Skip to content
Y CombinatorY Combinator

Why Everyone Is About To Have Their Own Database

In this episode of the Lightcone, the hosts sit down with Paul Copplestone, co-founder and CEO of Supabase. Since starting in the YC summer batch of 2020, the company has exploded to 13 million users and over 50 million databases under management. Supabase is now positioning for a future where everyone can write their own software, billions have access to personal databases and agents are driving much of the demand. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs Chapters: 00:00 Intro 01:18 Growth and 4x Revenue 02:35 Three Eras of Supabase 04:34 “Builders” vs. Traditional Devs 08:42 Personalized Apps 12:12 Personal Databases & Data Ownership 15:56 Scaling to Billions 17:58 AI Adoption At Supabase 19:58 Lessons Learned Along The Way 27:29 Building For Personal Agents, Dogfooding 30:01 Agent-First Design and Evals 38:42 The Future Of Coding 42:36 Opening Up More Entrepreneurship + Outro

Paul CopplestoneguestGarry TanhostHarj TaggarhostJared Friedmanhost
Oct 30, 202648mWatch on YouTube ↗

EVERY SPOKEN WORD

  1. 0:00 – 1:18

    Intro

    1. PC

      I'm genuinely excited about what the future could be for a lot of people. The thing that I really love about Supabase 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 wanna 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.

    2. GT

      [upbeat music] Welcome back to another episode of The Lightcone. Today, we're joined by Paul Copplestone, co-founder and CEO of Supabase, the open source Postgres backend that's become the default database inside tools like CloudCode and Codex. Supabase now has 13 million users, and it's spinning up over a million databases a week. Paul, welcome to The Lightcone.

    3. PC

      Thanks for having me.

    4. GT

      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." [chuckles] And your company really exemplifies that. You know, something like 70% of the new activity is from agents. Isn't that crazy? [chuckles]

  2. 1:18 – 2:35

    Growth and 4x Revenue

    1. PC

      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.

    2. HT

      Just so we can understand just how much you guys have grown, 'cause it's kind of mind-boggling, um, yeah, like, what are the numbers you care about, and where were you lo- like, this time last year, and where are you now?

    3. PC

      I think this time last year, so yeah, we're 13 million signups now. Probably 12 months back we would've been around 3 perhaps. Um, this year, like, revenue will grow 4x. Um, we've got... I'm trying to think what, what was it?

    4. HT

      You've got, like, a million databases being created per week at the moment.

    5. PC

      Per week.

    6. HT

      Kind of what was it-

    7. PC

      Over a million. Yeah, yeah, yeah. I, I-

    8. HT

      What was it this time last year?

    9. PC

      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.

    10. HT

      What's been driving that?

    11. PC

      First, people are building with abandon, 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 to actually build things on top of Supabase.

  3. 2:35 – 4:34

    Three Eras of Supabase

    1. GT

      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 gonna keep choosing Supabase, but, you know, how do you get the agents to come over in the first place?

    2. PC

      Yeah, we largely have seen, like, three chapters in Supabase. 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 CLIs 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. HT

      How much do you think being open source played a role in it too? 'Cause the agents love open source things.

    4. PC

      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 source-y way. Like, we try to support existing tools. It's not just Supabase tools. We, we support, like, Postgres as a very, um, famous tool for the Postgres e- ecosystem, and we help to maintain that, so we've kind of got sprawl across many communities.

    5. GT

      I would guess that the agents actually really like open source, because when something goes wrong, it can just look at the source. [chuckles]

    6. PC

      Yeah.

    7. GT

      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.

    8. PC

      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. 4:34 – 8:42

    “Builders” vs. Traditional Devs

    1. GT

      Is developer even still sort of the, the core user that you're going after, or how, you know, how do you think about it now in 2026?

    2. PC

      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 and-

    3. GT

      That's the distinction is, like, builder as in they might not be actually software engineers.

    4. PC

      Mm-hmm.

    5. GT

      They might just be someone who needs to build a thing, and they're just, you know, popping open CloudCode, and then it turns out files only get you so far. [chuckles]

    6. PC

      Mm-hmm. 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-led growth, it's gonna 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.

    7. GT

      I mean, that was basically true, like, two years ago-

    8. PC

      Yeah

    9. GT

      ... or one year ago.

    10. PC

      Yeah.

    11. GT

      But definitely not true this year.

    12. PC

      Yeah.

    13. HT

      I was just talking to someone actually this last weekend who fits the builder category. It's like a, a fintech founder who just exited his company of, like, over a billion dollars, and, um, he's always been sort of product adjacent, like, studied math at, like, as an undergrad, and sort of like kind of could pull together some Ruby scripts, but, like, always needed 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 writing all the integrations from scratch. And it's just, like, the kind of software that would never have been built, um, even two years ago.

    14. PC

      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 wanna 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 d- 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, in YC, like the profile shifting even from, from who you're bringing into the cohort.

    15. GT

      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 a, 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 fore at YC during that time period. It was 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 [chuckles] 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-

    16. PC

      Yeah

    17. GT

      ... can you imagine all the things that never would've built exactly for what you said? 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 [laughs] to work on it.

    18. JF

      Do you have some examples, Paul, of, like, apps that

  5. 8:42 – 12:12

    Personalized Apps

    1. JF

      people have built on Supabase, maybe just for themselves, that are the kinds of things that would've never been built before?

    2. PC

      Oh, 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 f- uh, from his phone, and it's, um, kind of like a l- a little mini Uber for his local market. And I just thought, eh, he's a taxi driver himself. I don't actually know why he built it, but the fact that he could build it [laughs] 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 something. 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 Supabase. It's, like, something that 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.

    3. JF

      Harj, you've been building some of your own personal software recently.

    4. HT

      Yeah.

    5. JF

      Can you talk about what you've been cooking up?

    6. HT

      It's just grown. Yeah, it's sort of like the end of one stuff, but it's just grown out of, um, y- getting really addicted to OpenClaw. Actually, like, maybe six months ago now, embarrassed I said it, I said, like, there was gonna be no UIs, and-

    7. JF

      Mm-hmm

    8. HT

      ... it was all just gonna be, like, chat through my OpenClaw. 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. [laughs]

    9. JF

      [laughs]

    10. HT

      And 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. I know, like, I have like a UI to, like, triage all my emails, so I don't need to read my inbox. Um, finances, tracking, like, spending, health. I both, like, tracks my weights and my workouts, and everything is all in, like, one place. But I think the magic of it is, sometimes it's a mind-boggling 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.

    11. JF

      Yeah.

    12. HT

      But in some ways 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, I 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 now you can 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, is kind of awesome.

    13. PC

      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-

    14. HT

      Yeah

    15. PC

      ... data.

    16. HT

      Yeah.

    17. PC

      So we see a, a lot of people doing that and syncing all the devices-

    18. HT

      Yeah

    19. PC

      ... to, to a single database is kind of a-

    20. HT

      Yeah

    21. PC

      ... a magic skill. Then you can, like, prompt it to, like, build these correlations across all the-

    22. HT

      It's the correlations that are really va- like, again, like if you just take the health example, it's like, yeah, all of that data is in, like, my Supabase 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-

    23. PC

      Yeah

    24. HT

      ... you can just, like, get back on track-

    25. PC

      Yeah

    26. HT

      ... um, next week, and it just has, like, this context that's really valuable.

    27. PC

      I also found that as I started to use the

  6. 12:12 – 15:56

    Personal Databases & Data Ownership

    1. PC

      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 wanna attach different agents on top, then I know that, like, I can use any, any agent. So the CRM is another really critical one.

    2. HT

      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 or to the, the, the database is actually the thing that's valuable. Like you don't, you want to own your own database-

    3. PC

      Yeah

    4. HT

      ... and then build all the applications or agents on top of it, versus having that all in like someone else's database.

    5. PC

      Mm-hmm.

    6. JF

      Which is a totally wild idea. Like if you just think about the history of databases, it 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 Supabase got started, you kind of had this idea that they should be like e- really easy for everyone to like make a database, and it almost like didn't make sense at the time why [laughs] so many people would wanna do that, 'cause unless you can write code, what can you do with a database? And there's n- 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 pre-AI.

    7. HT

      Like another example actually like where Supa is really valuable for me is like the other section I have is just like a file upload. It 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 Supabase. And so yeah, in general it's just like Supabase is actually gonna end up having like all of the like data about my life in a single place, and like I'm, I would never, I would never have thought about wanting a personal database like a year ago, 'cause it wouldn't have made any sense, but now I'd like, that's actually like the most valuable thing.

    8. GT

      Yeah, you have like an S3 compatible Supabase files thing and-

    9. HT

      Yeah, exactly

    10. GT

      ... all my stuff is in that.

    11. HT

      Oh, really?

    12. GT

      Mm-hmm.

    13. HT

      Nice.

    14. GT

      Yeah.

    15. HT

      Yeah, yeah.

    16. GT

      It's default in GBrain. [laughs]

    17. HT

      [laughs]

    18. PC

      [laughs] Great. Thank you.

    19. JF

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

    20. PC

      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 wanna 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 on- we had to be there on day one when businesses were getting started. The mission didn't change, just the aperture has like 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.

    21. JF

      Significantly meaning like 10 million X.

    22. PC

      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 ChatGPT, 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 billion databases a month. And so that's like the scale that we're moving towards, architectures that 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

  7. 15:56 – 17:58

    Scaling to Billions

    1. PC

      realm.

    2. JF

      Can you even do that with Postgres, or are you gonna have to build your own database engine to scale to 1 billion new databases per week?

    3. PC

      I think, yeah. Well, if we could negotiate better with AWS, then maybe we could.

    4. JF

      [laughs]

    5. PC

      But it turns out that, uh, everyone wants computers at the moment.

    6. JF

      [laughs]

    7. PC

      And, and actually I like, I don't know if you need like such a Ferrari for a lot of these workloads, and we made an acquisition recently, Turso. They've got a, a architecture that's, um, compatible with Postgres, and actually it's, uh, compatible with SQLite as well. I think SQLite's a phenomenal database. And so we'll provide this tier, which we call Supabase Spark, which is basically for, for these getting started workloads. The idea will be the same. You get started with the same experience. You can scale up to petabytes, so our tagline's kind of prototype to peta- petabytes. 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.

    8. HT

      Yeah, that's something I was curious about how you think, um, about this actually, is like the 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 pre-AI, the conventional wisdom was, well, like you wanna be Oracle, so you gotta 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 SQLite 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 or-

    9. PC

      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 Multi-Gres is scale up to petabytes, and then Turso is scale down to like these prototype 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.

  8. 17:58 – 19:58

    AI Adoption At Supabase

    1. GT

      So you ran 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 six months. Like how did that happen? What's happening? Like, you know, where's this going from here?

    2. PC

      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 five-coded 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 has been pretty useful to make sure that they actually know that the end result is gonna be good.

    3. GT

      Yeah, we're seeing that across YC, the YC startups like, uh, Blacksmith, Depot, UbiCloud, like, they're all vertical 'cause everyone's doing CI-

    4. PC

      Yeah

    5. GT

      ... and the number of tests that you have are just, like, through the roof.

    6. PC

      Like Reptile for-

    7. GT

      Yeah

    8. PC

      ... like review.

    9. GT

      So that's pretty wild, honestly, to see. Was it like a part- Like, it's just the models are good enough now, and-

    10. PC

      Yeah

    11. GT

      ... like, it's just people spend enough time where they're like, "Oh, actually, this is quite good."

    12. PC

      And people need to be convinced, especially, uh, engineers. Like, I mean, they might not... At the start of the year have 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 Navier-Stokes and all these stuff are, like, convincing the market that actually, yeah, we can break new ground here. So I think that's the world that we're moving towards, and now people are convinced that this is the way that it's going to be.

  9. 19:58 – 27:29

    Lessons Learned Along The Way

    1. GT

      You've seen Supabase, like, through three eras. First, kind of like a dashboard company, um, built in 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 jumped out at you as like, "Oh, that was the thing that made us in that moment"?

    2. PC

      I think, like, those shifts happened... So the first one, actually, yeah, I think you were saying, like, why would a database, um, company exist when we came into YC. We actually-

    3. GT

      It seemed like such a contrarian idea at the time, actually.

    4. PC

      Yeah.

    5. GT

      Yeah.

    6. PC

      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 Airtable on top of Postgres, because I actually loved Airtable as well. I was like, "Wouldn't it be cool if that was just a Postgres 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-

    7. GT

      [laughs]

    8. PC

      No one visits dashboards anymore. So, um, how are agents gonna build? In this one, I just kind of put out a product memo to the team that said, "It has to be code first, Git native." Supabase just has to shift to, to code first. So if it exists on the dashboard, it basically has to work in lockstep in code, infrastructure as code, uh, essentially, and we've re-architected a lot of the CLI and everything to work i-in sandboxes in code.

    9. HT

      Were you guys, this may be too far back, but were you ever inspired by Parse, another YC company?

    10. PC

      Yeah, yeah, yeah. Parse 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 and Parse 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've been ridiculous not to use RDS for your, for your database. Then they came along, Mongo came along. Uh, Mongo 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.

    11. HT

      Yeah, Parse is sort of forgotten now, but 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-

    12. PC

      Yeah

    13. HT

      ... that I was trying to deal with.

    14. PC

      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-

    15. HT

      Yeah

    16. PC

      ... 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-

    17. HT

      Yeah, I mean, this is what I was asking about, sort of like how you think about the enterprise versus early, 'cause I think, I mean, if you go even further back, this is sort of like Heroku was the, the first, where it's like, hey, like just start with, like, the best developer experience and then scale up.

    18. PC

      Yeah.

    19. HT

      But it, 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 think could quite bridge that gap, um, to how do you keep people on you, like, as the apps get bigger and-

    20. PC

      Mm-hmm

    21. HT

      ... and need to be more performant, et cetera, et cetera. But like historically, every company's had to figure that out.

    22. PC

      Mm-hmm.

    23. HT

      And, like, I know you guys are looking that way, but you might not have to. Like honestly, if the, the, 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 gonna be huge.

    24. PC

      Yeah. Well, we want it all.

    25. HT

      Yeah, yeah. [laughs]

    26. PC

      [laughs] So, uh, we might not have to, but, uh, we'll definitely do it. And, like, kudos to Heroku. I think they popularized Postgres, but at the time, Postgres was pretty... Uh, it was still pretty nascent, and it's still got some scaling, um, limitations. And so, yeah, we've had to wrap Postgres in some tooling that will allow it to scale indefinitely, but-

    27. HT

      I mean, I guess a better analogy for you guys is more like AWS was able to actually, like, get people early and they can scale.

    28. PC

      And scale, yeah.

    29. HT

      And so do, do... Yeah, like, what are the lessons maybe? Like, how, how do you think about making sure you can scale infinitely?

    30. PC

      The, the lesson, I think that they... I heard a stat, and was telling me, um, 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. [laughs]

  10. 27:29 – 30:01

    Building For Personal Agents, Dogfooding

    1. PC

      Yeah. I'm very bullish now on personal agents after a week of my EA being away-

    2. HT

      [laughs]

    3. PC

      ... 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, 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 heuristic to make sure I'm building or dogfooding 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 wanna check that it's actually building things correctly. But when I'm making these changes, I just wanna talk to it and see what it can change. So it's-

    4. HT

      One of us, one of us.

    5. PC

      Yeah. [laughs]

    6. HT

      [laughs]

    7. PC

      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, two 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 six months ago, they would've just thought it was impossible.

    8. JF

      Yeah. You... I was at, um, your Supabase Select conference-

    9. PC

      Oh, yeah

    10. JF

      ... a couple weeks ago, which was an 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 Supabase was putting out, and I was like, "You know, if I was building an app on Supabase, maybe I wouldn't even care to understand all these awesome features myself. I wanna, like, send my agent to Supabase Select to, like, l- listen to all the awesome new features-

    11. PC

      Yeah

    12. JF

      ... and figure out how to integrate them into my code base." [laughs]

    13. PC

      Oh, that's wild. A truly virtual conference.

    14. JF

      [laughs]

    15. PC

      We should do that, a conference just for agents.

    16. JF

      For agents.

    17. PC

      Yeah. [laughs]

    18. JF

      A conference for agents.

    19. PC

      They all turn up live.

    20. JF

      Live. They can, like, talk to each other, exchange tips on, like, you know-

    21. GT

      Oh, live. Wow.

    22. PC

      Well, you can bridge it. You can sort of airdrop M- like, the markdown files for everyone-

    23. JF

      [laughs]

    24. PC

      ... but you have to be there in, like, the, the audience to get it.

    25. GT

      We'll call it the Artifactory.

    26. PC

      Yeah. [laughs]

    27. HT

      [laughs]

    28. JF

      [laughs]

    29. PC

      Oh, man, I quite like that.

    30. GT

      We talked about before this, like, there are just a bunch of things that you've been doing that, like, really make agents like you better, like error messages, you know? What... 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 doing yet?

  11. 30:01 – 38:42

    Agent-First Design and Evals

    1. PC

      Yeah. So, like, the error messages, yeah, I was at a dev tools dinner 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 tool 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, uh, 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 one-shot basically anything that you want.

    2. JF

      Yeah, that makes sense. Basically, you know, if you're being used by an agent, the agent will encounter a, a 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 inodes, so you should probably go do this.

    3. PC

      Yeah, 'cause 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 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.

    4. JF

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

    5. PC

      Yeah. Yeah. Yeah. All the different models. We've got an evals, um, website where we see which models are building the best, and we've got our own eval, um, suite internally. We eval as well which ones are best just with Postgres, so that's interesting for the industry, and build skills around it so that they can adopt them and actually develop with Postgres. So yeah, it, 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 wanna think through how people are building and build suites around that.

    6. JF

      Kerry, when you built Gbrain, you built it on top of Supabase.

    7. GT

      Oh, yeah.

    8. JF

      Can you talk about, like, how did you decide to build it on top of Supabase? Well, how is it like for you to be a-

    9. GT

      Yeah

    10. JF

      ... a, a user?

    11. GT

      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 this, 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, 'cause the idea was like, okay, I had it in rails, and that was kinda like a Foxconn 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 v- you know, it was kind of like Esalen. It was just, like, a very different way for, uh, you know, you to work with AI. 'Cause then it's like, oh, the AI's 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 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-

    12. JF

      Yeah

    13. GT

      ... 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. So it felt like there was this thing in between. For a company brain or, like, my personal stuff, it's like y- 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, it's a retrieval problem. And so, uh, at that point, you know, at m- many, I think it's, like, th- 30, 40 gigabytes, you need pgvector, you need Postgres. 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.

    14. JF

      Oh.

    15. GT

      And so it's, like, dynamic schemas. Like, a little bit like what I remember, uh, Palantir was back in the day.

    16. JF

      Yeah.

    17. GT

      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 Supabase was just, like, very straightforward. It's like, I need, I need hosted Postgres, and I need it to be able to support, like, a 50 or 100 gig or 300 gigabyte, you know, database, uh, corpus-

    18. JF

      Yeah

    19. GT

      ... really fast. And, uh, it's been great. Like, you know, the auto-scaling works really, really well, and now the funniest thing is, like, with browser use, like, I use, uh, a side browser now for browser use, and it's like, oh yeah, like, OpenClaw can go into Supabase and, you know, use the database or the new APIs you made.

    20. JF

      Oh.

    21. GT

      And it just, like, managed it itself. It can, like, self-manage.

    22. PC

      Were you having to prompt it to, like, figure out the data structures, like graphs or, like, Rag or anything like that or...?

    23. GT

      Uh, I mean, what's funny is, like, I, I remember going into Claude Code and just saying, like, "Use EXA and download ev- download and diarize, uh, every paper you can find in AI research." Um, today I could use, like, AlphaSignal or something.

    24. PC

      Yeah.

    25. GT

      But it's like, go and find every piece of research about Rag-

    26. PC

      Yeah

    27. GT

      ... 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 what w- here's how we're gonna do it.

    28. PC

      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-

    29. GT

      Oh, yeah

    30. PC

      ... for, for data. And, you know, you can put indexes so that they'll search across the data in certain formats, 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-

  12. 38:42 – 42:36

    The Future Of Coding

    1. PC

      You obviously know about evals, 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 like-

    2. GT

      Maybe not. I mean, honestly, I feel like we're so early that, you know, I'm just messing around-

    3. PC

      Yeah

    4. GT

      ... and, you know, I like doing it in open source, and someone el- You know, I hope someone looks at that and says, like, "Oh, I can apply that," you know?

    5. PC

      Yeah.

    6. GT

      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 Yegge's, uh, software factories and things like that, and then not being able to totally figure it out, and it's like, I don't know. I feel like now I've cobbled together something that works for me at least. [chuckles]

    7. PC

      Yeah.

    8. JF

      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 evals and all, all this, all this stuff, and, like, Claude just, like, figures out how to build the thing that you have in your mind.

    9. PC

      I've got this domain name, openusd.dev, and it's because there's actually a file format called OpenUSD, and I collect domain names, and then suddenly Stripe and Visa and everyone-

    10. GT

      Yeah

    11. PC

      ... announced OpenUSD, and I was like, "Oh, I better put this domain to use now." But I'd 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, 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-

    12. GT

      [laughs]

    13. PC

      I promise I'm just-

    14. GT

      Just checking in

    15. PC

      ... 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, "Oh, 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 those moments where I was... I, I sort of saw a glimpse of the future.

    16. GT

      I mean, you can do that because you know what you want to build.

    17. PC

      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 dogfood, um, Supabase and know that, oh, is it going to have a good time with Supabase in one year's time?

    18. GT

      Yeah, it's inter- 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 something. [chuckles] You just... Like, a lit- Like, not even a lot of prompting. Like, very small amounts of prompting. It can just do it. I, uh, 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 Codex or wherever it is. And then simultaneous to that, like, society doesn't really have enough people like you, Paul, [chuckles] 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.

  13. 42:36 – 48:45

    Opening Up More Entrepreneurship + Outro

    1. GT

      [chuckles]

    2. PC

      Yeah, and want to be kind of excited by it. I, I think that's the other thing. I, I think a lot of people are 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, blue-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 Supabase 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.

    3. GT

      We're seeing this moment where vertical SaaS founders actually are kind of struggling with raising Series A's. Uh, sh- you know, when you're subscale at like, you know, 5 to 10 mil ARR even, which, like, historically is a lot of ARR.

    4. PC

      Yeah.

    5. GT

      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 SaaS 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.

    6. PC

      Yeah, yeah, yeah. With, like, if you've got 15 people, 2 million ARR 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.

    7. GT

      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 a Series A. And so, you know, uh, many of my office hours there are just like, "You're probably gonna look back on this as a blessing-

    8. PC

      Yeah

    9. GT

      ... 'cause you don't need the money." Like, time was you had to raise like $100 million to get to, like, 30 million a year in revenue 'cause you just had to hire all these people, and now you don't have to do that.

    10. PC

      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. [laughs] But actually, n- you know, to actually not fundraise now would, in my mind, be like, "Oh, that's achieving something great." [laughs]

    11. GT

      [laughs]

    12. PC

      So, like, I'm a little bit envious of these companies that, that are getting to that point.

    13. GT

      Yeah. So I don't know. I mean, we're- it's a super changing world, but, um, you know, Supabase of all the companies has really been able to ride high through every single wave. Um, do you have any thoughts for people as they try to emulate what you've done?

    14. PC

      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. Um, 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 there'll be databases. So parse from that whatever you will. Like, uh, you gotta choose categories that are very durable, and if you're going to bet your entire life, which is basically what I, 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 Supabase, 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. 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, a founder who just cares about just, 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 t- 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.

    15. HT

      I think that you've... Like, maybe it's any specific things you've learned there. Like, y- 'cause you've had, you know, maybe you 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, are there things that you'll, you'll do differently to be better prepared for it?

    16. PC

      Well, first of all, like, dogfooding is one of the most important things, at least from our, um, perspective. So I'm always trying these tools with ours to know, oh, 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 play 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.

    17. GT

      That's a great note to end on. Paul, thanks so much, man. We'll see you guys next time. [outro music]

Episode duration: 48:45

Install uListen for AI-powered chat & search across the full episode — Get Full Transcript

Transcript of episode vl7HiMdGfjo

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.

iOSAndroidClaudeChromeChatGPTComing soon