What Happens When Everyone Can Build Software

9,389 words · about 38 min to read

AI agents and non-engineers fuel massive growth

0:00 I'm genuinely excited about what the future could be for a lot of people. The thing that I really love about Superbase is that like I see a lot of entrepreneurship um because of the platform. I certainly think that it'll be the case that everyone in the world with access to AI will become a builder of some sort. Like you can build anything, you can customize it. You want to make tweaks to some app, some UI, then you don't have to be beholden to to someone. I'm pretty pumped about 2027 actually.

0:37 Welcome back to another episode of the light cone. Today we're joined by Paul Coppstone, co-founder and CEO of Superbase, the open-source Postgress backend that's become the default database inside tools like Cloud Code and Codeex. Superbase now has 13 million users and it's spinning up over a million databases a week. Paul, welcome to the Lite Cone.

0:57 Thanks for having me.

1 Highlight · Agents driving 70% of new activity

0:58 So, to start off, uh, you know, famously YC gives you a t-shirt on the first day of YC that says, "Make something people want." But increasingly, all of us are realizing it's make something agents want. And your company really exemplifies that. You know, something like 70% of the new activity is from agents. Isn't that crazy?

1:18 Yeah, it's wild. It's wild. I think like this year especially what we've seen in terms of the numbers the inflection is just a huge shift towards agents

1:29 just so we can understand just how much you guys have grown cuz it's kind of mindboggling. Um yeah like what are the numbers you care about and where were you like this time last year and where are you now? I think this time last year, so yeah, we're 13 million signups now. Probably 12 months back, we would have been around three perhaps. Um, this year, like revenue will grow, 4x. Um, we've got trying to think what

1:55 you got like a million databases being created per week at the moment.

1:59 Yeah. Yeah. Yeah.

2:00 What was it this time last year? I think actually if um databases under management now are approaching 50 million and this time last year it was 8 million. So it's just a huge huge inflection.

2:12 What's been driving that?

2:14 First people are building with abandoned software engineers. Second I think that there are a lot more builders coming online. So what was traditionally uh someone with a software engineering background is now uh it's now becoming possible for non-engineers

Transitioning to a code-first and open-source model

2:32 to actually build things on top of superbase.

2:35 So this is a really big shift. Uh what have you guys actually done to facilitate or encourage this shift from you know obviously software engineers are going to keep choosing superbase but you know how do you get the agents to come over in the first place? Yeah, we

2 Highlight · Why AI agents prefer open-source infrastructure

2:50 largely have seen like three chapters in Superbase. We started as a dashboard company, then we went to an API company, and now we're very much a code first company. So, we try to have the modalities that the agents really want to build with, which is code first. They really want to use CLI most of the time. The other thing is just being chosen as a default uh in the LLMs which I think we were a huge beneficiary of our of our um the timing of which we started to become a default choice for databases.

3:24 How much do you think being open source played a role in it too cuz the agents love open source things?

3:29 You know it's hard to know the counterfactual but I think it was critical. I mean everything that we do is open source and it seems to have been a a huge benefit to us and we do it in a very open- sourcy way like we tried to support existing tools. It's not just superbased tools we we support like Postgress is a very um famous tool for the Postgress Ecosystem and we help to maintain that. So we kind of got sprawl across many communities. I would guess that the agents actually really like open source because when something goes wrong, it can just look at the source.

4:03 Yeah.

4:03 Yeah. I mean, I noticed the agents really like feeling powerful and they love data and uh there's nothing more frustrating than hitting a brick wall and then you don't know what's going on and you can't fix it. I think it's going to be increasingly important as well because now with you know security being so important I think a lot of the say enterprises are going to want to inspect the source code to know that it's secure and if you've got closed source code then you probably won't want to adopt them as a vendor.

4:34 Is developer even still sort of the the core user that you're going after or how

4:40 you know how do you think about it now in 2026? Yeah, I think that the world where we're moving and at least what we're seeing this year is like um kind of builders builders are coming online and it's like a crazy amount of people coming online. The crazy thing about this year is usually when you're um like our top of funnel, our signups are accelerating. And usually when this happens, you see a lot of the other numbers start to decline, activation, conversion. But actually this year, all of them are kind of going up and to the right, which is a bit insane just because the models are getting so good at building. And we're starting to see people who traditionally wouldn't have a software engineering background able to come and and build things.

5:25 That's the distinction is like builder as in they might not be actually software engineers. They might just be someone who needs to build a thing and they're just, you know, popping open cloud code and then it turns out files only get you so far.

5:40 Yeah. And in some ways like this category of people have all these pent up ideas that they could never convince a software engineer to like help them build and now they don't have to convince anyone. They've got all these ideas that they're churning out. Software engineers still make up a huge portion but the rate of the growth of the builder segment is is pretty pretty big. Also like I don't know where the ceiling is on this one. Like I I remember our early investors were saying ah PLG product like growth is going to tap out at this revenue and you'll have to start moving into this segment of the market and there just appears to be no ceiling so far and I I can't see where it stops.

6:23 I mean that was basically true like two years ago or one year ago but definitely not true this year.

6:28 Yeah. I was just talking to someone actually this last weekend if it's the builder category. It's like a a fintech

Domain experts building bespoke personal software

6:34 founder just exited his company of like over a billion dollars and um he's always been sort of product adjacent like studying math at like as an undergrad and sort of like kind of could pull together some Ruby scripts but like always need an engineer to like build the software and now side projects he's just building his own stuff and he has all the knowledge from how to build a fintech company so he can actually build pretty sophisticated just like for his own personal finances like balance sheets and tracking software and knows how to like integrate in with banks and he's wring all the integrations from scratch and it's just like the kind of software that would never have been built um even 2 years ago. These are the perfect type of builder as well because like developers like me I have very like developer focused ideas and things that I want to build but then you've got all these domain experts and they know exactly the niches of oh this is an unsolved problem in my niche and so they're actually able now to like dig right into those niches without having to convince someone else to join them. I think you guys were talking about this, weren't you in NYC, like the profile

7:35 shifting even from from who you're bringing into the cohort. I think that if you look at the sort of era of what 2022 2025 there's sort of this real shift thinking like well AI is coming and suddenly um having software engineering as uh you know core you know you need a technical co-founder no matter what that was like a a mega idea that you know really came to the four at YC during that time period. is always sort of true, but like sort of doubled down on that. Uh and then really in the last year, we sort of said actually yeah, builders like we're starting to see people who are able to like I mean the much harder thing to do is to know what to build. You know, being able to build is something that anyone can sort of have on tap now. And that's actually a really cool thing. Like can you imagine all the things that never would have built exactly for what you said?

8:29 It's like oh we know that people would buy this. We know that there's a problem here, but at the margins, those people couldn't convince an engineer to work on it.

8:39 Do you have some examples, Paul, of like apps that people have built on Superbase, maybe just for themselves, that are the kinds of things that would have never been built before?

8:49 Well, one kind of cool example was at our conference. We had the conference here and afterwards this guy from Brazil came up to me and he's built an entire taxi app uh from his phone and it's um kind of like a a little mini Uber for his local market and I just thought he's a taxi driver himself. I don't actually know why he built it, but the fact that he could build it and he came up extremely grateful and that he could do this and also like with the type of energy he's he was like 50 years old or something like that, but he had the energy of a like teenager building suddenly, which I think is kind of cool because now it's kind of getting to that stage where I I think it's a little bit there's so much uncertainty around like what is the future of work going to look like but in this category of builders there's that excitement of the future and that's really what I love about superbates it's like something that

9:49 people can come in and those who are uncertain now are discovering this skill set and these opportunities where previously they were just blue collar workers these type of profile

9:59 hard you've been building some of your own personal software recently you talk

3 Highlight · Building personal control towers with local data

10:02 about what you've been cooking up

10:03 it's just grown yeah it's sort of like the end of one stuff but it's just grown out of um getting really addicted to open claw actually like maybe 6 months ago now I'm embarrassed I said it I said like there was going to be no UIs and it was all just going to be like chat through my open claw but it turns out actually and I also was really determined not to use a database for a long time I just wanted everything to be in markdown um but yeah it turns out actually you hit a point where like a database is useful and you do need UI so I've just been building that over the last couple of weeks in particular and so it's like um I mean I call it control tower but it's just like sort of every section of my life like I have like a UI I to like triage all my emails so I don't need to read my inbox. Um, finances, tracking like spending, health, like both like tracks my weights and my workouts and everything is all in like one place. But I like the magic of it is sometimes it's a mindboggling thought actually is like I think about like the finance section of like my one app for myself is better I think is at least feature parity to mint or monarch or all of these things but in some ways

11:04 actually better because you can start doing really personalized context like it can figure out what a transaction is by looking up in my like the name in my Gbrain to figure out who that person is. Oh, like you know that's like and and and categorize it correctly. And that was like a whole company like several startups just doing personal finance and then you just like build it for yourself and I don't need it to work for anyone else or like have anyone else's opinion on it. It's just like kind of like my thing is like it's kind of awesome. We see a lot of that one like where it's finance and health are basically the two like ones where you want your own data.

11:38 So we see a lot of people doing that and syncing all the devices to a single database is kind of a magic skill. And then you can like prompt it to like build these correlations across.

11:50 It's the correlations that are really bad. Like again like if you just take the health example, it's like yeah all of that data is in like my two base database but then it also has access to my calendar so it knows things like it's like oh like your weight I know your weight went up recently but like you were traveling so that's okay like you can just like get back on track um next week. And it just has like this context that's really valuable. I also found as I started to use the personal agents like I'm getting a little bit paranoid that I'm putting all of like all of the um like routines and everything and the CRM is becoming like um boxed into one agent. And so now I'm slowly extracting it out into one so that if I want to attach different agents on top then I know that like I can use any any agent.

12:33 So the CRM is another really critical one. Yeah, that's why you guys are so valuable is like actually like it's like the it's sort of like the store of record. to the the the database is actually the thing that's valuable. Like you don't you want to own your own database and then build all the applications or agents on top of it versus having that all in like someone

12:52 else's database.

12:54 Which is a totally wild idea like if you just think about the history of databases used to be the case that like the world had only a relatively small number of very large databases run by like large companies. And I remember like when Subbase got started, you kind of had this idea that they should be like really easy for everyone to like make a database. And it almost like didn't make sense at the time why so many people would want to do that because unless you can write code, what can you do with a database? And there's not just not that many people who can actually like write code and build a personal CRM like that. Like it's just like too much work for most people preI.

13:28 Like another example actually where super is really valuable for me is like the other section I have is just like a file upload. Sounds very simple, but like any file I can sort of either forward via email or just like dump it in this UI and then like my agent like figures out what that is and how it's relevant to my life and like what to do with it. Um, but that's all being stored on Superbase. And so yeah, in general, it's just like Superbase is actually going to end up having like all of the like data about my life in a single place and like I would I would never have thought about wanting a personal database like a year ago because it wouldn't have made any sense. But now I like that's actually like the most valuable thing.

14:05 Yeah. You have like an S3 compatible superbase files thing and all my stuff is in that.

14:09 Oh, really? Nice. Yeah. Yeah. Yeah.

14:11 It's default in Gbrain.

14:14 Great. Thank you.

14:15 Do you think this is the future, Paul, where like basically everyone in the world, not every developer, every person will have a superbase database that has stuff about their life in it, their health, their finances, their relationships.

14:29 Yeah, we'd love that. I mean I I certainly think that it'll be the case that everyone in the world with access to AI will become a builder of some sort. Like you can build anything, you can customize it. You want to make tweaks to some app, some UI, then you don't have to be beholden to to someone. Of course, like we think of ourselves as an index company. We when we came into YC, we just focused on YC companies. We wanted to win all YC customers and like now that was because we knew that we had to be there on day one when businesses were getting started. The mission didn't change just the aperture has like

Architecting for billions of personal databases

15:07 increased significantly. Now as more builders come online we know that we need to service them which is actually a whole different problem to solve but kind of an exciting one.

15:17 Significantly meaning like 10 millionx.

15:21 Yeah. Like so what we launch now a million databases every single week but I mean if you do some basic arithmetic let's say with chat GPD I think they said they've got 1.2 billion weekly active users and let's say all of them want to launch something every month that's 1.2 two billion databases a month. And so that's like the scale that we're moving towards architectures that

4 Highlight · Scaling down to SQLite to handle billions of databases

15:46 we need to have so that we can actually cater for for that scale which is something that has never had to happen before on the database database realm.

15:56 Can you even do that with Postgress? Are you going to have to build your own database engine to scale to 1 billion new databases per week?

16:03 I think yeah. Well, if we could negotiate better with AWS, then maybe we could. Turns out that uh everyone wants computers at the moment and and actually like I don't know if you need like such a Ferrari for a lot of these workloads and we made an acquisition recently terso they've got an architecture that's um compatible with postgress and actually it's compatible with SQLite as well. I think SQLite's a phenomenal database and so we'll provide this tier which we call superbase spark which is basically for for these getting started workloads the idea won't be the same you get started with the same experience you can scale up to pabytes so our tag lines kind of prototype to pabytes and we as a company need to make sure that we can provide for everyone and if they do scale up and their business keeps growing then we make sure that they have a great time. Yeah, that's something I was curious about how you think um about this actually is like the

17:03 classic sort of software company. you start with, you know, maybe early stage startups like in a YC batch and then you sort of have one eye towards the enterprise and I feel like especially if you're a database company like preAI the convential wisdom as well like you want to be Oracle so you got to get to the enterprise as quickly as you can because that's where all the money is and so you start building out like enterprise features you sort of leaning into SQL light is sort of going the opposite direction like how do you how do you think about it like are you sort of looking both ways?

17:31 Yeah. Yeah, we're having to do both which is like incredibly difficult. Um, basically we've got two products that cater on the two ends. So multigresses scale up to pabytes and then terso scale down to like these prototyping and SQLite type workloads. So trying to do this uh at the rate of growth with like having to employ more people. It's just even with AI is becoming or has been a real challenge but a fun one. So you ran

Internal engineering adaptation and heavy automated testing

5 Highlight · Internal engineering shifts to 60% AI-generated code

17:59 a poll recently uh where people went from 10% of your engineers were writing 80% of their code with uh the coding agents and then that number recently got up to 60% in a matter of 6 months like how did that happen? What's happening? Like you know where is this going from here?

18:20 So we don't have an AI policy internally. we just let people do whatever they whatever they want and we give them access to to whatever tools they they want to use. And I think now it's just that they're convinced that the models can do so much better better work and so much more. So the adoption has been crazy and yeah the the things that they're building internally are not just viodated type stuff. They're pretty intense. Um, and as we're like shifting into this uh like AI coded realm, like just the amount of testing that we're doing and the tools that we're adopting for testing is being pretty useful to make sure that they actually know that the end result is going to be good.

19:04 Yeah, we're seeing that across YC the YC startups like uh Blacksmith Depot, Ubie Cloud, like they're all vertical because everyone's doing CI. Yeah.

19:13 And the number of tests that you have for just like three

19:16 reptile for like review.

19:18 So that's pretty wild honestly to see. Was it like a partic like it's just the models are good enough now and like you just people spend enough time where they're like oh actually this is quite good

19:26 and people need to be convinced especially uh engineers like I mean they might not

19:32 at the start of the year I've thought that it was very good and the models have gotten better but also they're starting to see oh actually you can achieve some great things with with these models and all the stuff with Navia Stokes and all these stuff like convincing the market that actually yeah we can break new ground here. So I think that's the world that we're moving

Pivoting database infrastructure to code-first for agents

19:54 towards and now people are convinced that this is the way that it's going to be.

19:58 You've seen Superbase like through three eras. First kind of like a dashboard company um built in a 100 days during YC then the API company and then now it's you know sort of this agent you know make something agents want sort of moment. Uh was there like one or two things like in each era that really jump out at you like oh that was the thing that made us in that moment?

20:22 I think like those shifts happened. So the first one actually Yeah. I think you're saying like why would a database um company exist when we came into YC? We actually

20:32 it seemed like such a contrarian idea at the time actually.

20:35 Yeah. Yeah. Yeah. I think like we saw how hard it was to use a database even for developers and so that dashboard first was like oh let's build a UI that looks like air table on top of Postgress because I actually loved air table as well. I was like wouldn't it be cool if that was just a Postgress database on the back end. So um that one was just seeing that even software engineers struggled. And then like when we moved to AI, I think we talked about this on the other podcast, the AI uh API um shift was because we had someone integrating with us and they were like, "Oh, we want to launch lots of databases. We need an API to do all of this." And that was like 2021 maybe. And it turns out that was exactly the right move for 2024 when the likes of Bolt and Lovable and all of these people started building on top of us. Then this year I just saw that actually no one's coming to the dashboard like no one no one visits dashboards anymore. So um

21:37 how are agents going to build? In this one I just kind of put out a product memo to the team that said it has to be code first get native. Superbase just has to shift to to code first. So if it exists on the dashboard, it basically has to work in lock step in code infrastructure as code essentially and we rearchitected a lot of the CLI and everything to work in sandboxes in code.

22:03 Were you guys maybe too far back but were you ever inspired by par another white company?

22:07 Yeah. Yeah. Yeah. Par and Firebase. I I liked both of those companies and it's funny these waves, right? because they did the back end and Firebase acquired by Google, pars by Meta, but in some ways I think they like blazed the trail for us to come along and actually have a legitimate database business because in 2014 it would have been ridiculous not to use RDS for your for your database. Then they came along, came along, u started moving to Atlas and a lot of these database companies kind of showed that you don't need to just use one of the three hyperscalers. You can actually have a legitimate database company and um so that that timing was crucial for us.

22:55 Yeah, past sort of forgotten that it was like actually a really well-built product. They launched like just when I was building iPhone apps for the first time and it was like quite nice to switch to like a nice restful API that I was trying to deal with.

23:07 These shifts always happen with like inflection points, right? So at that point there were two things that happened in the market. Somehow MongoDB convinced everyone that NoSQL was supposed to be like an amazing uh way to store your data. And um the second was mobile. And so, you know, we're fortunate that we had a couple of these waves as well and now we're right in the thick of it. And

23:33 yeah, I mean, this [clears throat] is what I was asking about sort of like how you think about the enterprise versus early cuz I think I mean you go even further back. This is sort of like Heroku was the first where it's like hey like just start with like the best developer experience and then scale up. But it is actually can be quite hard to like scale up with people and I think like you know Heroku sort of I don't could quite bridge that gap um to how do you keep people on you like as the apps get bigger and and need to be more performant etc etc but like historically every company's had to figure that out and like I know you guys are looking that way but you might not have to like honestly if the like the the market for just owning like I don't know call it 0 to 10 whatever like keeps expanding at this rate it's going to be huge. Yeah.

24:15 Well, we want it all. So,

24:17 so we might not have to, but uh we'll definitely do it. And like kudos to Heroku. I think they popularized Postgress, but at the time Postgress was pretty uh it was still pretty nent and it still got some scaling um limitations and so yeah, we've had to wrap Postgress

Capturing startups on day one to scale infinitely

24:37 and some tooling that will allow it to scale indefinitely. But I mean I guess a better analogy for you guys is more like AWS was able to actually like get people early and like scale and so do yeah like what are the lessons maybe like how do you think about making sure you can scale

24:52 infinitely? the lesson I think that they I heard a stat and was telling me I might get it wrong so fact check me but something like 40% of AWS's revenue comes from like startups that started on them and then scaled up and like that's the category that we want you know like we know that to convince people to migrate to from one database provider to another is near impossible and so we just want to be there on day one make sure that they have a great time and and make sure that they actually don't want to leave.

25:24 The same business model to strip. I mean, it's like basically the best business model on earth if you can get it. But you get them on day one and then like scale with like the fastest growing companies in the world infinitely

25:33 and you just do that for a generation and you become a generational business. That's pretty much it. Yeah. It's hard for us because

25:40 what does day one look like? That's rapidly shape changing. So in the past day one for me was always like why see customers and now day one is becoming like okay everyone's a builder what are they going to use what are the modalities what how are they going to choose their databases these are tricky questions next batch is now taking applications got a startup in you apply at y combinator.com/apply it's never too early and filling out the app will level up your idea okay back to the video it's kind a different customer segment like like initially when you started like there was not an individual market for databases like the idea of a database company being a direct to consumer business would have just like sounded like a syntax error.

26:26 Yes.

26:26 Um but now you actually have two segments. You have the like early stage companies that that that has this powerful stripe business model, but you're also like selling directly to consumers or to their agents perhaps.

26:38 Yes. Yes. And those use cases presumably will not scale the way startups will, but they might just like continue to use you for like for the rest of their lives because you're powering the app that like runs their personal finance software or their taxi cab company or something like that.

26:54 And as their lives grow and they accumulate information, that is basically an index of our our own growth, you know. So they just store more. People are collecting more data. this kind of proumer market is essentially a good growth vector for us. I guess do you think about the personal agent world in that through that perspective then if sort of coding agents want superbase it's very clear like do you think about the next phase as being assuming we all have personal databases like do you need to do anything to make sure that it's easy for personal agents to talk to you is that any different or is it basically the

Designing software for the era of personal agents

27:28 same thing? Yeah, I'm very bullish now on personal agents after a week of my EA being away and uh me learning exactly what they can do. And now I'm just kind of obsessed with the idea of building for personal agents. And it's true that I I said to our company like we're code first. Um like we're building for humans that are doing code first, but actually we're doing it for agents. Those humans pretty soon won't actually be interacting. So like the way I've been building is I'm using dots. Um I just sit on a phone call with it all the time and I'm chatting to it and saying oh can you make these changes and my my kind of heristic to make sure I'm building or dog fooding correctly is that I just don't look at the code and I don't allow myself ever to check the architecture except when I want to check that it's actually building things correctly. But when I'm making these changes I just want to talk to it and see what it can change. So,

28:26 one of us.

28:29 It's crazy as well. Like, it's doing some phenomenal stuff that I just it it feels like something out of a sci-fi movie from like 2 years ago, but now like I'm having so many of these moments that I'm just mind blown. If you had shown someone this 6 months ago, they would have just thought it was impossible.

28:48 Yeah. you I was at um your Subbase select conference a couple weeks ago which is awesome conference by the way and I had this like kind of crazy thought. I was sitting there and you were talking about all these awesome new features that Superbase was putting out and I was like you know if I was building an app on Superbase maybe I wouldn't even care to understand all these awesome features myself. I want to like send my agent to Superbase Select to like listen to all the awesome new features and figure out how to integrate them into my codebase. Oh, that's wild.

29:18 A truly virtual conference. We should do that. A conference just for agents.

29:22 For agents. A conference for agents.

29:24 They all turn up live.

29:26 Live. They [clears throat] can like talk to each other, exchange tips on like, you know, Facebook live.

29:31 Wow. Well, you can bridge it. You can sort of airdrop like the markdown file for everyone, but you have to be there in like the the audience to get it.

29:38 We'll call it the artifactory.

Rewriting error messages to enable agent self-remediation

29:42 Oh man, I quite like that. We talked about before this like there's just a bunch of things that you've been doing that like really make agents like you better like error messages you know you know what was that key insight and like are there a bunch of other things that you're doing that kind of obvious on the one hand on the other hand like nobody's

6 Highlight · Designing error messages for agent self-remediation

30:00 doing yet? Yeah. So like the error messages. Yeah. I was at a dev tool center last night and I was surprised that this wasn't so obvious, but we really dug into our error messages so that you can take a use case like oh I want to build an application and generally like developer error messages are like 500 um something basic and you just know there's a problem but now you actually want the agents to like remedy themselves. So inside the error messages, you are literally telling them how to fix this error or to go and read some docs to fix the error. So a lot of it is just picking your use case and just trying to do these loops on improving your own error messages so that you can oneshot basically anything that you want.

30:45 Yeah, that makes sense. Basically, you know, if you're being used by an agent, the agent will encounter an error message. In the past, a human would have to go Google that and do a bunch of stuff, but here you can just say, oh, like you're just, you know, out of nodes, so you should probably go do this.

31:02 Yeah, cuz there's like two stages to winning the agents. The first is being picked by the model, and then the second is like if they get stuck, you don't want them to switch away. So, guaranteed they'll get stuck uh at some point. You

31:16 just want to give them the tools to to remedy. So, uh, it's not actually that complicated. They're smart enough now that they can figure out a lot of stuff, but you do have to re-engineer a lot of what previously was just for humans and developers for agents.

31:31 Do you test your project, your product for agents? Like, do you have agents like try to use Superbase and then like report all the places where they had trouble?

31:39 Yeah. Yeah. Yeah. All the different models. We've got an eval um website where we see which models are building the best and we got our own eval um suite internally. We eval as well which ones are best just with Postgress. So that's interesting for the industry and build skills around it so that they can adopt them and actually develop with Postgress. So yeah, it's a lot of testing and in fact pretty much now a lot of our engineering effort is going into like testing specific use cases rather than the building. We want to think through how people are building and build suites around that.

32:16 Gary, when you built Gbrain, you built it on top of Superbase. Can you talk about like how did you decide to build it on top of Superbase? What was it like for you to be a a user? Yeah, I guess I mean Gbrain was like a distillation of a bunch of stuff I wrote like I first worked on Gary's list which was like agentic it was like an agentic newsroom and I had to build up like basically a research system for rag and for like policy and papers and it would like read every newspaper article about a given topic and then try to synthesize um and then I took that and then distilled it into uh open- source retrieval for openclaw cuz the idea was like, okay, I had it in Rails and that was kind of like a Foxcon factory for agents. It's like I treated every LLM call as very expensive and incredibly dangerous. And then when I saw OpenClaw, it was this, you know, it was kind of like Eselin. It was just like a very different way for uh you know, you to work with AI cuz then it's

33:17 like, oh, the AI is smart. uh it's not trying to hurt you and then you should just let it like do stuff and you should just give it data and capabilities. And

7 Highlight · Combining vector search and graphs for agent memory

33:26 so I recognized a million tokens is actually an incredible working memory. Like most human beings only have like seven plus or minus two things that they can keep in their head. Whereas like a million tokens is like basically uh like three Harry Potter books. But then even that is like a little bit limiting for the agents. Like keeping the correct three Harry Potter books in your context at any given time is a real challenge.

33:52 So it felt like there was this thing in between for a company brain or like my personal stuff. It's like you I have half a million markdown files on like every communication I've ever had. And so this thing really does have context on me and everything that I care about. Uh but then at any given moment like the agent it might need like two pages or something. it's a retrieval problem and so uh at that point you know at many I think it's like 30 40 gigabytes you need PG vector you need Postgress you know you can do graph databases very easily in SQL and so that's what Gbrain is it's like you know rag retrieval um plus like a a graph database that creates like structure out of unstructured data

34:39 and so it's like dynamic schemas like a little bit like what I remember uh Palanteer was back in the day.

34:45 And then, you know, the entire idea is that agents are much more powerful when um there's sort of this intermediate thing where the agent can just say like this is what I'm looking for and it'll traverse the graph. It'll do all of the uh you know uh vector search and it'll come back and say like here here's a report and like load this into context. And so that's what Gbrain is. And then Superbase was just like very straightforward. It's like I need I need hosted Postgress and I need it to be able to support like a 50 or 100 gig or 300 gigabyte you know database uh corpus really fast and uh it's been great like you know the autoscaling works really really well and now the funniest thing is like with browser use like I use a side browser now for browser use and it's like oh yeah like open clock can go into superbase and you know use the

35:34 database or the new APIs you made and it just like managed it itself it can like self-manage Were you having to prompt it to like figure out the data structures like graphs or like rag or anything like that or

35:47 uh I mean what's funny is like I I remember going into cloud code and just saying like use Exa and download and diorize uh every paper you can find in AI research. Um, today I could use like alpha signal or something, but it's like go and find every piece of research about rag and graph databases and like you know text retrieval and then summarize it for like my use case which is like how do I help an agent get access to this stuff and then after it did that it's like oh okay well here's here's how we're going to do it. Yeah, I was at a dinner the other night on like the future of databases and one idea was like databases essentially are like a retrieval mechanism for for data and you know you can put indexes so that they'll search across the data in certain format. So a graph or or rag and then one of them which was super interesting was just like putting an agent on a loop to create the perfect data structure for the search. Like if you're searching this data set this many times and it's

36:48 taking 10 seconds, then why don't you just put an agent on a loop to create a new type of index or like find the best index for returning that in less than a second.

36:58 I mean dynamic retrieval is pretty clearly going to happen the second you have really really smart codegen.

37:03 Yeah.

37:04 So I mean for now I mean I use it for open claw. So then uh I use my production instance and then the traces from that um I extracted out like a eval data set and then I have a separate um repo called Gbrain evals and it's got 40 different categories of like specific types of uh retrieval uh retrieval efficiency like cost efficiency latency and then uh the cool thing about eval is then you can just tell the agent like loop you know just auto research and loop and anything that uh improves your stats on this eval like ship it into master on by default. Yeah.

37:42 And anything that you tried that didn't work, write a markdown file that you know explains why you think it didn't work and then file it away in Gbrain evals. I use Cappy. There's a you know Cappy has this concept of uh captains which is kind of like similar to Grockbots bots. And so you can just give it a context. And so I have one that is always going that's like come up with new categories. And I have another captain that's uh always going that's like go through all the categories in evals and auto research and every single day try to find a way to improve our scores on our own internal evals

38:16 and that's just going all the time. It's a very very primitive uh version of RSI for like a particular use case but I guess if you like go up one level of abstraction you know you could do that you know not for uh my use case which is from for openclaw or something like it could just be for generically like anyone's retrieval use case like the only thing that changes is like the use case and uh the traces and the data set.

38:42 You obviously know about eval and you can improve your software because you're like wrapping this framework around it. Like do you think that in the future builders will have to actually know about these type of things or

38:54 maybe not? I mean honestly I feel like we're so early that you know I'm just messing around and you know I like doing it in open source and someone else you know I hope someone looks at that and

Unstoppable agent capabilities meet scarce product vision

39:03 says like oh I can apply that you know like we're I think we're literally coming up with the primitives on how to use this stuff right now. Yeah. I mean, I remember earlier in the year, you know, reading about Steve Yaggi's uh software factories and things like that and then not being able to totally figure it out and it's like, oh, no, no, I feel like now I've cobbled together something that works for me at least.

39:24 Yeah. Yeah. When we had Boris Turney here, um his vision of the future of coding was more like you just talk to Claude like a friend and you don't have to know about eval all this all this stuff and like Claude just like figures out how to build the thing that you have in your mind.

39:41 I've got this domain name openusd.dev dev and it's because there's actually a file format called open USD and I collect domain names and then suddenly

39:51 stripe and visa and everyone announced open USD and I was like oh I better put this domain to use now but I never had time to to use it so I was chatting to the dot and it's like developed this like developer site with the ecosystem and everything and I was just chatting to it on my computer and then like as I was winding down my day I called it on my phone like as I'm getting to bed which sounds sus but I'm I promise I'm just just coding with it and I was like saying I don't like the information architecture of how like the ecosystem links to the the use cases can you make some suggestions and it did and I said okay yeah implement them and then 20 seconds later it said ah yeah okay I've done it do you want to refresh and I refreshed the site and it was really well written and everything was linking together and it's hooked up the SEO type stuff and so I haven't done all the classic stuff that I'd have to do traditionally. I've just been chatting to it and it really felt like one of

40:52 those moments where I was I I sort of saw a glimpse of the future.

40:56 I mean you can do that because you know what you want to build.

40:59 That's the thing. Yeah. So like I obviously have a background in engineering so I kind of know how to prompt it but I'm trying to not say anything. I'm trying not to like point it towards GitHub or anything like that. And I'm trying to code like a like a normie or someone will do next year so that I know it's basically so I can dog food um Superbase and know that oh is it going to have a good time with Superbase in one year's time. Yeah, it's funny for Boris to say like, "Oh, I I just want it to do it automatically." And like certainly once it's into distribution, like literally the model has it, you know, in its weights, it can do it. But until then, it needs like some markdown or so. You just like a like not even a lot of prompting, like very small amounts of prompting, it can just do it.

41:49 I we're entering this very strange moment in society I think where like uh it sounds like RSI really is here and it's like going from like the 20% to 80% moment of like AI research is just happening um in sort of these inside these loops inside you know cloud code or codeex or wherever it is and then simultaneous to that like society doesn't really have enough people like you Paul who like know what to build and how to ask it. And so it's like unstoppable force meets immovable object right now. Like the capabilities, the models are like going parabolic and then the number of people who know how to actually have an impact on society with it is like more or less constant.

42:36 Yeah. And want to be kind of excited by it. I I think that's the other thing. I think a lot of people were getting paranoid, but I'm genuinely excited about what the future could be for a lot of people. A lot of my previous startups were focused on like blueco collar workers and like people who I was wrapping tech around a lot of people who just had to work a lot of their life you know and I the thing that I really love about superbase is that it's um like I see a lot of entrepreneurship um because of the platform and so I can see this future where actually there is going to be so much more entrepreneurship and it's actually quite a fulfilling lifestyle for a lot of people. So, I'm pretty pumped about 2027 actually. As long as we can keep this cadence up and avoid a few few crazy events, then then it should be a fun ride for a lot of people.

43:32 We're seeing this moment where vertical SAS founders actually are kind of struggling with raising series A's. uh you know when you're subscale at like you know five to 10 mil ARR even which like historically is a lot of ARR like that's like a guaranteed series A even like 9 or 12 months ago and today it's like uh I don't know people are kind of like not really into it um for vertical like horizontal and AI investments like seems like it's uh totally green light but like vertical SAS people are really struggling but it's also sort of happening right at the moment where you can get to 10 to 15 mil, you know, often 25, 30 mil, 50 mil with like 10 or 15 people. And so at that point, like you're very profitable at that point.

44:19 Yeah. Yeah. Yeah. With like if you got 15 people, 2 million AR per head and with 50% margins, you're all making a million million a year. I mean, that's an amazing outcome for for a lot of people.

44:31 Yeah. And simultaneous to that, we just do a lot of office hours with people who do like they got the brass ring and then they're bummed out that they can't raise the series A. And so, you know, many of my office hours there are just like you're probably going to look back on this as a blessing cuz you don't need the money. Like time was you had to raise like a hund00 million to get to like 30 million a year in revenue cuz you just had to hire all these people and now you don't have to do that.

44:56 Yeah. Yeah. There's a real thing in startups like the badge. I I mean it was the same for me like to get funding at the start like feel felt like you know I was achieving something great but actually you know to actually not fund raise now would in my mind be like oh that's achieving something great so like I'm a little bit envious of these companies that that are getting to that point.

45:20 Yeah. So, I don't know. I mean, it's a super changing world, but um your super basease of all the companies has really been able to ride high through every

Betting on durable categories and radical team adaptability

45:28 single wave. Um do you have any thoughts for people as they try to emulate what you've done?

45:35 One thing that helps me sleep well at night is that it's kind of the Lindy effect. Databases have been around for 50 years. I'm I think they'll be around for another 50 years. And this is one that at the end of AI no matter what I'm pretty certain they'll be databases. So apart from that whatever you will like uh you got to choose categories that are very durable and if you're going to bet your entire life which is basically what I'm doing you choose the category that you feel is worth investing in. I think the other one is like things are changing so fast. So we don't try to have all the answers as superb base, but we just try to make sure that we're always adapting the fastest. And you know, for me, I've evaluated or like watched a lot of my favorite dev tools.

46:26 um they kind of start with the developer focus and then they always move up and they become very corporate and they kind of stagnate a lot and they lose that that love. And from our point of view, at least from my point of view, companies like Stripe for example, they have this real like someone like a founder who just cares about like almost focusing on what the new ways of building are. And so if you're like building for this next wave, you just always need to be one eye on the future of what is next, which is a very short timeline now. Things are moving so fast, but um being super adaptable um and making sure you've got capacity within your team to shift very fast. That's the thing that we're that we're focusing on for the next year. are the things that you've learn maybe any specific things you've learned there

8 Highlight · Dogfooding and maintaining capacity for rapid iteration

47:18 like because you've had you know maybe had the initial vibe coding inflection point and then the opus 48 inflection point and just codegen like when the next sort of wave hopefully next like many inflection point hit for you but like are there things that you'll you'll do differently to be better prepared for it

47:34 well first of all like dog fooding is one of the most important things at least from our um perspective so I'm always trying these tools with ours to know where are the gaps there's no better feedback than you getting stuck on your own tooling. Um, and then having capacity. So we try to partner with with the the key players in the space and this ecosystem player has been really helpful because they give us feedback on what they're building so that and we try to leave some capacity within the team which is also very difficult but um so that when they have ideas we can we can give it a shot and not a lot of the bets actually win. Even when they seem like we're partnering together to do some new cool thing we actually don't know. They might sound cool and we try them out and they they they kind of flop, but the ones that do work then end up meaning that we ride this awesome wave together.

48:28 That's a great note to end on. Paul, thanks so much, man. We'll see you guys next time.