The creator of Clawd: "I ship code I don't read"

What if you could merge 600 commits on a single day and none of it was slop? This is what today's guest, Peter Steinberger, the creator of cloudbot, claims he's doing. Peter is a standout developer who built PSPDFKit, the PDF framework used on more than 1 billion devices. Then he burned out, sold his shares and disappeared from tech for three years. This year he came back, and how he builds and what he's doing now looks nothing like traditional software development. In today's episode, we cover why he no longer reads most of the code he ships and why that's not as crazy as it sounds. How he's building cloudbot, his wildly popular personal assistant project, which feels like the future of Siri, the closing the loop principle that separates effective AI assistant coding from frustrating vibe coding. Why he says code reviews are dead and PR should be called prompt requests and many more. If you're interested in how the software engine workflow could change in the coming years, thanks to AI, this episode is for you. This episode is presented by statsig, the unified platform for flags, analytics, experiments and more. Check out the show notes to learn more about them. The pragmatic summit on 11 February in San Francisco that I'm hosting with them and our other season sponsors. Right, Pete, welcome to the podcast.

0:00

Thanks for having me, Gage.

1:06

It is awesome to meet you in person. Yeah.

1:08

And I almost messed it up. Yeah.

1:12

What happened? You lost track of time. Does that happen often? And how.

1:15

So not usually. Not usually. This is an interesting time for me because my latest project is blowing up.

1:19

Claude, right?

1:28

Cloudbot. Yeah, cloudbot. I'm struggling a bit to get enough sleep, but it's interesting. I never had a community blowing up so fast and it's just incredibly fun to work with.

1:29

So before we get into Cloudbot and all the fun stuff you're doing, I want to rewind all the way back. You create a PSPDF kit, which is used, I think, on more than 1 billion devices users. If you see a PDF render, you probably see that. But even before that, how did you get into tech?

1:39

Oh my God. How did you get into tech? So I'm from rural Austria, always more being the introvert. So eventually we always had summer guests and one of them was a computer nerd. And then I kind of got hooked with the machine he had and begged my mom to buy me one. And ever since then I.

1:59

This was in high school or so.

2:23

I guess I was 14.

2:25

Yeah.

2:27

And ever since I started tinkering, like I can remember the earliest Thing was, like, I stole an old DOS game from my school and then wrote a copy protection for the floppy disk so I could sell. Took like two minutes to load. I was just always thinking, also playing a lot of computer games, of course, but like, building stuff almost feels like playing a computer game. Definitely right now it feels better than Factorio. When I started out, I read the equivalent of bash scripts for Windows and then I did websites. So I guess a little bit of JavaScript, even though I had no clue what I was doing. And then the actual first language where I had to learn how to build things is when I started university and I never met my dad and I come from a poorer family, so I always had to work. I had to finance my own studies, right? So when other people were having holiday, I just worked full time at a company. So the first real job I had was in Vienna. It was supposed to be one month, and then they kept me for six months. It was just a bridge between military and my university. And I kept working there for like, I think five years. And I remember the first day they gave me this huge book, maybe that huge, and says, Microsoft mfc. I still have nightmares. And I was like, this is terrible. For the next win, I just silently used Net. I just didn't tell them. And a few months in I just told them, yeah, but the tech stack. I did a few modernizations, but then it was too late. I did this a few times in this company. I don't know why they kept me. No, because it's because my shit worked. So I did Net and actually, I actually dig it. Net 2.0 had generics. It took insanely long for the application to launch because everything was compiled at first start and your hard disk was like, if you remember.

2:27

So how did you stumble into both iOS and where did the idea from PSPDF so come from?

4:33

Not even. Yeah, the first one. The first one wasn't even available in Austria.

4:39

In Austria, Yeah.

4:43

A little time went on and I was at university and a friend showed me the iPhone and I think I touched it for a minute and then I immediately bought one like this. It clicked when I felt it. And to me, this was like a holy F moment because it was just like so different and so much better. So I got one. I was still not thinking about building for it. You know what, when was this?

4:44

2009, 10? Something like that.

5:14

Yeah, yeah. And then I used their browser. I can say the story. I was literally driving in the subway and by the time I was using a gay dating App. And this was iPhoneOS 2.

5:16

A long time ago.

5:30

I typed this long message, I pressed send, and we were just going into a tunnel. And the JavaScript disabled the send button. And then an error message came, but there was no copy paste, there was no screenshot. So it was just like. And I couldn't scroll anymore because scrolling was disabled. So this long message, which was a little bit emotional, was gone. And I was so mad. I was so mad, I'm like, what the hell? I went home and I downloaded xcode. That's where. That's where the window came. And I was like, where is the ide? So I was like, this is unacceptable. I basically hacked the website. I used regular expressions to download to parse the HTML, which is totally not something you should do. And I built an app and I used iPhone OS 3 beta with core data in Beta Regex Kit Lite. I used a hacked version of GCC that backported the blocks compiler so I could use blocks in iPhone OS 3. It took me quite a while until anything worked because I had no idea what I was doing and I was using all kind of beta tech. But eventually I got it to work and I wrote that company. It's like, hey, I'm making an app. What do you think about it? Got no response, of course.

5:31

So I was like, let's just put.

6:43

It in the app store.

6:45

And this was for the dating app, right?

6:46

Yeah.

6:48

So you just like, you know, you saw their APIs, you could just easily build a client on top.

6:48

The API was HTML. Oh, I was just literally parsing HTML.

6:53

Oh, so you kind of parsing HTML, kind of turn it into your own, you know, like, use it as an API. Clever. I mean, this was back in the day where no one thought this would happen.

6:57

But I made. I put it in the app store, I charged 5 bucks for it, and I made like 10k in the first month. And I had no clue what I was doing. And there was like so many complex tech stuff. This was very early on where there was a lot of weird forums on Apple. So I just put in the bank account of my grandpa. And then one day my grandpa called me. Yeah, something is weird. Like, I got this huge payment from Apple. I'm like, this is mine, this is mine. Don't touch it. But the funny thing was, this blew off. And I remember I was in a club one day and I saw someone using my app and I was so proud. And I wanted to tap him on the shoulder and say, I built this. And I thought, really weird. So I didn't. And then I went to the company I worked for five years and told him, I'm going to pursue this. This is really exciting. And my boss was like mocking me.

7:07

Oh, really?

8:00

Like, oh, you're making a mistake. This is a fad. This will not go blah, blah, blah, blah, blah. And you know what that got me? That's what you call a new as a chip on your shoulder. I'm like, you know, one day I'm going to have a company that's worth more money than yours. Why? It took me eight years. So I, I got hooked. I'm a little bit of an addictive personality, which you see again right now. But I worked a lot on this app. I learned in high speed. And this was also the time where I started Twitter. And that was usually hugely influential for my career. I made this app actually quite good. And then one day I was at a party at 3am Slightly intoxicated, and I got a call from a U.S. number. The guy on the phone was like, yeah, hello, this is John from Apple. Yeah, there's a problem with your application. Like some people reported pictures and that was it. That was the end of my app.

8:01

It was good until it lasted.

9:02

And I was just, I just quit my job and was like, well, F U Apple. I did freelance work. I was at ww. I was introduced to WW being wwdc. Yes, sorry for the insider terms. I was introduced to someone as one of the best iOS developers in Austria at a bar at 2am in San Francisco and then basically got a job in the US and then I moved to the US for a while and then I went to the Nokia development days. This is all like stone age by now. Oh my God. And then someone came up to me and said, yeah, they built this app somewhere in Eastern Europe and it works, but it crashes sometimes. And it was like a magazine viewer. This was back when the iPad just came out and Steve Jobs said that this is the savior. So everybody was building magazine apps and I was like, that sounds like an interesting short term gig. And I was like, okay, I'll. I'll help you out. And I opened the app and it was like, oh, the worst code of iOS that I've ever seen in my life. It was literally one file with like thousands of lines.

9:03

Our Objective C. Yes.

10:16

Where they used Windows as tabs. I didn't even know this worked. I was surprised this worked at all. But it felt like a house of cards. And I tried to surgically fix things, but as soon as you Touch something, something else would break. So I got it somewhat stabilized and told him, look, this is madness. I'm going to rewrite this for you. Yeah, but it took half a year. I'm going to do it in a month. Well, it took me two months. I wasn't that far off. And then here I was working on a PDF viewer. On every technical problem the domain is, I wouldn't say completely unimportant, but you can always find interesting problems in every domain. And there was a lot of interesting problems because you had a C call that would render a PDF that would maybe take 30 megabytes, but the whole system had 64 megabytes. So if you're not very smart and very careful what you do in the background and when the OS would just kill you, I got really fixated at making it good. When rotation is. The page would animate. I like those details. I spent way too much time on that. That's why it took two months instead of one. But the end result was, it's good. And then I worked with them for a while, and then a friend texted me up and was like, yeah, I'm working on this magazine app and it's really hard. I'm like, no way. It's hard. I know. I did it.

10:18

You just built one.

11:43

And he was like, can you get me the code? I'm like, sure. So I sold him. I extracted the part that was PDF from this magazine app and I made sure the other person was okay. And then I sold him that. I was like, well, if he's interested in that, why let's not try to sell it to other people. I used a WordPress template and mutilated it to run on GitHub pages. And then when you did the fastlink flow at the end, you got a Dropbox link to my personal Dropbox with a source code sip. And I put this on one afternoon and I tweeted it. And then in that week, three people bought it. It was like, I guess 200 bucks. But back then, and for me, this was, like, amazing. And not only I got, like, three people who just bought it and like, 10 emails, 10 people who complained about it because they wanted it, but it didn't have the features they wanted. You know, it was like I got nerd sniped. I was like, oh, I didn't have text selection. Oh, how hard can it be three months later? Oh, yeah, it's really hard.

11:44

Text selection and a PDF, specifically.

12:50

Yeah, yeah, yeah, yeah. You know the saying. They're saying, like, the companies are built by young people because they don't know how hard it is. Yeah, yeah, I had no idea what an insane madness this file format is.

12:52

Peter was talking about how some problems look deceptively simple. PDF rendering is a good example. You look at it and think how hard could it be? And then you spend months on edge cases that you didn't even know existed. This looks easy until you build a pattern shows up in other places too. Internal tooling for feature flags and experimentation is a classic example. Teams often underestimate how much work it is to build the infrastructure around these tools. There's a reason big tech companies like Uber invested years into building internal experimentation and feature flagging systems. Which brings me to Static, our presenting partner for the season. Static gives you the complete toolkit without building it yourself. You get feature flags, experimentation and product analytics all in one platform, tied to the same underlying user assignments and data. In practice, it looks like this. You roll out a change to 1% of users first. You see how it moves the top pipeline, metrics you care about, conversion, retention, whatever is relevant for the release. If something goes wrong, instant rollback. If it's working, you can confidently scale it up. Companies like Notion went from single digit experiments per quarter to over 300 experiments. With Statsig, they shipped over 600 features behind feature flags, moving fast while protecting against metrics regression. Microsoft, Atlassian and Brex used statsig for the same reason. It's the infrastructure that enables both speed and reliability at scale. Static has a generous free tier to get started and pro pricing for teams starts at $150 per month. To learn more and get a 30 day enterprise trial, go to statsic.compragmatic and now let's get back to Peter and why rendering PDFs was a surprisingly hard problem.

13:04

But now I remember there was a few weeks ago someone emailed me, they did something PDF and they wanted my help and I just wrote them like, I'm sorry, like I did my deed. I know more about PDF than any any sane human person ever should know. And I went to therapy. Good luck. But that took off and I just. While I was waiting for my visa, I worked on this project and it just kept on. More people kept on buying it and it was like summer. I was lying at the lake and got another email that someone bought it for 600 bucks, 800 bucks or just up the price as it had more features. And by the time I went to San Francisco to work at this company, it already made more than what I made there. But my Whole life was. I still thought, like, I have to be there, you know, So I did it. And also, interestingly, at this company, I had to.

14:36

So when you say that you moved to San Francisco.

15:31

Yeah. And of course also it ended up being something where I had to build something with my framework at that company too. But, you know, startups are not like eight hours. They're a little more. And my personal project was also a little more, so my sleep was a little less. And then eventually, after three months, Sabine, my manager, came over and said this, Peter, are you okay? And they gave me a choice to either keep working at this company and drop my project or vice versa. And I had one week to decide. The counter was one week to stay there or leave the country because I was on a complicated visa. And a decision was quite easy. It's like, yeah, I want to do my own thing.

15:33

And at this point, it was already taking off. You already saw that there's a big business here. It will probably pay you as much as your US job would have paid.

16:21

It was never money driven.

16:31

It was more about. What were you driven by?

16:33

I want to make stuff that other people find amazing. I love tweaking the details. I love those little delights. It wasn't even that the space. There were competitors in that space. But my angle was always, like, I built something as if Apple would have built it with all the love and care and polish and those little delights that a lot of people in the industry don't get. So even though we had competitors that had way more features and were around way longer, my company was more successful. My product was more successful because developers tried the different ones, and mine just felt the best. I think soft is all about how it feels much more so than the feature set. Like, why did we buy Apple stuff? It has more features than Windows, but it's. It feels better.

16:35

So how did you go from, like, you. You left this company and you were building this PDF component that started to sell. At what point did you hire the first person realizing, okay, there's something more to this?

17:28

When I went back to Vienna, then I was like, okay, I have to go all in. And that's where I started working with freelancers a little bit and way too late, to be honest. Also, like, I could have. Could have hired much earlier, but, you know, you know, it's. It's a big step and that's kind of where it started having a life of its own. And I spent pretty much 13 years of my career building this product with this weird name. That I never changed because it took me like, I thought like five minutes about it, but then it's video Kit finally. They finally did a rename, but I wouldn't have. I wouldn't have renamed it, but now.

17:42

It'S a mouthful, but it's very unique.

18:19

Well, you get it if you do Objective C because it's just a namespace.

18:22

Yes.

18:25

And by the time it made perfect sense, my strategy for marketing was always I only care about the developer. I know upper management does the decisions, but if I can convince the people inside the company, they'll do the marketing and lobbying for me. That worked really well. We never did cold emails or aggressive. It was all inbound. All we did was make good stuff and write insightful technical blog posts. And I went to a lot of conferences. For me, important. It was okay if people understand that the people who built this product know what they do and love what they do, that reflects on the product. And that worked really well.

18:26

And then what was the tech stack behind PSPDFKit? Was it objective C? Was it later Swift? Were there other technologies like C or anything else?

19:13

We eventually being expanded to all the platforms. Big Shift was to switch out Apple's renderer, which was NES still quite buggy to like a big C1. That one then we used across all the frameworks. We were really early with web. We were one of the first PDF frameworks that ran in WebAssembly. And I did the most clever thing that I did was the very early days when webassembly was just taking off and we built a benchmark. And that benchmark was eventually used by Google and Microsoft and Apple. And I basically had all these companies working really hard on making my renderer faster because they used their benchmark as one of their benchmarks and the benchmark was just rendering our stuff with our shit.

19:20

Nice. And then as the company grew, one thing that I remember about PSPDFkit, you did write a lot of blogs and one blog in 2019. So this was about, I think year 9 or 10 in the company. It was about how the team worked. And you mentioned things there like every feature starts with a proposal. You mentioned that you are conservative because it's a big API that people use. You want to be careful. Things like the Boy Scout rules to refactor. How did you kind of put together the culture of this team, which was now closer to 30 or 60 people.

20:04

You were actually 70 when I sold my shares and now it's almost 200. And I knew right from the get go. I'M not going to find the people that I need in Vienna. So it was always just like remote first. And eventually we landed up with some kind of hybrid model which made things a bit more complicated. I learned a whole lot on the go. I never had the urge to be CEO. I always was coding. I brought people in to people that helped me a lot with other parts. And on the business side I can do it and I think I'm quite good at it, but just don't enjoy it. Like being on sales calls where you have to think about a magic number, how much it would be worth, because that's how enterprise works. Worse.

20:38

Peter just said the worst about enterprise sales. Because selling to large companies enterprises is as tricky as it gets. Not just because you need to get pricing right, but because of all the enterprise features that you need to build. And this leads us nicely to our seasoned sponsor, WorkOS. If you're building with AI agents or automation tools, here's a problem most teams don't think about at first. Once an agent can take actions on your behalf, you need to control what it's allowed to do. And traditional AUTH just wasn't designed for that. That's why WorkOS introduced MCP Auth, which gives teams a way to authenticate AI agents with explicit permissions. Auth Disability and Enterprise grade security. Instead of sharing overscoped API keys, you can define clear boundaries for the data that agents can access and the agents can perform. If you're building AI powered features and want to shift fast without compromising security, check out workerwas.com MCP and with this let's get back to Peter and enterprise pricing.

21:27

But that's also the only thing that really works on a model like this.

22:22

Yeah, you mean enterprise sales specifically. Right, Meaning custom pricing. So can you tell us for devs listening who go to a vendor's website and they're frustrated that there's no price. It says call us or schedule a meeting. Why that is?

22:25

Oh, that's right, because we gonna look at your company and then just take the dice and think about a number that you're probably willing to pay and that sounds horrible, but also when you have a product where you can't really tier it down to a specific number, like it makes a difference if a freelancer contacts us or one of the big Fortune 5000, let's not say names because the usage will be different, the value they get out of it will be different, and charging the same, you would either exclude one or the other. If I go too low, they're gonna see this fishy. It's like procurement for like 500 bucks. We're not gonna even start the process. And if we target it too high, we are gonna lose those people. So as horrible and unfair this process seems for some kinds of products, it is the, it's the most fair way. After all. You know, on software, I would say there's like four X's there's like easy and hard and interesting and not interesting. We were very much in the not interesting and hard part. If you build something that every developer wants to build, it's going to be a hard sell. It's a hard sell anyhow. Selling anything to developers is a hard sell. But if it's too easy or too interesting, good luck. But if it's, oh God, I don't want to do this and oh my God, this is hard, that's a good spot to be in. So I found a really interesting niche and there were just an infinite number of complex problems.

22:40

You need to tell me, tell me one or two hard things about parsing PDF. How hard could it be if there's a specification? I'm an engineer, I know specifications. What's so hard about it?

24:10

I mean, there was just one example where, you know, like PDF has links. So like there's like a table of contents and you click on it and it goes to like page 37. So I built this whole model with assumption, oh yeah, maybe there's like a hundred or a few hundred links in there. And then we got this one customer who like paid really good money and then they said, oh, it takes four minutes to load the PDF. What the heck, guys? And I looked at it and it was like a 50,000 page text Bible from Canada.

24:22

And it had like 50,000 pages.

24:45

It had like more than 100 links.

24:47

Per page, 500,000 links.

24:49

My data model completely exploded because my assumptions were off by a number of what, 1,000. But by then you have like a mature product with an API. So how do you completely redesign the internal part without breaking things for everyone? Suddenly everything has to be lazy. Before, parsing 101 was easy, but now this was so difficult to keep it working for people. I think I spent two months just on that, completely redesigning the internals and like making sure it's still easy for people. They don't have to know what we load easy, what we load, lazy, or if you copy the thing. It still has to like have to keep some connection.

24:51

It needs to keep the references and some of those things.

25:36

And I love to do support And I think that was also a confining factor why the company worked, because if you send a ticket and then the CEO replies and helps you out, that has impact. And my strategy was always like, I always used to list in reverse because if you send a ticket and you get a reply within five minutes, that's magical. If you wait one or two days, not much difference.

25:40

Yeah.

26:08

So, yeah, this was one of the problems where I worked two months and I finally got it down to almost like this.

26:08

That must have been satisfying.

26:15

And that was very satisfying.

26:16

And you were writing a lot of the code or you were involved in a bunch of the code. Obviously a big team was now here, but you were still kind of overseeing it, right? I mean, the details.

26:19

I mean, of course I had a really great team and some parts I was more involved. I was always more involved in mobile because that's where my heart was. But I was always very deep in the tech and the marketing side, the business side. I had Jonathan's help, I had Martin's help. Those I found good people. The thing is, if you like the blogging and writing about how you solve interesting hard problems will help you hire interesting people that want to solve interesting problems.

26:27

This is what I remember at PSPDF Kit that your blog was. Every now and then it made it to Hacker News as well. But it was just interesting to read. And I couldn't name again, I'm not one into PDFs, but if I had to say something a PDF, I would have said PSPDF Kit because they're the only ones where I read interesting. Entering blogs about how you optimize your ship is still there, by the way. I myself also sometimes ask myself, like, interesting, do more companies not see this? Or is the question that you need to be a developer who's either the CEO or up there who just likes doing this? And by the way, did you ever write this thinking this will be helpful, or you just wrote because you got something out of it, like putting out that you solved this hard problem?

26:54

I like sharing and like inspiring people. There was sometimes even conflicts where we were like, should we write about this? Because it's like a little bit of secret sauce. But I just never listened to those voices too much. There's also, like, when you write something down, it's this principle of, like, you understand it, but then if you want to teach it, you really have to understand it. So to me, it was also a little bit like, oh, yeah, I worked on this really hard problem and now I want to preserve it. And help others. I got a gig of it. Of course I liked the attention, but really it was this. Sometimes I just referenced a year later to my own post. It's like, yeah, this is both company documentation. This is like my own logbook. It's helpful in so many ways. And a lot of those bigger companies, they put on too much red tape. There's a lot of developers who don't really like to write. So I forced everyone once a month, a full day, just to write a blog post.

27:39

But you gave them the time. You're like that day, you don't need to do any other work but write something.

28:48

Yeah, you have a day to come up with a post. A day is quite much actually. I mean nowadays when I write posts it still takes me a few hours. I don't want to dwell too much on like the. I think the starting time of the company is the most interesting. Then the growth phase. You get more red tape, you get more people. It's much more gardening your product instead of like doing white hacks and more iterative. So it got a little bit less interesting over the years and there was like more people drama. The more people you have, the more issues there are. And I didn't enjoy it that much and I was really, really burned out.

28:53

What burned you out?

29:40

Do you think I was just burning too hard? I was working most weekends. I tried to shuffle all my managerial needs and you know, as a CEO, you're basically the waste bin because everything that other people don't manage or can do or mess up you have to fix. And it's also quite lonely because you can't openly talk about a lot of things. I mean I structured the company to be quite open, but still you cannot be negative even if really bad stuff happens. I know that was one weekend where my co founder called me at 5am and told me like, yeah, there's this big airplane company and their planes are down because our software is crashing. That was a very interesting weekend until I could like I disassembled their app and did prove that they messed around with our source code to triggering a. Triggering a license key fallback that eventually like cost issue they had. But that was like a. If the sewers company is gone and more moment and that's just on top to all the additional stress. And there were quite a few of those things. You can do that for a while. And I also believe burnout doesn't necessarily come from working too much. It comes more from or at least for me when you work on something. But you don't believe in it anymore or you have too many conflicts. And we did fight a lot in the team with like, management team. And by the time I made this mistake and I thought, you have to, like, lead a company more democratically. So that was also something that burned me out. I wouldn't want to miss it for the world, though. Yeah.

29:41

So, you know, from the outside, it seems you sold your shares, you made enough money to not have to work again, should you not choose. And for a lot of people, like, you know, people who are starting out their business or one day want to start a business, this sounds like the absolute dream. Like, this is, I guess what we know realistically that most people will not make it. But if you make it, I mean, you've kind of like, I guess, you know, checkbox done. You're kind of. It's a little bit. If you're like climbing on a wall and you ring the bell, you're done. And then what I noticed is from the outside again, on your blog. The blog post completely stopped for several years. What did you do in this time and what did you learn in this time before you came back to where we are now?

31:28

I needed a lot of time to decompress. I. I catched up a lot on things I thought I missed. I partied a lot. There were months where I didn't even turn on my computer. And for a while I was. I just didn't have this feeling of, like, what should I do now? Like. Like, I definitely was like, why bother? You know, you're not. You're not supposed to. To retire so early or, like, have so much, have such a good exit that you never have to work again. That messed with my mind quite a bit. That was some. That was some hard years. And then in April, I was like, there was this idea that I had years ago and even a side project that I started, it's like, oh, yeah, I want to continue on that. And then after more than three years, I just sat back to my computer and. And started hacking again. But the thing was, this was like a Twitter analytics thing and it was written in Swift and SwiftUI. Back then, I already knew this would be so much better if I would build as a website.

32:09

So was this an existing idea that you kind of had at the back of your mind something Twitter analytic?

33:20

Yeah, it was just like something I wanted to build for myself because it didn't exist. And then even three years later, it didn't exist. It still doesn't exist. It kind of does. But I Got a bit sidetracked. So I went back and I wanted to build it with WebTech, but web was always, even at the company, the one thing that I looked into the least, because I had someone really smart who took care of that side in the company that I brought in Martin, so I never had to worry about it. That was one of the.

33:25

You're not hands on with React or any of that stuff.

33:57

Yeah. And when I came back, I was like, what's a prop? You know that, that level where you. And you know, this is like, this is a trap. I see with many developers, the better you get at one technology, the harder it is to jump somewhere else. It's not that you can do it, but it hurts so much. You're like, like, I can program in Apple stack, I can program program blind, but then in that stack I have to Google the most mundane stuff and it just hurts. You feel like an idiot again.

33:59

Yeah. And I guess the more experience you have, it kind of sucks feeling. I mean, I'm sure you say embrace and all that, but it's not great. You're not as efficient, you know that you could be faster, et cetera.

34:33

Yeah. So I came back and I was like, gosh, there has to be. What is this AI? What is this AI stuff that people are dismissing? Let's look into this.

34:43

And in April, a lot of us were dismissing it, probably for rightfully so.

34:52

To a degree. I credit those three years where I basically didn't turn on my computer because in those years you guys checked out AI and learned that it's crap.

34:59

Yeah. The people who I was about to say, so you missed out on, you didn't do the beta of GitHub Copilot, you know, glorified autocomplete, which is GPT3 or maybe not even. There was then of course 3.5, which is a big jump. And it got incrementally better than GPT4. And so by the time you came back, what tool did you first use? Because you missed out on like two years of US devs using, dismissing, finding some niche use cases for it or cloud code. So you start with cloud code. I think that just came out. It came out in May, but there was a beta beforehand.

35:13

Yeah, I think they had something. Didn't they have something in February already?

35:48

They had a beta from February, correct?

35:51

Yeah.

35:53

So clock code was your first. You come back after like a hiatus and you immediately turned on clock code and you missed everything else before.

35:54

And you know, it was like, I remember I took this big messy side project that I built and I have this browser extension that converts a GitHub repository into one big markdown. It was like a 1.3 megabyte markdown file. And I dragged it into Google CI Studio with Gemini 2.5 or 2 something. And I typed write me a spec. And it generated those 400 lines of spec and I dragged the spec into cloud code and I was like, build. And then I continue, continue, continue, continue. And while I was like working on other stuff, you know, and eventually told me like it's 100% production ready and I started it and it crashed.

36:02

I'm sure we can all relate to the story of the AI saying the code is production ready, then crashing. This is a pretty funny and innocent story, but I personally don't trust code that AI generates without verifying it. And this leads us nicely to our season sponsor, Sonar. So let's look at some data. A new report from Sonar, the State of Code Developer Survey report, found that 82% of developers believe they can code faster with AI. But here's what's interesting. In the same survey, 96% of developers said they do not highly trust the accuracy of AI code. This checks out for me as well. While I write the code faster with AI agents, I don't exactly trust the code it produces. This really becomes a problem at the code review stage where all this AI generated code must be regularly verified for security, reliability and maintainability. Sonarqu is precisely built to solve this code verification issue. Sonar has been a leader in the automated code analysis business for over 17 years, analyzing 750 billion lines of code daily. That's over 8 million lines of code per second. I actually first came across sonar 13 years ago in 2013 when I was working at Microsoft, Skype and a bunch of teams already use Sonar Cube to improve the quality of their code. I've been a fan since Sonar provides an essential and independent verification layer. It's the automated guardrail that analyzes all code whether it's developer or AI agent generated, ensuring it meets your quality and security standards before it ever reaches production. To get started for free, head to sonarsource.compragmatic with this. Let's get back to Peter and how AI agents cannot exactly be trusted.

36:49

But then I had, then I added an MCP so it could use the browser. I think a player with MCP was already there and it looped a few more hours and then I had a, I had a Twitter login page and it, it did something. I mean it was not great. But it did something. And to me, to me, this was my. Holy fuck. Mind blowing moment. Yeah.

38:21

And this was like in April or May this year, right?

38:42

Yeah, it was, it was. It was just good enough that I could see the potential and I understood. It's like, yeah, this is where it's going. And from that moment on, I had a few months where I had really trouble sleeping. And I in.

38:44

I remember because once on Twitter, I sent you a direct message. I was up early for valid reasons, you know, my kids or something like that. But it was 5am and I sent you a message on Twitter and you replied immediately. And I was like, why are you up? And it's like, oh, this is usual. Like, I'm still usually awake. And I asked like, why? And you said like, oh, I'm just like using Claude and it's really addictive. And I was like, really? And you're like, yeah, I'm not joking. It's really good. And I think that was the thing. You said something or wrote something, like just one more prompt. You told me how. What made it so addictive or what still makes it so addictive?

39:01

Oh, it's the same economics as you go to a casino. It's my little slot machines. You press the trigger and it's like, nope. You tap in the prompt and it will. Then it does crap or it does something that actually blows your mind and it's just.

39:40

And you're saying it blows your mind. As you're a really experienced developer, it's not easy to blow your mind, right? You've seen good code. You can differentiate crap code, decent code, good enough code, you have a bar, right?

40:00

It's so funny. In my company, I used to obsess over every detail, every spacing, every new line, the naming. I spent so much time bike shedding, and in retrospect, I'm like, what the heck? Why did I do that? Like, what's the point? The customer doesn't see the insights, of course. Like, it has to meet certain, certain standards. It has to work, it has to be fast, it should be secure. But, like, how much that bike shed there is like, stupido.

40:12

You say that, but then you also just said that people loved PSPDF because it was the most polished, it worked the best. Do you not think that that amount of carrying, bike shedding, as you call it, being obsessed, it sounded like you were keeping tech debt at bay. You know, like being obsessed with white spaces is not going to be messy. And we know it's not just the white spaces. We know you're going to care about testing and all that. Like, it sounds to me that PSPDFkit, what I see is you were not just building a product that was great ux, but you built something that had a really good hygiene and that's how it could be. High performance and all that. How do you think about it?

40:47

Yeah, yeah, yeah. To a degree, yes. And even now, I mean, like my last blog post was confession that I ship coded on Reed.

41:25

Yeah, we have to talk about that.

41:37

And at the same time, I spent so much time to restructuring. Even today I really wanted to get this PR in where it was like a 15,000 line change, where in my literature I moved everything over to a plugin architecture, which I was so excited about. And I care a lot about the structure. Did I read all the code? No, because a lot of code really is just boring plumbing. Well, what are most apps like? Data comes in from an API in one form. You parse it, you package it into a different form, you store it in your database as a different form, it comes out again in a different form. Then it's like HTML or whatever and you type in something, it's a different form again. And all you do is you're massaging data in different forms throughout your app. This is what most apps are. We are pretty Chasent printers and the hard part is solved by Postgres 30 years ago by some neckbirds. That's really what a lot of software is. There's always some interesting parts, but I don't have to care how this button is aligned or which tailwind class is used. Many details are boring and many other details are interesting. But I think it's much more about system architecture than having to read every single line.

41:40

Right now, jumping forward, what is your workflow like when you're working on Cloud bot? Are you using a terminal? Multiple terminals, which tools and how are you? You said you're kind of not reviewing the code, but you're still thinking about architecture. What does your average day look like in terms of tooling? You have to explain to a developer who might join the team. At one point you think like, what does it look like?

42:59

It's interesting. Let's go a little bit. We were in April with cloud code and then I got really hooked and then I did some. I had a phase where I did cursor and then I used Gemini 2.5 a bit. Then we had this phase with Opus 4. I hooked up a lot of my friends. I know both Armin and Mario from Vienna. They got AI pilled because I was addictive. My enthusiasm was confusing them. And then they tried it out and then eventually they also were up at 5am and I called it the black iClub. I mean, there's a reason I started a meetup in London that I called Cloud Code Anonymous because it's a little bit like a drug, because it's so much fun. To me, what blew my mind so much was this realization that I can build everything. Now. Before, you had to really pick which side project you build because software is hard. It's still hard. But now this friction where I talked about where I'm so good at this technology and I'm so bad at this, and I'm like, oh, let's make the CLI in go. I have no clue about go, but I have a good system understanding. And once you have that, it's like you develop a feeling what's right, what's wrong. It is a skill in itself. I remember there was this tweet where someone said, oh, when you write the code, you feel the friction, and that's how you make good architecture. I feel the same friction when I prompt because I see the code flying by. I see how long it takes. I see if the agent pushes back, I see if what it creates looks messy or makes sense. When I prompt, I have a hinge already how long it's going to take. If it takes much longer, I understand that I messed up somewhere.

43:24

You kind of feel the model, you know how usually it's like this, or.

45:21

If it runs, I feel it's very much a symbiosis. Like I learned to talk, may I even say there or that language more? So it's like my knowledge how to use those things improved. And also the models improved. And then over the time between April and now, I would say, yeah, the inflection point was Summer, where it just got so good that you create software without actually writing code by hand. But the real that change that sold it for me was again, GPT 5.2. That was again, I think it's underrated. I don't know why all these people still use cloud code. I kind of get it. It's a different way of working. But whatever OpenAI cooked there is insanely good. Pretty much every prompt I type gives me the result I want, which is insane. On cloudbot, my latest project, I use between five and ten agents in parallel. If you're very much cloud code build, you have to forget quite a lot of the silliness that the things that you have to do to create good output with cloud code. I mean, I also met that team and they created a whole new category. Like cloud code is a category defining product and it is amazing for general purpose computer work. And it's really good for coding and I still use it almost every day. But for writing code in complex applications, Codex is just so much better because it takes 10 times longer. Claude would read three files and then be confident enough to just create code. And then you really have to steer it and push it so it reads more code, so it sees a bigger picture of your code base, so it weaves in new features better. And codecs will just be silent and just read files for 10 minutes. And if you only work on one terminal, I completely understand how you find this unbearable. But I rather have something where you don't tell it what to do. This is also something that people don't get. I have a conversation with the model. It's like, oh, let's look at this. What options do we have for this structure? Did you consider this feature? Because every session is like the model starts from having no understanding about your product. And sometimes you have to just give it a little bit of pointers. What about this? And this? So it explores different directions and you don't need plan mode. Like I'm just having a conversation until I say build this. It will not build this. There's some trigger words because it is. They all are a little trigger hungry. But as soon as I say let's discuss or give me options, they will not build things until I say build.

45:26

So a lot of would you say a lot of your prompting or a good part of it is this conversation where you are pretty much planning together with the agent.

48:28

Yeah, what about like I say, you remind them. It's like, okay, we need documentation. What would be a good spot? It would give me some recommendations and say no, this should really be its own page. Do we need a configuration? How does this fit into this other feature? It's like I am designing the system because I have this system understanding about how is my product, how are the shapes looking? I don't have a line by line code understanding. That's what codecs does for me. But I'm the architect.

48:38

It sounds a little bit like you're almost, you know, for years back this totally came, got out of style. But there was this idea that you would have the architect with a capital A who used to be a software developer, but they're not hands on anymore because they spend a lot of time understanding the business and they have These developers working underneath them. And some companies still kind of work a little bit like this, but most modern companies don't, but some banks, et cetera. I met people there who are capital architects. They do the system plan, they talk with fellow architects, they have the blueprint and then they literally pass it down to the team. And everyone hates this model, obviously, because again, I think as people, you kind of want more. The architect is never on call for this stuff, and so it just kind of breaks down in practice. And a lot of large companies just move to the staff engineer model, where you're kind of all working together. Of course, there's people who might have more input, but sounds like it's almost like this world where you are the architect who kind of, you know, you have your little agents who do the code. Except in this case, you are, of course fully responsible because you're still an individual contributor. You're not like, okay, you might say you're a manager of agents or whatnot, but the code is yours. It's your responsibility. You're going to be on call. If you push out code that takes down cloudbot, which it did just recently, you're on the hook for it. Right? And I think the difference in this system, when it was in companies, the architect was kind of shielded from the output of their work because there's so much people and so much process, etc.

49:08

Well, I wouldn't say architect. I like the word builder.

50:41

Builder, yeah.

50:44

And as I go to that, there's a few categories that I see for people that are highly successful using AI and people who really struggle. I care more about the outcome, the product. I very much care about how it feels and everything, but how the plumbing works underneath. I care structurally, but, you know, not the biggest detail. And then there are people who really love to code on hard problems, like think about algorithms. Don't really like the. I'm building a product with like all the marketing. They like to solve hard problems. And those are the people who really struggle and often reject AI or get really sad because that's exactly the job where that AI does it solves the hard problems. Sometimes I give it some pointers, but many times I learned more this year than last five years around software, architecture and designing. There's so much inside those monsters on knowledge and everything is just a question away, but you have to know what question to ask. Of course. I also built this Twitter thing and it's still not done, and I really hope I'll get back to it. At one time, everything worked, but If I used it more at some point, things got really laggy and weird. And then it worked again. I just couldn't figure it out. And it was really difficult to debug because it was not easy to reproduce. It was just like, you use it more and things got really slow. I basically had software in psql, like in postgres that would be triggered when certain inserts were doing. And then the database would get really busy and the model couldn't see it because it was. It was so far abstracted from all the, you know, like those models are really good at tracing through. But this was a side effect that was so hard to see because it was only in this one file. A function that had no connection to anything else with a name that was not easy grabbable. I just never asked the right question until I was like, do we have any side effects for this and this? And then I found it and I fixed it. And it's like. But I. Everything is just the right question away.

50:44

Yeah, but you need to have knowledge, expertise, experience.

52:52

So these are the people who reject it and then the people who care a bit less about how it's being plumbed internally, but are just excited to build things, they're really successful. And one thing that also helped me is when you run a company and then you hire people, you can't breathe on everyone's neck and make them have the line of code exactly that way. And there's a lot of people who didn't manage a team who didn't have this experience, how to relax a little bit and understand that yes, this maybe is not exactly that code that I want, but it will get me closer to my goal. And for anything that is not perfect, we can always make it better and put more time into it. I very much believe into this iterative improvement. I had to learn to let go a little bit of my company. So then when I had cloud code, it kind of felt like I have imperfect, sometimes silly, but sometimes very brilliant engineers that I have to steer and where we work together on a common goal. It felt a lot like being the boss again.

53:00

Interesting. Now you built kind of software, I guess the traditional way pre AI for 15 years or even more than 15 years. And you got really good at being also leading a team and how to have high standards. You really cared about the craft there as well. You've now kind of been, I guess vibe coding or working with agents for a year. You're comparing the two. What do you think really, really changed and what do you think Are things that kind of stayed the same despite all.

54:05

First of all, I don't like the term vibe code.

54:31

All right. How should we call it?

54:34

I think wipe coding is by now almost a slur. I call it. I tell people what I do is agentic engineering with a little star vibe. Coding starts at 3am now because all the mundane stuff of writing code is automated away. I can move so much faster, but also means I have to think so much more. I'm still very much in the flow. It is completely the same feeling for me. I very much get in this flow state, but it is mentally even more taxing because I don't have one employee that I manage. I have like five or 10 that all work on things. And I switch from this one part to this other part, to this other part to this other part, mostly because of I'm designing this new subsystem or this feature. And then I know that it will probably take Codex, like 40 minutes or one hour to build. So I want to have the plan right and then I build it, and then I'll move on to something else. But then this is cooking, and then I work on this, and then this is cooking, and then this is cooking, and then at some point, this is cooking, and then this is cooking, and then I go back to this one. So I switch around a lot in my head and wish I wouldn't have to do that. I'm sure this is a transitionary problem. And at some point we have models and systems that are so fast that I can paralyze a little less. But to stay in the flow state, I need to massively parallelize. So that's how it works. And I go back to there and maybe tweak it a little bit more. But usually just try it out. Maybe then this is ready because this only took like 20 minutes. So I constantly jump around. Usually there's one main project that has my focus and I have some satellite projects that also need attention. But where I can maybe spend five minutes, it does something for half an hour and I try it and it doesn't need so much capacity up there.

54:36

This almost sounds like two things come to mind. One is there's these games where you have to manage a kitchen with the employee and you see recipes or something come out and you need to jump and do it.

56:27

It's more like StarCraft. You have your main base and you have your side bases that give you resources.

56:38

That as well. And also one thing that just came to mind, as you said, I go there and I Watch this. And I make a decision is when I see the chess grandmasters play multiple boards at once. Sometimes they play 20 boards and they always all, you know, they go there. They kind of, you can see that. They just like see what's on that board. They make a decision. And for some boards, they suffer longer, I guess. Better players or better opponents, it feels, you know, both. They're occupying 100% of their bay. You're occupying your bay and you're kind of just scaling yourself as long as you can.

56:42

Context switch the difference. The difference was up until this cloud code, you have to work a little different because it is much faster. But then the output often doesn't work on the first try. So like, it makes something, but then it forgot to update three other things. It crashes or you give it the good thing. How to be effective with coding agent is always like, you have to close the loop. It needs to be able to debug and test itself. That's the big secret. That's also something. I think that's part of why I got so much more effective. But yeah, with cloud code, I often had to go back and fix up the stuff or it just takes a lot of iterations. So in the end, it's not that much faster. It's just more interactive. And these days with codecs, it just almost always gets it right. My general strategy is always, I build a feature and of course you always let it write tests and you make sure that it runs its runs.

57:11

Yes.

58:15

So even, even when I write a Mac app, I don't know, I just yesterday I debugged this feature where the Mac app couldn't find a remote gateway. But, like the same coding TypeScript could. But Mac app is kind of annoying to debug because, like, it builds it, you have to start it, you have to look at it, you have to like, take, no, this is not working. So now I just said it like, you know, you're going to build a cli just for debugging that invokes all the same code paths that you can call yourself. And then you just iterate and you fix it yourself. And then it will just cook. And it just cooked for an hour and it was done. And it told me, like, yeah, there was a race condition here and here and like a misconfiguration, blah, blah, blah. I was like, yeah, sounds sensible. I don't need to see that code. It's like.

58:16

But you don't need to see it because you set up the validation loops and you trust that because it Ran it. I mean this is. I guess it's not too dissimilar to sometimes when you work on a large project, on a large company, when all the tests pass, I mean it doesn't mean 100% it's there, but it's a pretty good. And all the new code has tests as well. Someone thought about it and tested it and all that.

58:59

Even on the very latest project, we always had bugs for like Anti Gravity has a certain weirdness with how it takes tool calls in the loop in the format. So you have to do some filtering.

59:21

Yeah.

59:36

And that broke a bunch. And it actually took me way too long to realize like what am I doing here? I just need to automate this. So I was just going to Codex. It's like design life tests that spin up a Docker container, install the whole thing, spin up a loop, use my API keys from this and this file and then you tell the model to read an image, create an image before and then look into the image and see what it sees. So I don't not just tell the loop, I'll tell tool calling, make it work. And then it solved itself. It took forever, but it tested all my API keys like from Anthropic over set, AI over glm, like everything. And it fixed all those little indicacies where sometimes the tool calling didn't work or the ordering was wrong because I closed the loop. And that's closing the loop.

59:37

You mean just have a way to have the agent be able to validate its work.

1:00:29

That's the whole reason why those models that we currently have are so good at coding, but sometimes mediocre good at writing creative because there's no easy way to validate. Right. But code I can compile, I can lint, I can execute, I can verify the output. If you design it the right way, you have a perfect loop. Like even now for websites, I built the core in a way that can be run via a cli. So I have this perfect execution loop. Because the browser loop is insanely slow. You want something that loops fast.

1:00:34

So it sounds like one thing that is not really changing from before is we had this before backend or business logic heavy thing could easily be or more easily be verified that it's correct.

1:01:09

I'm surprised actually using agent decoding makes you a better coder because you have to have to think harder about your architecture so that it's easier verifiable. Because verifying is the way how to make things good.

1:01:20

Well then remember back even before AI for complex systems, once you got someone who built these things before what they started with. How do we make it testable? Right? You need to design interfaces, classes, testable. You need to think about, am I going to fake things? Will I use mocks, will I use end to end testing, which will be long, et cetera. But these are really hard architectural decisions and once you make them, they're I guess, harder to change. In your word. The model would cook a lot longer if you asked it to make a massive refactor. And if you have tested, it'll get it right. But we still have these trade offs.

1:01:31

It's still software. I would say I write better code now that I don't write code myself anymore. And I wrote really good code. But even back at the company, sometimes testing was so tedious and you come up with all those edge cases and the branching.

1:02:08

I mean, outside of Kent Beck, who I deeply respect, he was on the podcast and we talk like he still writes tests first. And he tells me he's not mad at me for not writing it, but if you want to write poor quality code, that's on you. But I don't know many developers, myself included. I never liked writing tests. And even when I pretended that I did, I just never did. It's a little bit like writing documentation and writing tests. To me it was never a creative expression.

1:02:25

It is so good. Now I would say for my last project, I have really good documentation and I didn't write a single line myself. No, I don't write the test, I don't write the documentation. I explain the model, the trade off. So why we did something like this and then tell it, write that, write the entrance section, beginner friendly, and then add more technical detail at the end. And it is so good. I never had a project with that good documentation. Just by every time I design a feature, this is a part of the process and also testing, I'm almost like, okay, we built this, how are we going to test this? Yeah, we could do this and this and this. What if we build it this way? Oh yeah. Then we can test it better. This is now part of my thinking because I always think, how do I close the loop? The model always needs to be able to verify the work itself, which automatically steers me to better architecture.

1:02:54

So why do you think there's a bunch of experienced devs who are still pushing quite a bit back on just the idea that AI can do a lot of this?

1:03:45

That was a week ago. I stumbled over a blog post by Nick Gallaherger Kokovislav that I deeply respect and learned a lot from. And this blog post was just a dissing of the current way, how models work. And what he did was he tested like five or six models, including some that make no sense, like the OpenAI 120 billion open source one is not good enough to write good code, you know, and he wrote a prompt. As far as I understand it, there was not a lot of information on the website, but to me it sounded like he wrote a prompt, he put it on Claude web and he pressed send and then he took the output and ran it and it didn't compile. And he was disappointed, but he's like, of course it will not work. Do you think I can write bug free code on the first attempt? And those models are ghosts of our collective human knowledge. They work very similar in many ways. Of course you don't get it right the first time, there will be mistakes. That's why you have to close the feedback loop. And also you don't just send a prompt to the model, you start a conversation, hey, this is what I want to build. He complained that it used old API. Yeah, you didn't specify the macOS version. So it made an assumption to default to old API because that information was missing. And it is trained on a lot of data, not just the last two years. And there's just more old data than new data. So this is like the more you understand how those little beasts think, the better you get at prompting. And then he spent maybe, I don't know, a day or so on playing with it and then just decided that this technology is still not really good. But to be effective, you have to spend significantly more time. It's like, you know how to play guitar and I put you on piano and you try it a bit. It's like, oh, this sucks. I go back to my guitar. No, no, It's a different way of building. It's a different way of thinking. You have no idea how often I screamed at like 3am to cloud code because it did something silly. I slowly started to understand why those things do what they do with exactly the way I tell it to do things. And sometimes you can literally ask. Even last year for this project, the last project, like Cloudboard, I feel like a human merge button because the community is blowing off and all I do is reviewing PRs. I have very little time to actually write code myself anymore. And in the beginning it would often just cherry pick things and would close the pr. And it was so annoyed, I'm like, why are you doing this. Yeah. When you say this and this, I interpret this, this, and this. It was like I learned the language of the machine a little bit more. I tweaked my prompting, and now I get exactly what I want because it's a skill like any other skill. Yeah.

1:03:57

And this is like, Simon Wilson has been saying the same thing, even though he's been using it for years. And I think once I started to use it, I also realized I'm okay at it, but I could do better. What if we put this to a real test? Because I think it's fair to say that right now you're building cloud bot, which is a. You know, it's not something that generates revenue. There's a lot of users, and it's blowing up, and it's a really cool tool, but it's not PSPDFkit, which is a business that. It's. A lot of revenue is hinging over it. If today, you know, we just wiped. PSPDFkit does not exist. You need to rebuild PSPDFkit. You now have these agents. How differently would it look? How much would you trust it? What would you delegate? What would you validate? And. And when you built up a team around it, because now it's a profitable business, at the very least, you need to hire salespeople, whatnot. How do you think the team would look different today with that same product? Because you know exactly what it took to build it, and you also know what these tools can do.

1:07:06

Today I could easily run a company with 30% of the people. It would probably be quite difficult to find people on that level. So you want. You want to have really senior engineers that really understand what they build, but that are also comfortable in delegating and know which parts are actually important to work on and which parts. I can vibe that's still something I don't see. I don't see a lot, especially in the AI world. There is so much crap on Twitter. There's so many people that are loud but clearly have no clue what they're doing. There's so many dumb concepts around. Like, I'm sorry, but the Ralph Wiggum one like this is again, another. Another silliness people use to work around model limitations of opus. You don't even need. When you use Codex, that's. There's maybe a few cases where you have a really long list of individual tasks that can be automated, but that's usually not how software building works. So there's these people who. I see so many people building up this elaborated orchestration. Layers and then you have Beats that automatically creates tickets. And then your agent does tickets and then your agent emails the other agent and then you build up this elaborate mess. What for? Oh yeah, they designed the specific for a few hours and then the machine builds it in the whole day. I don't believe this works. This is the waterfall model of software building. We learned long ago that this doesn't work. Yes, people work differently and maybe it does work for some. I don't see how this could work for me. I have to start with an idea and often I purposefully under prompt the agent so it would do something that would give me new ideas. Maybe like 80% of the things I assumed were like crap. But there are two things like, oh, I didn't think about that way. And then I iterate and shape the project and I have to click it, I have to feel it. I feel to make good software, I. You know, one thing those things often lack is taste. I have to feel like, how does this feature feel? And the beauty now is that features are so easy I could just throw it away or reprompt it. My building model is usually very much forward. It's very rarely that I actually revert and have to go back. It's just like, okay, no, then let's change this. No, let's do this. It's like shaping. I love how this, like you start with a rock and then you sizzle away at it, pick different areas and then slowly this statue emerges out of marvel. That's how I see building something.

1:08:02

I guess reflecting on how software engineering is changing, this seems like a change because before we had AI or any of these agents upfront planning did make a difference. At pspdf, you insisted, I think, to have a proposal where people put a lot of thought up front to specify and do all the. Because it was expensive to I guess, to build. Do you think this is changing because of the cost of just writing code is going down or.

1:11:07

I mean, I still plan, but you still do. Yes, but I don't put as much into it because it's now so much easier to just try and look at the results and then see if, oh yeah, this shape could work. Or now we have to. The tweaking and even like, oh no, we have to do it a completely different way is not so much cheaper that to me it became much more playful.

1:11:36

Yeah, I guess because when you're working, even if you have a new grad on the team or an intern, you give them something, they work on it for a day or Two. Now you give them another day or two. And we're not talking days here, we're talking minutes, or if it's a long running task, 10, 20 minutes at worst. Plus, you're not just waiting on that thing. You have parallel things running. So it's not that much of a.

1:12:00

Waste, if you will, in cloud. But at the beginning, I had this assumption of one agent and then eventually changed to multiple agents, and there was an assumption of one provider like WhatsApp, and now it's multiple ones. And changing that was such a pain, or would have been such a pain if I would have written it myself, because you have to weave in literally everything through the whole logic of the application. And yeah, it took Codex like three hours. It would have taken me like two weeks, you know, so that upfront planning, I could have realized that in the beginning, but now I know that, like, I can just change things and it's much easier to work down your technical depth or your. You know, you evolve how you think about a project as you build a project. That's why I don't believe in, I don't know, things like Gastown, where, like, you write up the spec and then it builds itself and then it's done. How can you even know what you want to build before you built it? You learn so much in the process of building it that will go back into your thinking of how the system actually will end up being. To me, it is very much a circle until I. You don't walk up the mountain like this. You go around and sometimes you, like, you stray off a little bit of path, but eventually you reach the top. That's how I feel software is then.

1:12:21

You'Ve been building cloudbot for what, like two months, three months? Nonstop? Ish. Or how long?

1:13:42

Let's switch a little bit gears. One of the ideas that got me back was even in April, May, was I wanted to have this hyper personal assistant, not like one that sends you a good morning email. Oh, these are your three tasks. No, one that has a really deep understanding of me and doesn't just, I don't know, I meet a friend and then when I go home, it would ping me, hey, how was that meeting? Or one that would wake me up one day and say, hey, you haven't texted Thomas in three weeks. And I noticed he's in town right now because I checked his Instagram account. Do you want to say hi or something that says hey? I noticed every time you meet that and that person, you're sad. Why is that like something that is deeply personal, like almost the anti orm. It's kind of like the movie her, but that's where the technology is going. Those models are really good at understanding text. The bigger the context is, the more patterns they see. And even though they are like Matrix calculations without a soul, it very often feels different. So this was one of these ideas, and I even created a company I called Amanthus Machina, the Loving Machine. But in summer, when I explored it, the models weren't quite there yet. I got some results. It was like, okay, this is like, I'm a little too much on the edge of what I need right now. Which was very exciting because I know the state of AI goes so fast that, oh, I can just revisit that in, like, a little later. And one of the ideas also was that I assume that all of the big corporations right now are very much working on personal assistance in the future. Everyone will have. You will have your best friend who is a freaking machine that will understand you, that will know everything from you, that can do tasks for you, that will be proactive, that will require a lot of tokens, but everyone who can afford it will have one. And of course, this will democratize and trickle down to more and more people as we learn how to build more efficient systems and hook up on chips. No question, this is where the things are going. You see the first things with OpenAI, who launched pals with some productivity, but we just don't have enough compute yet to offer this as a feature. And also it's quite difficult. My idea was it's like, I kind of want something that runs on my computer, and where the data is yours is actually mine. And it's also quite scary that you give open your entropic access to your email, your calendar, your dating apps. I don't know if you talk to your normie friends, but a lot of my friends in eDream, they use that a lot to basically have a therapist. And it does work incredibly well. It's a really great listener. It understands your problems. And unless some of versions of 4O that are like, sure, this is a great idea. I want to put french fries into a salad. It works really well. And I did that too. I mean, part of it just is like the act of reflecting already is helping you. So it would even work if the machine would only repeat exactly what you wrote to a degree. But it actually gives insightful questions. Actually, it got really good. So I had this idea of this assistant, but the tech wasn't there, so I did the other part. And I built a whole bunch of fun stuff. Of course, I built wipetunnel this in your career to become an agent engineer, you have this phase, it's a trap phase, where you're looping and building your own tools to optimizing your own workflow. But this idea of this hyper personal agent stuck a little bit. And then over the last few months, I really started, I built it, but finally, initially, I didn't even had the scope that it has now. I called it WhatsApp Relay. I just wanted to trigger stuff on my computer with WhatsApp. So I built a WhatsApp relay where I had an agent that could do stuff with my computer. And then I was traveling to Morocco for a friend's birthday and was out most of the day and just used WhatsApp to talk to my agent. And I was kind of hooked. It was guiding me through the city, it was making jokes. It could text other friends via WhatsApp from me. And I remember I was blown away because in the beginning, the tech was very scrappy, but I built in something where I could send it an image. Didn't even use the proper thing to send an image. I just gave the LLM a string and you could do the read tool to read the string. And then I was in Morocco and was just like. Just like, not thinking and sending it a voice message, but I didn't build that. And then like 30 seconds later, it replied to my voice message. I'm like, how the did you do that? Oh, yeah, you sent me a file. And then I looked at the header and I found that it's otg. So I used FFMPEG to convert it. And then I looked for VSPA on your computer, but it's not installed. But I found the OpenAI key. So I did a curl to OpenAI server, let it translate, and I'm like, holy cow. This was Opus 4.5. And it's so incredibly resourceful. You just did this. Other people say, oh, you need a skill or some system. No, it just figured it out. I slowly got hooked on this thing. I used it to wake me up. And it was running. It was running on my Mac studio in London and was connecting over ssh to my MacBook in Morocco and was turning on the music and making it louder and louder because I didn't reply. And to make that work, I added a heartbeat, which in a way is insane from a security perspective. You have a model that you prompt with do something cool and surprise me that you send every few minutes to make it proactive and go through your task list. Probably the most expensive alarm clock ever, but it was just hilarious. And also the text it sends because I had a balloon thought and it knew that I had to wake up very early and I didn't reply. And it was like you could see the reasoning. Peter's not responding, but Peter has to wake up. No, no, no, no, no. No sleep as it was bitching to me. And then I showed it to the friends I was with and everybody was like, hooked. This is something magical. And I was hooked too. And then I went on Twitter and I got the most muted responses because nobody would get it. I feel it's somewhat of a new category of products that.

1:13:50

A little bit like your story with when you didn't get the iPhone from the marketing campaigns on TV and anywhere. And then you have to use it. Yeah.

1:21:10

So I worked on it, but Only the last two months and the name changed from VA Relay to some point a. Claude, what is this name? Like it doesn't fit the feature set anymore because I had Telegram in there and other features. So I renamed it to Claudis because it's an inside joke. Because I like Doctor who. I felt claudebot is a better name, had a better domain, and explained the product better. So I hit it on the domains and then I also quietly built up my army because to make this work, you want everything to be a cli. So I was just building Clis for everything, like for Google, for my bed, for lamps, for music.

1:21:18

Why clis? Why not mcps? And what do you think about MCPS anyway?

1:22:01

It's a crutch. I think that the best thing that came out of MCPS is that it made companies rethink to open up more APIs. But the whole concept is silly. You have to pre export all the functions of all the tools and all the explanations when your session loads. And then the model has to send a precise blob of JSON there and gets JSON back. But surprise models are really good at using Bash and imagine you have a better service. So the model could ask for a list of available cities and then get like 500 cities back. And then it has to pick one city out of 500 cities, but it cannot filter that list because that's not part of how MCP works. And then you say, okay, give me the weather for London. And you would get the weather, temperature, wind, rain, and like 50 other things that I'm not interested in because I just want to know, is it raining or not? Probably raining, because London. But the model needs to digest everything and then you have like so much crap in your context. Whereas if it's a cli, it could use GQ and filter for exactly what.

1:22:06

It needs, but does not seem like a limitation that everything is loaded around the MCP in the context. That seems a problem. Like it sounds like it could work if MCPs were not in the context and there was a way to discover or decide which one to use.

1:23:19

That's what companies are building now. But there's still the problem of that. I cannot chain them. I cannot easily build a script that says, hey, get me all the cities that are over 25 degrees and then filter out only that part of information and pack it in one command. It's all individual MCP calls. I cannot script it.

1:23:33

Yeah, but I guess this is just a matter of time because if we think about when I'm building a weather app right now, I know that, you know, even without AI, I know I need to build up this thing, I need to, I need to fetch the data. So I will search what kind of APIs are available, which one do I like, which what kind of trade off for pricing, for covering, etc. And then I choose that API and I could chain APIs because I could get that result and look up, et cetera. So I guess this is, you know, like it sounds, pretty much, we've solved this. So as free AI, we're going to solve it. It'll just take some time and who knows what the format for this will be.

1:23:54

I mean, I built MacPorter, which is a small typescript thing that converts an McP to a CLI, so you can just package it up.

1:24:29

Basically you're saying clis right now are a lot more efficient.

1:24:39

Yeah, yeah. In cloudbot I don't have MCP support, but you can via make Porter. You can use any mcp. You can literally be on your phone and say, hey, use the Vercel MCP to do this and this. And it will go on the website, it'll find the mcp, it will load it and it'll use it all, all on demand. Even right now, if you use mtp, you have to restart cloud code, which is very user unfriendly. So I quietly built up my army to automate everything, which was a lot of work. I think Theo did a video a few days ago where he told me, this guy is insane because the list is really long by now. But as I was playing with my agent, I want him to do more and more Stuff I felt it really hard to convey what it does. It's still hard to me in January 1st, just a week now, I did. Okay, let's try something. Let's do the really insane thing of making a discord and then adding my agent to Discord. There was somebody who contributed discord support to it and even though I wasn't sure if I should merge it and I eventually did, so I put on my agent who has full read write access to my computer in a public discord.

1:24:42

What could possibly go wrong?

1:26:00

Yeah, this is absolutely insane. And then of course some people joined the Discord and then they saw me using the full power of this thing, like checking my cameras, doing home automation, it playing DG for me. I was in the kitchen and I told him, look at my screen. And my agent's done. Because it has full access of my clean and it can click. So it can actually click into the terminal and type for me and it can tell me your codecs say this and this because it just sees the screen. I mean I'm working on optimizing that. I actually want to stream out it because it would be much better if it's text, but it works already. It's in the background. You look at my screen and make some rants if I do some shit. And everybody who experienced it for a few minutes got hooked up. This was the craziest blow up from 100 stars to 3,300 stars in a week. And I think I merged 500 pull requests already. That's why I feel like a human merge button. That's why I'm a little all over the place these days. Because this project is blowing off. And the beauty of it is the technology disappears. You just talk to a friend on your phone that is infinitely resourceful, has access to your email, your calendar, your files, can build websites for you, can do administrative work, can scrape websites, can call your friends, or can call a business. I'm just about to merge the call feature. It literally can call a business and make a reservation for you. And you don't have to think about computation or, or all of that context blends away. I have like a, have a memory system so it will remember, not perfect, nothing's perfect yet. But it already feels magical because now I walk around, I see like this event. I send Claude a picture. It will not only tell me the reviews of this event, if there's a conflict in my calendar, if friends talked about it or you know, it has so much context that it, the responses that it can give Me are like so much better than like what any of the current tools that live in their own little box can give me.

1:26:01

Well, sounds like you built whatever Apple was hoping Siri to do, but they've been unable to.

1:28:20

I honestly, I built the best marketing tool for Anthropic to sell them more subscription. I don't know how many people signed up for the $200 subscription because of Cloudbox and many people already had one and used a second subscription because of that. Because it's so token hungry. It's not that it's token hungry, it's just that people love it so much that they use it all the time. And because the technology blends away, they don't see that it spawns sub agents and does a whole bunch of things in the background to just make it feel easy. But there's some actual engineering. There's a lot of work in the back to make it feel easy. This is the hard part. You hide complexity to a degree that it feels magical.

1:28:26

Yeah. But this is interesting because I can sense from we're talking you put so much thought into architecting this thing and right now you've been building this for a few months and yes, it blew up. But in your head, do you have a structure of how cloudbot is structured, what parts you need to modify? You can get your mindset into it and you know where modification needs to do you know what you want to refactor? Because it's not going to be efficient. Are you thinking about things like memory consumption, token consumption, efficiency, those kind of things?

1:29:12

I mean token consumption is more like how do you structure the prompt and memory? It's typescript that shows Jason around. In the end, let's be honest. I get text from an LLM, I save text to disk, I send text to WhatsApp or to now we have like Ms. Teams, Slack, Discord, Signal, iMessage, WhatsApp and there's two more that are landing like metrics that will expand this thing even further. It's like it's really poly by now, but mostly again I move around text in different shapes and maybe it goes to different providers or there's like now it's different agents and there's like the agent loop and there's like a lot of configuration and it's a lot of plumbing but there's nothing in there that is really difficult.

1:29:45

But it's a lot of small things. Right. I feel in software, right. We know for software even before AI there was not much difficult. Of course you need to learn and Understand the language and all that.

1:30:42

But the difficulty is how do I make it so that it feels magical. So what I worked on a lot is now you have. You have this one liner that you type in that you pass in your command. I will check if you have node installed, Homebrew installed. I'll install the NPM package. I do some check if you have any existing stuff. Just do like, just to make it work simple, even if you already used an older version and everything. And then I'll guide you through setting up a model. But again, I will pre find if you have codecs or CLAUDE installed. So you can just press Enter so you don't have to think about it. Mostly just press Enter and then you want a WhatsApp. You type in your number, it will just work again. And then I'll ask you, do you want to hatch your bot? You can press yes. And then a TUI comes up because you're still in the terminal, right? You want a good experience. So just a tui basically for that and where you just see. Wake up my friend. And then I programmed the model, I added a bootstrap file and to explain the model that it is now being born to create an identity in a soul where the values of the user are in. And then the model will be like, hello, stretchers. Who are you? Who I am? What's my name? And this like I watch people do it. And that's where the magic starts. That's where they're like, they no longer think about. I'm talking to GPT 4.2. No, I'm now talking to my friend. Created Wahoon like a unicorn with part of his name. Or like I'm talking to Claude. And then it's like, what's important to you? What do you do? It's like curious. I programmed it to be like curious. And then go through this bootstrapping phase. And then it will actually delete the bootstrap file and create a. A user MD with information about you, a soul MD with all the core values, and an identity with what's his name, what's his core emoji, what are the things that are inside jokes. But there's evolving documents that it will maintain and tweak as you interact with it. And then it will just send you a message on WhatsApp. And you just suddenly you talk on WhatsApp, making this flow easy. That was hard. Also, even coming up with the idea of you're not editing the configuration because the agent can edit its own configuration. You don't have to update anything because the agent can update itself. You can literally ask your bot, update yourself, and it will fetch itself and update itself and come back. It's like, hey, I have new features. Blending the technology away so far. That's the magic. That's why.

1:30:52

But it feels very similar to what you would with PSPDFKit, right? You kind of blended away the complexity of a PDF so that it was just there. You could rotate. You could do.

1:33:39

Yeah, even at the API level back then.

1:33:48

But it's a bit bizarre. Like, what you described reminds me of this black mirror episode I just watched, which is called Plaything, where it's a digital little creature that creates, of course, a black mirror. So it has a black bit of a dark ending, but it was also a game. It kind of feels. You know, we talked about how you don't play as much games because you like. But this also feels a little bit like a game. Right. But it's kind of like more connected with reality. Just fascinating how we're here pulling back into the realm of software engineering. So you built this product and it's now it's a production software. You're merging Pull request. People are using it now. Thinking back to PSPDFKit and companies that are like that, which have, you know, like tens or hundreds of developers working on production software, knowing what you know, with how you're building cloudbot and the tools that you're using, how do you think software engineering at those larger companies could change? Because one thing I see is for individual people like you, it's like AI is really, really hitting a fit. Like, you're making you way more productive. You're in control at teams or at companies that are, you know, have existing code. It's just a lot kind of slower. It's not really okay. People use it for this or that. But it seems a huge divide between the two worlds. And you've kind of been the CEO for company. What might that be? Or is it just more of a timing thing where every new technology often comes with hobbies? You know, pick it up earlier.

1:33:50

I think companies will have a really hard time adopting AI efficiently because this also requires to completely redefine how the company works. You know, like at Google, they tell you you can either be an engineer or, like a manager, but. Or you want to also, like, define how the UI looks. That rule doesn't exist because either you, like, you build it or you design it. But this new world needs people that have a product vision that can be able to do everything. And you need far fewer of them, but ultimately just very high agency and high competency people. But you can probably trim the company down to like 30%, which is very scary because economically this will all lead into a fiasco and a lot of people will have trouble finding a place in this new world. But I'm not the least surprised that current companies cannot very successfully use AI. I mean, they do to a degree, but you have to do a big refactor first. Like not just on your code base, but also on your company. I design, even on a code basis, I design the code base. Not so it's useful, it's easy for me, so that it has to be easy for the agent. I optimize for different things. Not always the things that I prefer, but the things I know work the best and have the least friction for those models because I just want to move faster. And ultimately they have to deal with the code, not me. I deal with the overall structure and architecture, and I can still do that in the way that I like. Everything has to be reshawed, you know, pull requests. I see them more as prompt requests now. Like, somebody opens a pull request, all I do is say thanks and I think about the feature. And then with my agent, we start off with the PR and then I'll design the feature as I see fit. The agent rarely reuses. Like, maybe I reuse some code, but it's more like it gives the agent a good understanding of what the goal is. And sometimes it's very useful because it's tricky. Bugs. Right. But I basically rewrite every pull request and weave it in. Also, a lot of people, let's just say the overall code quality of PR is went down a lot because people wipe code. And building a successful feature still needs a lot of understanding of your overall design. And if you cannot do that, you will have a harder time steering your agent and the output will be bad.

1:35:19

Yeah. And if you don't have the feedback loop to close it, etc.

1:37:54

Yeah, yeah. So I found it highly effective. You know, at PSV devkit, sometimes a pull request was like a week in the work and you comment on it and then somebody has to context switch and you wait for a CI for 40 minutes. No, I have the discussion. I see. Okay. How would this affect something? Like, I let the model review it, it will already bring something up. I have some ideas as well. We're going to reshape it into a form that fits my vision and then we weave in the code. It's literally, there's so many New words I use for, like, writing code now with those models, which is so funny. Like weaving in code into an existing structure. And sometimes you have to change the structure so it would fit.

1:37:57

Now imagine that you would hire one or two people to make it a small team. How do you think in this world and you want to keep doing what you're doing, how do you think things like code review, CI CD would change?

1:38:34

I don't care much about CI.

1:38:48

Why not? You used to care a lot.

1:38:50

Like a PSPDF kit.

1:38:52

You used to care a lot. Right.

1:38:54

And I still do this. There's value, but I have local CI. I'm a little bit of dah pilled now that.

1:38:55

Because the agent runs the test, right?

1:39:05

Yeah. And it's just way faster. I want to push back on the pian and wait for 10 minutes to wait for CI.

1:39:07

Because you've waited 10 minutes on the agent already.

1:39:15

If the test passed locally, we merge. And then, yes, sometimes main slips a little bit, but it's. It's usually very close because maybe sometimes I forget the. And the agents call it gate. I don't know where that's coming from. Should I run full gate? So now I call it gate. Full gate is like linting and building and checking and running all the tests. And I almost think it, like, because it's a wall, you know, like, it's like he calls the linter and the builder and the tester. It's almost like a gate before my code goes out. So I know. I always see, like, okay, once you're done, commit this. Run full gate. I'm slowly adopting their language.

1:39:17

And if you hired, like, one more person to work on this, you probably wouldn't do code reviews either. That's what I'm sensing. You'd probably trust this person to run, like, pick up your working style. Right.

1:39:54

Even in Discord, we don't talk code. We talk about architecture. Like, big decisions. You still need to have style. Like, there was, like, this one pull request that adds voice calling. So now, literally, I can tell Claude, hey, can you call this restaurant and reserve your seeds? And it can do that, but it's quite a big new module that touches a lot of places. I'm like, you have to have this feeling, this ick. I got a little bit of this ick. It's like, I want to merge this, but this is becoming bloatware. So I had this idea of, like, my typical way, let's make a cli out of it. And I already had a project where I tried to solve something like this. But I'm finished. So I opened up Codex and said, hey, look at this pr. Look at this project. Could we weave this feature in? I again say weave. I'm like, so, no, let's keep it. Could we weave this feature into the cli? What are the up and downsides? And then would like tell me, like, oh, yeah, I could do this and this and this. They give me honest opinion. Would this. To me, this sounds like it actually it would fit into the project. And it was like, yeah, you could get this and this. Benefits that we cannot do if we next have cli. Okay, but I don't like this. This is getting bloatware. Could we build a plugin architecture? And you know, one of the secret hacks on using AI effectively is you reference other products. Like I constantly tell it, look into this folder because I solved it there and I solved that there. And all the previous thinking I did to solve the problem. Well, AI is so good at this still to read the code and understand my ideas, I don't have to explain it again, or if I explain it again, I might make mistakes that wouldn't get across exactly the idea that I have in my head. So in this case, I know that Mario, who does shitty coding agent, which is like, actually very much not shitty coding agent, it's called py. I know that he had this plugin architecture that would load code via gt and because it's all typescript, so it was like, can you look into this folder and this folder? And then it just came up with this really insanely good plugin architecture. But again, by, like being inspired by other people. And then that's where, you know, I have this feeling. And then I came up with, yeah, that's what I built last night, basically.

1:40:05

I mean, sounds like this is going to be completely different. Like, you know, PRs are like in your workflow, you're not using PRs that much. CI is just different. It's tests are still doing. There's a more important feedback loop. Using things more like weaving instead of code, you're talking more about architecture and tastes. It sounds like a pretty big shift to me. Now, in this world, let's assume you get to the point where you hire the next one and two and three developers on this team. Let's imagine that this thing gets a life of its own and maybe it's a business as well. What skills would you look for and what would you advise an experienced engineer right now? Who would you be excited to work with? What kind of either expertise projects. Would you look for someone who sounds like. Who can work in this way or can pick up this way of working.

1:42:18

Someone who's active on GitHub and does open source, and someone where I have the feeling that they love the game. The way you learn in this new world is by trying stuff. And it very much feels like a game where you improve your skills as you get better. Like a music instrument. You have to keep trying that. I'm now this efficient and this fast. And I don't know, I think the other day I had like 600 commits in a single day. This is like completely nuts. And it works. It's not like there was a. Somebody did a code review and said like, oh, this is actually not slop. And like, yeah, there's a lot of skill.

1:43:05

I wanted to.

1:43:46

Yeah, it's a lot of hard work. But you need to play with the technology and learn and then you will get. In the beginning, it might be frustrating. I don't know. Kind of like you start going to the gym, it's gonna suck, it's gonna be painful. But very quickly you get better and you feel that your workflow gets faster and then you feel the improvements and then you slowly get hooked. But yeah, play and yeah, also work hard.

1:43:47

Yeah. I mean, you're putting in more hours into this thing.

1:44:19

I've never, right now, I've never. I never worked more. Even when I had my company, I've never worked so hard as I do now. Not because I have to, but because it's so addictive and so much fun. But also because right now I'm using the moment where this has traction and there's a lot of people who are pushing me and I feel, could it.

1:44:22

Be because I think you have pretty good business sense, not necessarily in the business business, but seeing when there's an opportunity, there is an opening for. To get traction. Right. Like what you said, for people to work in the open right now, it seems novel. You're telling me you don't think you could even if you wanted to hire. You don't think you could hire people because there's not many people working in the open. Clearly using these things. Fast forward two or three years from now, once a bunch of people start to do it and everyone does it, it's kind of like moot a little bit. So there's also that a group that a lot of people are worried about is the new grads, the people with no experience who are either in school or about to graduate. Because of course you've been an experienced engineer by the time this came around. You know, you have a lot of things to build on. Putting back yourself into shoes of someone like that and knowing what you know now, what would you recommend of activities that they do, things that they build or try and you know, like, would you recommend on focusing on the fundamentals of software engineering on this, on the agents, kind of mixing the two?

1:44:45

I would recommend them to be infinitely curious, yes. It's going to be harder to enter this market. It's absolutely going to be harder. And you need to build things to gain experience. I don't think you need to write a lot of code, but you need to, I don't know, you know, there's a lot of open source that is complex that you can like check out and learn and you have an infinitely patient machine that is able to explain you all the things. So you can ask, you can ask all questions. Why? Why was it built this way to like gain system understanding? But it requires real curiosity and I don't think universities right now are set up to teach you that in a really good way. This is usually something you discover through pain. It's not going to be easy for new people, but they have the benefit that they are not tainted by all the experience. They use agents in ways that we don't even think about. Again because they don't know that it doesn't work and by then it probably does.

1:45:48

And also their friends use it all the time.

1:46:43

Like the other day I, I have this little menu bar app for cost tracking on cursor and cloud code and everything and it was a bit slow so I was like, okay, let's do performance measurement. And my old way is I open instruments and click around and it would just call ixvis and do everything but a terminal. It blew me away. I didn't even have to open instruments anymore. It just made it faster and then did some recommendations. I'm like, all of that sounds good, do it.

1:46:45

Yeah. I think we might be underestimating both how resourceful people entering tech have been, also how young people. If I think about some of the great companies started, they were very young and obviously very inexperienced, but had a lot of passion. So that's there as well. Yeah, it's a big opportunity I'm especially taking in. I have to take it in. But all the things you mentioned about just your way weaving code in, not caring out pr, not carrying out code reviews, it's a big change because these things have been us with again for like 15 plus years of your life. They have been, in fact, a lot of it has been kind of solid building blocks of pspdf get right?

1:47:15

Yeah, we need a lot of new things. Even when I get a pr, I'm actually more interested in the prompts than in the code. I ask people to please add the prompts and some do. And I read the prompts more than I read the code because to me this is a way higher signal of like, how did you get to the solution? What did you actually ask? How much steering was involved then the actual output. To me this gives me more idea about the output. I don't have to read the code or like if someone wants a feature, I ask for a prompt request, like write it up really well because then I can just point my agent to the issue and we'll build it. So because the work is the thinking about how it should work and what the details are and if someone else does it for me, I can literally say build and it will work. And then yeah, of course I think about it, but it will really. Or if someone sends me a PR that has just a few fixes, I told people, please don't do that. It takes me 10 times more time to review that than just type in fix in Codex and wait a few minutes. So there's all these insane things that would have been completely different even in the beginning. Now we have a one liner, but for the last two weeks, like when it got really traction, I told people to just point an agent at the repository to configure it. So I didn't have an onboarding, but we had Claude code based onboarding where Claude would check out the git repository, read the things and write the configuration for those people and set everything up so it works like set up a launch agent that didn't have the manual setup because it was not a priority anymore because agents can now do that for you. And since the product was built by agents, they structured it exactly the way agents expect things to be named and saying there's certain ways that are encoded in the weights. How do you expect things to be named and everything exactly like how you expect. So they are really good at navigating their product. So it was not a priority to work on onboarding as much. I mean, eventually I wanted this magical experience, but it was more important to make sure that your message arrives and that things don't explode. So onboarding was literally like type this prompt into your agent. Which would have been mind blowing even a year ago.

1:47:54

All right, so to wrap up, we'll do some rapid questions. So I'll just ask and you tell me what's on your mind. What's a tool that is not a cli, not an id? It can be physical that you use you like you would recommend.

1:50:10

I buy a lot of gadgets and many of them dust away but. But there's this one kind of crappy thing that was not expensive that gives me almost unlimited amount of joy. And it's like this Android powered photo stand where I can upload pictures and where it has an email address and friends can send pictures and it will just show pictures and I put a few in my house again and I mean even the animations are a little crappy because it runs Android and it's terrible for my technology but. But it gives me infinite number of joy because it is low tech that just shows pictures and reminds me of happy moments in my life. And it was like 200 bucks and I don't know, to be honest, it gets me more joy than the latest iPhone. I bought the iPhone 17. I still haven't unpacked it because I just in my head I wanted it, but then I couldn't get around to it because it's just a hassle to move the sims around and basically no feelable benefit. But this little device gives me infinite joy.

1:50:23

What's something that helps you recharge outside of tech or just moving away from tech and screens?

1:51:25

What keeps me sane, even if I work crazy hours, is going to the gym. Even better, working with a coach and leaving my phone in the locker. And then I really have a good hour where I just feel me and I'm like in the moment and I'm not distracted by notifications or tempted to touch my phone, like we need more time for this or even sometimes I go for a walk and I leave my phone at home and it feels very scary. It's almost like. It's almost like an organ by now, you know, it's like your body knows where it is and if you don't know where your phone is, you freak out. I'm having a blast.

1:51:31

Love it. This is great, Pete, thanks very much. Well, this was a super interesting conversation and it feels to me that how one person teams build software with AI is already completely different to what we've been used to. One thing that really caught my attention is how Peter thinks in prompts and not pull requests and how he weaves in the code and no longer merges the code code. He doesn't find pull requests all that useful and would rather get prompt suggestions even on GitHub. I do think we might have to rethink the importance of prompts, or at the very least sharing of prompts in software development the more we use AI and AI agents Another thing that struck with me was Peter's emphasizing how important is to close the loop. As Peter explained, the reason AI is so good at coding but often mediocre at writing is because you can validate code. You can compile it, run tests, check the the output. So the secret to making AI system development work well is to design your system to close the loop and have the AI run the test. Finally, I was wondering if Peter is in the flow as much even when he's not writing code. Turns out he is. He's in the flow more than ever, and he told me that it's mentally more exhausting to juggle several AI agents in parallel than it was just to write code. My feeling is that someone who was a great developer without AI can be an excellent kind of code, code architecture or card or person with AI. This is just a gut feeling I've had so far, but Peter seems to prove it. Finally, we should note that cloudbot is more of a YOLO project than most production apps, so take the approaches that we discussed with a grain of salt. At the same time, I do think that a lot of what Peter does could well spread to building production code, except review and validation will become a much more important step in those projects. If you enjoy this podcast, please do subscribe on your favorite podcast platform and on YouTube. A special thank you if you also leave a rating on the show. Thanks and see you in the next one.

1:52:20