. And so the first thing actually was not agentic coding, it was LLMs for writing SQL queries.

• 5:18Speaker 03

  Yes.

• 5:18Speaker 00

  So that's what I remember from like the first versions of what you built was how good it was and how basically it rhymed with like these other failed startups that we had funded, like each of us probably funded one at some point, you know, here it was, it was working. And it worked so well that non-technical people, granted very smart people from finance, but with no engineering background, could use these tools to ask real questions.

• 5:44Speaker 03

  I was really surprised too, to be honest. And so that, we started with this kind of purpose-built thing for finance and then rewrote it to be more of a general agent loop, right? And it's, this is now, you see these all over the place now, but the first kind of magical moment that I had was, we had this agent loop and we had a tool registry, a shared tool registry for kind of YC-specific tools. And the first tool that really was an unlock for me was, I think, a tool, looking back, that you actually built, Jared. It gave these agents the ability to run read-only SQL queries

• 6:20Speaker 02

  Oh, yes.

• 6:20Speaker 03

  against our database.

• 6:21Speaker 02

  Yes.

• 6:21Speaker 03

  Right? It was two tools, actually. One was running queries against our database, and the other one was the ability to read our model files.

• 6:29Speaker 02

  I remember I built those tools and I felt a little bit like I was breaking the rules. Because initially, we started with very limited tools that had very narrowly scoped domains. And I kept getting frustrated because they weren't powerful enough to do the things that I wanted. And so I was like, what if we just gave the thing like access, complete access to the production database where it could just like trample on anything?

• 6:54Speaker 02

  And I sort of like surreptitiously pushed it out, maybe late at night.

• 6:59Speaker 03

  And it worked.

• 7:00Speaker 02

  And it worked.

• 7:00Speaker 03

  It worked extremely well, right?

• 7:03Speaker 02

  Perhaps foreshadowing, you know, subsequent things like OpenClaw, where it turns out that like the thing that was hampering the world was being worried about security and privacy and all the things that could go wrong. And when you like worry a bit less, you're like, oh, my God, these things are unbelievably powerful.

• 7:17Speaker 03

  It's another really good example of this weird split between I'm at work and I'm kind of operating in this really narrow box. And I'm at home using Claude Code or whatever, like OpenClaw, Hermes, and I can do anything, right? And trying to narrow that gap. So why was this so useful? This ability to run SQL queries against our database? It sounds really simple. Well, I think this is where it's important to talk about. One of the big advantages that I think YC had coming into this experiment, which is that we run on our own software. And all of that software sits on one Postgres database that has everything that's important to YC's world in it. You know, every company that we funded, there's a companies table. There's a founders table, right?

• 8:03Speaker 03

  There's tables for our financial transactions. There's tables for the notes that I leave in our little internal CRM, right? All of these functions that I think a lot of other companies farm out to third-party SaaS tools, we've built our own. And as a result, we have this database with every important piece of context. That I can now ask questions like, hey, show me all of the investors who invested in a space-related company in the last four batches. Right? It just turns out when all of that context is in one place, with a little bit of additional information about how the schema is laid out, an agent can go and ask or answer arbitrary questions about our business.

• 8:41Speaker 00

  That was a magic moment, for sure, when I first saw that.

• 8:43Speaker 03

  Yeah.

• 8:44Speaker 02

  The cool thing for me is that it didn't just make it easier to answer questions. It dramatically increased the number of questions that we would ask and dramatically increased the scale and complexity of the questions that we would dare to ask. Where like, you know, in the in the old days, back when we were using like BI tools, to ask to ask a question like that, you know, like when investors have invested like in space-related companies, that would be like several hours of writing SQL. And so like, unless it was really important, you just wouldn't bother.

• 9:10Speaker 03

  It's just another example of the, you know, this instance of Givon's paradox that you get when you remove the amount of back and forth between different teams in order to get a thing done. Right? If if in order to ask some kind of complex question about YC, I have to go and knock on, you know, the data science team's door and wait for them to get it through, you know, their backlog, I'm just going to ask far fewer questions.

• 9:36Speaker 00

  I mean, there are people out there watching this who work in places that still use it. The majority of people live in that world still, and it's 2026, which is a little unfathomable, actually.

• 9:47Speaker 03

  There's a long way to go, I think, which is which is really exciting.

• 9:50Speaker 01

  I guess my question is, how do companies that live in that old world could get sort of wings to move so quickly? Because the magic for us was, as you said, everything was, the context is in one place that made it easy.

• 10:03Speaker 00

  You know, if you think about data science historically, one of the first things that the Googlers had to figure out was a big table, right? And big table was, you know, instead of schema and joins, you have one big table that can be map reduced.

• 10:20Speaker 03

  Yes.

• 10:21Speaker 00

  And so I think that that's happening again. And I would argue that that's happening now with Karpathy-style knowledge LLM wikis with G-brain.

• 10:32Speaker 00

  I mean, that's what I'm seeing anyway. Like, you know, obviously, I have, I have an OpenClaw. It has access to lots of, lots of systems. And then I'm normalizing it to my own schema that's relevant to me and the things that I care about. And it is like denormalization. It's you're taking data and you're putting it into a format that is more or less optimized for OpenClaw or Hermes agent, like that particular type of harness to be able to ask questions. And it needs retrieval, it needs RAG, it needs GraphRAG, it needs, you know, hybrid RRF, like there's reranking in there. Like, you know, all the things that everyone has learned about retrieval is now inside G-Brain. And then when you give the agents a soul and it, and you give it the data and it knows

• 11:15Speaker 00

  you and what you care about, like suddenly these things have insane wings. Like, I just kind of can't believe how it sees around corners. And you might ask a question and it'll even, you know, sort of interpret what your question was about and like give you a thing that frankly, like it would take a human who really knows you well to answer. All that's possible now. And so, you know, your question is like, all the data is everywhere. My answer from like the OpenClaw Hermes experience with G-Brain is like, yeah, you basically have to take that you're going to denormalize it and you're going to put it in a format that is optimized for agent retrieval and understanding. You could wrap it in an MCP, but for whatever reason, I just like intuitively, I'd be worried.

• 11:59Speaker 00

  Like, it's still sort of, you know, these things are really good at working with MCP and CLI. Like, they're a little even better with CLI. It seems like you have to denormalize and do the big table thing, but, you know, specifically for the agent.

• 12:12Speaker 03

  Looking back over the last year and a half, it feels like we're still kind of in the single player era of agents where the harnesses that have gotten really popular, right? Claude Code, Codex, Pi, OpenClaw, Hermes, they're all designed to be used by a single human running on a single machine. And it makes a lot of sense, right? Because in that environment, these, these agents can do just about anything, right? And they, they make you incredibly powerful. It's, it's, they're a lot of fun to use. I think one of the big problems that I don't think has been solved well yet by anybody is the multiplayer harness, right? It's, it's enabling that kind of superpower, but on a team or an organizational level, right? And, and, and that's, I think,

• 12:58Speaker 03

  Been the interesting thing to explore with the infrastructure that we've built at YC is watching which primitives that we've created that have enabled individuals and teams to use agents. You asked the question about if you're working inside of a kind of a legacy organization, which is like anyone who's more than two years old.

• 13:18Speaker 03

  What are the things that you can focus on in order to help enable everybody at your org to use AI to do more? And we talked about kind of this common context layer, right? And so a data warehouse where just as much of your internal important context lives, it just turns out is extremely useful. There are many tools for connecting individual agent harnesses to, you know, other MCP tools, other sources of truth. But just like a coding agent inside a monorepo just tends to be much more efficient, watching our agents operating on our single database that has everything in one schema

• 13:59Speaker 03

  tells me that there's a lot of value, at least, in getting all of the context into one place. Having an internal tool registry, this is, I think, the other really important thing that we've built. So in the beginning, like we were talking about, it was just, the whole system was really simple. It was like an agent loop and a simple tool registry and, you know, a few other pieces, right? Like a model router underneath. The tool registry is where most of the like YC-specific stuff lives, right? Like tool registry is what turns these agents into something that's useful at work. And we had like 20 tools at the beginning, including this magical ability to query our SQL database. But over time, teams have added more and more tools.

• 14:40Speaker 03

  Every time we kind of come upon some piece of work at YC that we think could be improved with an agent, we can just add tools. And there's more than 350 today, I just checked, right? Every team is adding their own tools. You know, I can do things like manage my office hours. Our finance team can, you know, can book journal entries, right? We can help manage the events that we run. There's tools for all of the important work that we do at YC. And now, once these all exist in one place, you can make them available to these internal agents that we've built. But you can also make them available to Claude Code, you know, running on our individual machines. So those things above all, I think, were the important pieces that we built that. If I were working in any other organization, I would focus on building.

• 15:26Speaker 00

  I mean, honestly, inspired by what you guys did with tools, like this idea of Skillify in OpenClaw. And then actually, the most important, the last part of Skillify. Skillify is like this meta-skill that I made in OpenClaw where it's like you just do anything in OpenClaw and Hermes. Hermes actually already has Skillify. They call it something. It's like it makes skills automatically. But the most important thing I think is actually like plugging it into the resolver, which is like your agents.md with like the list of things that the agents can do. And then like it links to the markdown entry point that like lets you use a tool, basically. And so like this thing keeps coming up in all these different contexts, like Claude Code has a skill. The skill registry in Claude Code is actually a resolver.

• 16:11Speaker 00

  Our tool registry is actually a resolver. And then the weird thing that you have to do on top of that is actually I have a meta-skill called check resolvable that I call all the time. So I'm always like, I do something that's new or different in my agent. And then after it does it and I like it, I say Skillify it. And then it becomes basically like a tool call or method call. And then I run check resolvable, which is like, you know, look at all of the other skills and tools that exist. And is it, you know, dry, don't repeat yourself? And is it M E C E, which is, you know, I'm embarrassed to say a McKinsey term. Or the consultants use it for making really good slide decks, mutually exclusive, collectively exhaustive.

• 16:56Speaker 00

  That's like how you're supposed to do slides if you're a McKinsey consultant. But it's useful because it's like an additional layer on top of don't repeat yourself dry. And like the models just seem to know what those things are. And so if you have a dry and M E C E resolver table anywhere, it's actually like the optimal resolver.

• 17:18Speaker 00

  Like it's bad to have 10 skills that do all the same thing. It's good to have one skill or one tool that has parameters that then let you call them. So I don't know, I think it's like, this is like the wildest time to be alive as like an applied computer scientist. Cause it's like simultaneous like discovery of the same useful applied concepts over and over again. And I wonder if like, when people are, you know, developing the first versions of Unix or something. It's like discovering a stack and a heap. It feels like we're right at that moment today. Like we're just coming up with the new primitives for what an agentic system actually is. And you can see it in the parallel sort of development of like, we're just trying to do a thing. And it might be in Claude code, or it might be in our own internal harness, or it might be in OpenClaw, it might be in Hermes.

• 18:03Speaker 00

  Like these things just keep coming back over and over again.

• 18:05Speaker 04

  YC Startup School is back. We're hand selecting the most promising builders in the world and flying them out to San Francisco for July 25th and 26th to discuss the cutting edge of tech and startups. Apply now for your spot.

• 18:20Speaker 03

  Yeah, it's really interesting to look at how some of the other companies that are building this stuff have built their infrastructure because you see a lot of these same primitives in each of them, right? Like there's the agent loops, there's tool registries, there's skill registries. Looking at the way that we're using skills now at YC. So if you think of skill as a simple abstraction layer over tools. We have a handful of sort of shared skills that we all have access to through this agent system. And it's been interesting to watch. I think you've talked about this where this progression of like, in the beginning, you were kind of writing your own system prompts. And then skills emerged, and so you started writing your own skills. And then you would start meta prompting where you'd, you know, you'd have the agent write a skill.

• 19:05Speaker 00

  Exactly. Improve the prompt.

• 19:07Speaker 03

  Yes.

• 19:07Speaker 00

  Automatically.

• 19:08Speaker 03

  Yes. Seeing us kind of do the same progression internally where we have a couple of skills. And now we've gotten to the point where we have these sort of autonomous self-improving loops, right? You know, and so.

• 19:20Speaker 00

  Auto research from Carpathia again.

• 19:22Speaker 03

  Yes.

• 19:22Speaker 00

  Yeah.

• 19:23Speaker 03

  Yeah.

• 19:23Speaker 00

  Or slash goal now in Codex. Like they've incorporated it too.

• 19:26Speaker 03

  We have this general agent that every night will go and read through all of the agent conversations that employees have had. And look for things that could have done better and pieces of context that if it had upfront, it would have done more efficiently.

• 19:41Speaker 00

  This is OpenClaw's dream cycle. And G Brain also has a dream cycle. This is a. A skill improvement dream cycle, but it could also potentially read all the transcripts and then write them back into the internal DB, into the internal CRM on like what we know about people and companies.

• 20:02Speaker 03

  Indeed, and we, there are cool examples of using transcripts, actually, to make these skills more effective as well. One of the shared skills that we have is a skill that, that partners at YC use to help our companies write what we call two-sentence descriptions, right? Everybody here has written hundreds of these.

• 20:23Speaker 00

  We should probably explain what a two-sentence description actually is.

• 20:26Speaker 03

  Sure, so a two-sentence description is a concise way of explaining what your company does in natural language that anyone will understand and why it's interesting. Sounds easy, but it's surprisingly hard for founders to actually.

• 20:37Speaker 00

  And also, no one does it, weirdly. Weirdly, like even the most experienced founders like forget because they have perfect context. Interestingly, I now realize YC itself is a, a context engineering sort of process in that like people, we're frequently teaching people, you have perfect context about what's going on in your brain, but great communication is replicating that same context in someone else's brain. And that's what a two-sentence pitch is. Like, what is it? Like, I don't even know what the heck this is. And then second part is like, is it interesting or valuable? What, you know, is it worth my time? And so that, you know, when I, when I teach two-sentence pitches, that's my favorite way to do it is like, do I even know what the heck this is?

• 21:21Speaker 03

  Yes.

• 21:21Speaker 00

  Because if you don't know what it is, you can't even ask a question about it. It's like something about computers, I guess, whatever. What, what time is lunch again? And then the second part is equally important, which is like, if I've heard that, you know, there are like 20 companies, like there are five other companies in this room that do X. Like, and then I don't understand like why this is noteworthy.

• 21:41Speaker 03

  Yes.

• 21:42Speaker 00

  Again, I'm like thinking about my pastrami sandwich again, right? So, so the two-sentence pitch like viscerally is important for founders.

• 21:50Speaker 03

  And it's, it's a, it's a simple kind of atomic thing that every partner at YC has practiced over and over and over again. I think Tom. One of the partners here wrote a skill that teaches an agent how to take some context about a company and condense that into a two-sentence description. And so that was his sort of handwritten prompt or skill about how that was done. And one of the cool things that happened in the last month or two was that a couple of the other partners took a meeting that they had with a group office hours they had with a bunch of the companies in the spring batch and just went through and had every founder try their hand at a two-sentence description and kind of gave them feedback and input.

• 22:35Speaker 03

  And so kind of the knowledge that lives in a partner's head about how to do this effectively was exchanged back and forth, right? And now lived in the context of that meeting transcript and handing that back to the agent and saying, given what you've learned by reading through this context, improve the two-sentence description skill. And they got noticeably better after that. Like this thing is now better than I am, I would argue, at writing those.

• 23:02Speaker 00

  This is how superintelligence happens inside organizations. I mean, this two-sentence pitch thing sounds like something kind of small, but embedded in it is actually something very powerful. I'm sure you guys have heard Jack Dorsey talk about what he's doing with Block. He basically is trying to turn Block into a mini AGI around helping people in the world make payments to one another, right? And then this is actually the micro-mechanism by which he's going to do that, right? Like, you can look at the operation of any organization as the aggregate of, you know, I mean, the two-sentence pitch at YC is that's sort of one of like thousands of things that I would argue we do for founders.

• 23:46Speaker 00

  But, you know, we just walked through a very concrete way where someone wrote a prompt, used it, used a bunch more, other people used it, a bunch of artifacts came off of that around literally like the transcript of using it becomes a thing that can be used to meta-prompt and improve in an automated fashion on a daily basis, the operation of that one skill. And then suddenly, that one skill, you just said it. That skill is now better than any of us individually. Then before we actually had access to that. And so this is like a particular like needle pinprick in the fabric of like how any organization does things. And then how do you build superintelligence inside a company?

• 24:30Speaker 00

  You do that on everything you do. And it's not more complicated than that. Like you literally just compose everything that you do. And any given thing that any given person can do, you combine that in aggregate and in this particular process and like you have a super organization. It's possible now, like every single person watching this can do this at any company, at their own company, they can do it at their job. I mean, the interesting thing is that's why you should start a startup. Cause people are going to be trapped in organizations with people running organizations that are very powerful and have all these resources and all this capital that do not believe what we just said.

• 25:07Speaker 01

  Because they keep all the context locked down.

• 25:09Speaker 00

  Right, because it's unsafe.

• 25:11Speaker 01

  It's unsafe. This is one of those things that we talk about, how do you build that AI native organization, right? Part of the key thing is not to just use AI as a co-pilot. I think that's very 2023, four, right? This is the thing where you use it as a really, the building layer for everything. And you need to start recording all the artifacts, like people wouldn't have thought of a meeting recordings. And this is one of those reasons why all these meeting recorders have been taking off. People have been finding them with coaching them on the meetings, but it's not just that. You could take that and improve all the output for you that you do, like writing emails, communication, planning, you have the whole context of everything.

• 25:56Speaker 05

  It's funny, I remember the Dariya essay where it's like, there's some of the blockers and just the rate of progression of AI are not technical, they're just sort of like social cultural things. I think it's kind of like a really interesting example. Two years ago would have seemed, I just remember it felt odd to just like record a meeting or like there was just like people trying to figure out what the like social etiquette around it was and like how intrusive it was. And today I just feel like it's almost like default assumed that like most meetings are being required, especially if they're on Zoom, but just in general, like everyone started recording. Things now.

• 26:27Speaker 03

  It's a little scary, but I think if you frame this as a way for everyone in an organization to get better at what they do, using the like collective skill and instinct of the people they work with, it's incredibly powerful. Having a canonical two-sentence description skill is not just a way to like generate a snippet of text for a founder. It's a way to help me get better at understanding what makes for effective founder communication, right? Because now I can tap into everything that Diana and Hards and you two have learned over the many years you've done this job, which are now kind of baked into this skill through the conversations that you've had.

• 27:06Speaker 02

  It's like a shared organizational brain.

• 27:08Speaker 03

  Yes.

• 27:08Speaker 02

  This is very empowering. The closest thing to us being able to like connect our brains.

• 27:12Speaker 03

  Yes.

• 27:12Speaker 02

  Right, yeah.

• 27:12Speaker 03

  It totally is, right? And I can have an agent now come and I can do practice sessions with it, right? I can have it critique my like, there are so many possibilities once you get all of this knowledge into a place where an agent can can work with it. It's a very empowering thing for every human in the organization.

• 27:32Speaker 00

  There's some subtle, interesting things around here that like, you know, other people might get wrong that like, I feel like we've gotten right. I mean, one of them is by default, the agent conversation is actually globally viewable by any full-time employee at YC. You know, we sort of weren't sure about that decision. I mean, it felt right and it felt like living in the future, but it did not come easily. I feel like we had a lot of conversations about like, well, then everyone sees everything. Is that okay? And like, you know, what is not okay? And then I'm glad we made the choice to keep it open, actually. Because

• 28:06Speaker 03

  I agree.

• 28:07Speaker 00

  People learned how to use it from watching how other people used it.

• 28:10Speaker 03

  Yes. We used that transparency to solve several problems at the same time. One, every agent conversation, as you mentioned, was broadcast internally to a Slack channel. And anybody could join that Slack channel and look. And learn, right? And I remember, this is another kind of big unlock one was when you started using it really heavily. You were like super creative with with the things you were doing with it. And a lot of us watched that and was like, oh, wow, I didn't even

• 28:36Speaker 00

  You can do that now.

• 28:37Speaker 03

  To to to use it that way, right? It allows you to be a little more lenient on internal security, right? One of the things we talked about earlier was this trade off where these agents are at their most powerful when they are given unrestricted access to lots of context, which runs counter to the way more most organizations work. It turns out that by defaulting to public broadcast for these conversations, you kind of institute a bit of a social control on what people can do with it. That, as we learned, I think has been like reasonably effective inside of this high trust environment at keeping private information private.

• 29:15Speaker 00

  Yeah, what's interesting is it it betrays two traits of truly agentic, like 1,000x super intelligent organizations that I would not have necessarily guessed would exist, but are now like must exist. If you want to create this type of organization, you have to be relatively egalitarian and you also have to be trust by default. And then neither of those things actually are most organizations in the world. If you're the founder of an organization, you actually have to have those at the core of what you're doing.

• 29:44Speaker 03

  And I think like that kind of environment honestly works best at startups, right? When it's a small group of people that are all aligned and and and operating in a high trust environment.

• 29:54Speaker 00

  The other thing you have to do is be willing to spend like 10 to 100,000 dollars a year on tokens. But if you're willing to do it and you invest in the skills and you like actually do everything in an open way with your team that way. Like basically what I realized is it allows you to live in 2028, right? Like what you spend 100,000 or a million dollars a year on now, it will be commonplace like in in two years, right? It'll it won't cost 100,000 in a year. It'll cost 10,000 and the year after that it'll be like a couple hundred bucks, right? And everyone will do it and we'll call it like this is how companies are now. So basically there's a one time time warp where you can leapfrog every incumbent, all Fortune 500s, all startups that exist.

• 30:39Speaker 00

  By doing this.

• 30:41Speaker 02

  Like, I'm imagining in the 90s, I wonder if it felt similarly when companies started buying computers for their employees.

• 30:47Speaker 00

  Yeah.

• 30:47Speaker 02

  They were probably very expensive and probably only certain companies really invested in buying these like expensive, flaky computer systems for their employees. But like, what a superpower to have a computer when your competitors like don't have computers.

• 31:00Speaker 01

  I think more tactically how I've seen this effect at YC has been raising the floor.

• 31:06Speaker 02

  Floor.

• 31:06Speaker 01

  The floor, in a sense. What I mean by that is that you could have a new employee joining and maybe it would have taken them six months to ramp up. But with this, it's sort of like they automatically get a lot of the contacts from the company working and they know how the best people and the star players in the organization do things by apprenticeship automatically with AI instead of a because partner time is expensive or sometimes the best people in an org, they're very busy, right? And you get to kind of run the simulation of what it's like to be like Pete when he does like an awesome job coaching founders and sales or like Gary when he's like talking to founders and giving very specific advice. I think it helps all the new new entrants in the organization just be a mini version

• 31:50Speaker 01

  of you a lot faster.

• 31:52Speaker 03

  One of the first things that I appreciated about being able to use a coding agent was that all of the dumb questions I was too embarrassed to ask, I had no trouble asking asking the agent. And it, this is kind of that same thing, but at an organizational level, right? You're a brand new employee, you're embarrassed to ask, you don't want to bug hard with with a question. And now you don't have to, right? And which on that means a lot more questions get asked and answered and people ramp up much more quickly.

• 32:19Speaker 02

  After you had built all of this agent infrastructure at YC, it inspired you to write this essay, Horseless Carriages, that went like pretty viral on the internet. Maybe you can like explain the ideas behind Horseless Carriages. I think they're still very relevant now.

• 32:32Speaker 03

  It was a critique of a lot of the the AI software that I saw being built at the time. And to be totally honest, I think a lot of it still falls into.

• 32:41Speaker 00

  It's still like that. Yeah, it didn't change.

• 32:43Speaker 03

  Yes. I just saw a lot of examples of. Companies building software and adding AI features by sort of slotting a little bit of AI inside of a lot of software, right? And the example that I used at the time was the kind of email writer that the Gmail team had shipped. But the real idea underneath was this kind of that the potential for AI is to shift control of software from the developer to the user, right? And the simple example I started with was basically that all of these kind of like AI as a little feature kept a bunch of prompt context about how the AI should do a job locked away and hidden from the user, which was just this classic

• 33:28Speaker 03

  example of like, well, it's the developer's job to figure out how all of this stuff should work. So the developer should write that and we should protect the user from that kind of complexity.

• 33:37Speaker 00

  Safetyism, I hate it.

• 33:38Speaker 03

  Right, and you know, and it's just, again, going back to this contrast between watching the way that some of these tools work and what it was like to use a coding agent on my computer that could do anything, right? And feeling like I had superpowers. I think the conclusion that this essay points to is that as we get better at building AI native software, it's going to look a lot more like the agent wrapping software deterministic tools rather than deterministic software wrapping in AI, right? And we've done our best to expose that to internal employees with some of these primitives that we've built. But we have a lot, we have a long way to go.

• 34:21Speaker 05

  The chat as the interface, I just feel something, there's like things going around right now about how there's a need to build new interface for like AI and what does that look like? And I think that just comes from people who haven't like touched and felt it yet. Chat is actually pretty good because like you trust the agent, you increasingly trust the agent to do more of the work and you trust its decisions and you don't actually need to like have too much of a UI to go in and like review the things it's doing.

• 34:46Speaker 00

  It's time for just in time software.

• 34:47Speaker 05

  Yeah, basically, right? Like, yes, occasionally you want it to present you like maybe like a specific view of something, but.

• 34:54Speaker 00

  And it could make the software and build it as a single page JavaScript just purposely built for you at that moment.

• 35:01Speaker 05

  Yeah.

• 35:01Speaker 00

  And it could be a skill file that could be like called anytime you want.

• 35:04Speaker 01

  I was thinking a lot about this because I used to be in the camp that, oh, perhaps when ChatGPT came out and it was 2023, that perhaps chat was not going to be the UI for all these AI applications. And I've definitely changed my mind. Part of it is after experiencing all these tools. And I think the more I reflect upon it, why chat is probably the better interface is because it's the closest thing to human language. And human language and writing is basically the closest thing to expression of thinking. So chat is the closest stepping stone to clear intelligence.

• 35:36Speaker 00

  Yeah.

• 35:37Speaker 01

  So you can't just put it in a box. I think it just constrained it too much to have a very specific box. So that's why I thought it's like, okay, all in with chat interfaces. I used to be in the other camp and it's like.

• 35:49Speaker 05

  It's multimodal. I know we've talked about like Telegram is not ideal, but I actually.

• 35:53Speaker 00

  It's pretty good.

• 35:54Speaker 05

  Yeah, it's really good.

• 35:55Speaker 00

  I mean, the voice memos, sometimes when I don't want to type, you just do the voice memo. And it's, it feels like I'm talking to.

• 36:00Speaker 05

  I can give my open crawl, like I can give it text, I can give it voice, I can give it pictures of things.

• 36:04Speaker 00

  It's great.

• 36:05Speaker 05

  I can give it files, like it's like pretty good.

• 36:07Speaker 00

  Yeah, I just experienced this. So like January, I think the last episode we did, I just talked about this, like I spent January and through February, building a half a million lines of code for a Rails app, which was Gary's List. And it's like, you know, I know people make fun of me for like, it was a blog, but it was like, I built the blog in like the first week, like I spent a month and a half building a full agentic framework that did like my own version of deep research and like fact checking. But the thing is I built it the way I would have built software in 2013, the last time I wrote code. It was like the web 2.0 version of this and Claude Code lets you do that. And what's crazy to connect is like, I'm working like, I don't know.

• 36:49Speaker 00

  I think I wrote like 40,000 lines of code the last three days just for G-Brain. And G-Brain is basically Gary's List 2.0, but it's totally open source, right? So everything I had to write for agentic retrieval, everything I had to do for voice extraction, everything I had to do for fact checking, all of that now exists inside G-Brain. And I just gave it to my, you know, Gary's List team yesterday as their own OpenClaw instance. And they're flying now, right? Like they were complaining about like, I had made, you know, this monolithic writer chat interface. And it was like full of bugs because I was like re-implementing things that OpenClaw and Telegram already do.

• 37:31Speaker 00

  And now they just use OpenClaw, Telegram and my retrieval system with like all the same data that I extracted it out and with our MCP. And it's working great, like basically, you know, Gary's List 2.0. The next rewrite thankfully is not half a million lines of Rails code that is like insane to actually, you know, it's rigid, it takes a long time, it takes like 10 times long, you know, even though it was 1, 100 the amount of time to do it like by hand, you don't have to do it by hand, like that half a million lines of code in Rails is easily like 10,000 lines of like TypeScript and like maybe 2,000 lines of Markdown. And all of that is way more dynamic, like you could just say like, actually, for the

• 38:16Speaker 00

  second paragraph, I really like including a biography of like the politician we're focusing on. And it's like, I don't have to code that in Rails, I don't even have to write that into a Ruby file that then gets eval in like, you know, my complex eval infrastructure, like OpenClaw just knows that and I have an eval skill. My editor in chief can just change it on the fly and I didn't touch it. Yes. And it's like, this is insane, actually, like this is actually the dawn of just-in-time software and I can see it right now.

• 38:47Speaker 03

  The best AI software that I've used, whether it's inside of YC or tools that others have built, tend to be very small and just add kind of the smallest amount of code ahead of time that you need in order to let the model shine.

• 39:03Speaker 00

  Mm-hmm.

• 39:04Speaker 03

  And you can build an awful lot with that, right? I can write tens of thousands of lines of code, like you're saying, but the ability to start at this like extremely simple thing that I need to understand very little in order to use is incredibly powerful and I think that's, I think most software in the future is going to look like.

• 39:24Speaker 05

  We were talking about this earlier, but I think that is what OpenClaw did really well, like there were like a few things that you wanted, like some ability to give it a bit of personality, you wanted it to like persist and last for a long time and have some constant memory, it's not like perfect, but. That's actually like good enough as like for that use case.

• 39:42Speaker 02

  A Claude code too. Every time Boris comes and speaks at WESI, he spoke with Diana earlier this week. One of the things that really stands out is how obsessed he is with simplicity and with just like making the product as small as possible.

• 39:55Speaker 03

  My favorite example of this is this open source harness called Pi.

• 40:00Speaker 05

  Yep, that's what OpenCore uses as out of the box coding agent.

• 40:04Speaker 03

  It's this beautiful piece of software, which is just like the smallest possible coding agent. You can use Pi to modify and extend Pi, right? And it's this kind of idea of like self extending and self referential software. It's really fascinating. And you're right, OpenClaw was built on top of that. One of the things I'm very curious to see is how many other sort of pieces of classic software emerge in this form as this kind of minimal thing that you start with and then use an agent to extend over time. I think more and more, I mean, looking at honestly, the benefits that we've gotten from having our own customizable software, I suspect that a lot of commercial software will come with this capability out of the box in the future.

• 40:45Speaker 00

  There's a really interesting subtle thing that I wanted to talk about around like what I learned from your essay, which is like AI can either be centralizing or decentralizing. And the Google Gmail, like I can't change the prompt thing is like the perfect example of that. We basically have a choice to be made over the next, I don't think it's even that long. I think it's like 18 to 24 months. It might take five years, but there are sort of two scenarios. And what comes to mind is literally like the 1984 Macintosh commercial by Apple, where it's like, is 2034 going to be like 1984? And you know, the 1984 case would be we have centralized control, like there are five kings, there's only, you know,

• 41:30Speaker 00

  one of them maybe wins. They have the most advanced AI, they have end run around all compute and power. They have all the space data centers because you can't build any terrestrial data centers in America anyway. There's this like centralization of control. And not only that, they don't let you run your own prompts. Like they literally do the Gmail thing, but like for your whole computing existence, right? And this would be as if like personal computers never existed and there were only mainframes and mini computers. Like this is sort of lost to the sands of time. But, you know, in the 1960s and 70s, when computers first came out, like you couldn't go to the store like you can today. You couldn't go to an Apple store and just buy an iPhone, let alone a Mac.

• 42:15Speaker 00

  You had to get access to like this thing that was worth like hundreds of thousands of dollars to millions of dollars.

• 42:22Speaker 02

  And it was like tightly locked down by corporate policies. You're right. And the thing that really spurred the computing revolution was when people started having personal computers that they could experiment on.

• 42:33Speaker 00

  Yeah. And it was like the priesthood, right? There was a small priesthood and an institutional base that controlled capital, literally the means of production. And so, you know, this is like a coherent future that we could live in that I don't want to live in. And the alternative to that is actually embedded in the Homebrew Computer Club. It's embedded in the revolution that Steve Jobs and Steve Wozniak gave us when they were in the garage in Mountain View, literally soldering together breadboards. And they like sold 500 of these Apple Ones. And I think we're at the Apple One moment right now. We are coming up with the primitives. We are learning how do these things work and how do we sell it and how do we package it? But then there's like a lot of choices right now, right?

• 43:17Speaker 00

  Like most people, the mass, you know, a billion users use ChatGPT. And ChatGPT like gives you a little access, but MCP is really locked down. You actually, you know, can't hook things up to your own databases that easily. And, you know, for what? Safety? Like I would argue Claude is like a little bit more open, but not really. Perplexity Computer is probably the best version of it, but it's still like, you know, pretty limited compared to what you could do with OpenClaw and Hermes Agent. And so what does the revolution look like that is like the true personal AI moment? And that's what I hope that we are building with things like G-Brain and, you know,

• 44:00Speaker 00

  Hermes Agent and OpenClaw, like the ability to run your own software, to change your own prompts, to test all of it, to have your own private repo that like you know is only yours, to be able to choose which model to use, and maybe it's an open weight model. Like, to me, that's sort of the white pill for AI is we could have corporate control, no control of your own prompts, and like literally the AI happens to you, you know, you're under the API line. Or like, there's this other alternative where I want like a billion people to actually control and program for themselves. What are these things?

• 44:42Speaker 00

  This should be an extension of yourself and what you care about, not what, you know, Meta or Alphabet or even OpenAI or Anthropic care about.

• 44:51Speaker 03

  I always really bristle when I see AI framed as a way to replace people because it just doesn't match the way that I have experienced it and the way that so many of the people around me have experienced it, not as a replacement for humans, but as a thing that empowers. If you look at at kind of how tech has developed since the era of mainframes to PCs to the internet, which gave everyone like a publishing platform, like it's it's a story overall, above all, of individual empowerment. And I think AI is going to play out the same way. I think it is going to enable us to do more than we could before. I think it's going to eliminate kind of the drudgery style work that like made a lot of my job painful in the past.

• 45:33Speaker 00

  To me, it's like we have to make choices to do so. By default, like, a company is not open. By default, a company is command and control. By default, maybe the leadership gets access to these tools, but like the, you know, line level people, the staff people don't, right? And like, you, we need like a radically different type of organization, and we need to actually offer computing in a different way. And these are all choices. And the people who are watching are going to be the people who build all these things in society. So we better choose well. Well, that's all the time we have for today. I mean, I think we covered some pretty heavy stuff, but Pete, thanks for joining us. Thank you. Thank you. Thanks for watching, guys. We'll see you guys on the next one.