# Agentic Engineering: The New Software Workflow

**Podcast:** The Pragmatic Engineer Podcast
**Published:** 2026-01-28

## Transcript

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 ClaudeBot, claims he's doing.
Peter is a standout developer who built PSPDF kit, the PDF framework used on more than one billion devices.
Then he burnt 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 is building ClaudeBot, 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 engineer 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 the 11th February in San Francisco that I'm hosting with them, and our other season sponsors.
Right, Pete, welcome to the podcast.
Thanks for having me, Gage.
It is awesome to meet you in in person.
Yeah, I mean, and I almost messed it up.
Yeah.
What what what what happened?
You lost track of time.
Does that happen often?
And how how so?
Um, not usually.
Not usually.
Um, this is an interesting time for me, because uh because my latest project is blowing up Claude, right?
ClaudeBot, yeah.
ClaudeBot.
I'm struggling a bit to get enough sleep, but it's it's it's interesting.
I never I never had a community blowing up so fast, and it's just incredibly fun to work with.
So before we we get into Cloudbot and all the fun stuff you're doing, I want to rewind all the way way back.
You create a PSPDF kit, which uh is used, I think, on more than one billion devices, users.
If if you see a PDF render, you probably see that.
But even before that, how did you get into tech?
Oh my god.
How did you get into tech?
So I'm from U rural Austria.
Um always mobbing the introvert.
So eventually I we always had like summer guests, and one of them, one of them was uh was a computer nerd, and then I kind of got hooked with with like the machine he had and begged my mom to buy me one.
And ever since then, I this was in high school or so.
I guess I was 14.
Yeah.
And never since I started tinkering, like I 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 it.
It took like two minutes to load.
I was just always sinkering.
I also playing a lot of computer games, of course.
But like building stuff almost feels like playing a computer game.
Like definitely right now, it feels better than Victorio.
Oh, when I started out, uh I I I I read like the equivalent of bash scripts for Windows, and then I did like websites, so I guess a little bit of JavaScript, uh, even though I had no clue what I was doing.
And then the actual first language where I I had to learn how to build things is when I started university.
And I never met my dad, and I come from a from a poorer family, so I always had to work.
I had to had to finance my own studies, right?
So when other people were uh were having holiday, I just worked full-time at a company.
So the the first real job I had was 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 and my university.
And I kept working there for like I think five years.
And I remember the first day they they gave me this huge book.
Well, maybe that huge.
And it says Microsoft MFC.
Um I still have nightmares.
And I got I got like, I was like, this is terrible.
Like for the for the next win, I just I just silently used.NET.
I just didn't tell them.
And like a few months in, I just told them, yeah, but the tech stack I I did a few modernizations, so 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 my shit worked.
So uh I did.NET and actually I actually dig it.NET 2.0 had like generics.
It took insanely long for the application to to lo to launch because like it everything was compiled at first start, and like your hard disk was like if you remember.
So so you you how did you stumble into both iOS?
And where did the idea from PSPDF come from?
Not even yeah, the first one, and the first one wasn't even available in in in in Australia.
Yeah.
A little time goes like went on, and I was at university, and a friend showed me the iPhone, and I I think I I touched it for a minute, and then immediately bought one.
Like this, like it it clicked when I felt it.
And and the to me, this was like a wholly F moment because it was just like so different and so much better.
So I got I got one.
I was still not thinking about building for it, you know.
That was that was what one was this, 2009, 10, something like that.
Yeah, yeah.
And then I I used their browser.
I can't I can say the story.
I was I was literally driving in the subway.
And by the time I was using uh a gay dating app, and this was iPhone OS 2.
Yeah.
So I I Long time ago.
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 like scrolling was disabled.
So like this long message was like 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 that's where that's where the window came and I was like, where is the ID?
So it was like, like, I was like, this is unacceptable.
I basically hacked the website.
I used regular expressions to like download uh to parse the iHTML, which is like totally not something you should do.
And I built an app and I used I used uh iPhone OS 3 beta with like core data in beta, Reggex Kit Lite.
I used a hacked version of GCC that backported the blocks compiler so I could use blocks in iPhone OS3.
It took me quite a while until anything worked.
Because I had no idea what I was doing, and I was like using all kinds like beta tech.
But eventually I I got it to work.
And I I wrote that company is like, hey, I'm making an app, what do you think about it?
Got no response, of course.
So I was like, let's just put it in the app store.
And this was for the dating app, right?
Yeah.
So you just like, you know, you looked at you saw the APIs, you could just like easily like build a client on top of the API, it was HTML.
Oh.
I was I was just literally parsing HTML.
Oh, so so you kind of parse the HTML, kind of turn it into your own, you know, like you use it as an API.
Oh, clever.
I mean, that this is back in the day where no one thought this would happen, but I made I put it in the app store.
I charged five bucks for it, and I made like 10k in the first month.
And I had no clue what I was doing.
So and there was like so many complex tech stuff.
This was very early on, but there was a lot of weird forums on Apple.
Yeah.
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 the funny thing was when I this blew off.
And I remember I was in a club one day, and like I saw someone using my app.
And I was so proud.
And I wanted to like tap him on the shoulder and say, I built this, and I thought, like, probably really weird.
So I didn't.
And then I I I went to the company I worked for for five years and told him, like, I'm gonna pursue this.
This is this is really exciting.
And my boss was like mocking me.
Oh, really?
Like, oh, you're making a mistake.
This is a fed.
This will not go, blah, blah, blah, blah, blah.
And the way that got me, that's what you call an US a chip on your shoulder.
I'm like, you know, one day I'm gonna I'm gonna have a company that that's worth more money than yours.
Why took me eight years?
So I I got hooked.
Like I I worked.
I I'm I'm a little bit of an addictive personality, so which you see again right now, but I I worked a lot on this app.
I learned I learned in 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 at 3 a.m.
Um slightly intoxicated, and I got a call from a US member.
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.
Um it was a good until it lasted.
And I was just I just quit my my job and was like, well, f you Apple.
I did freelance work, I was at dubtub.
I was introduced to dub.being wdc.
Yes.
Sorry for the insider terms.
I was introduced to someone as one of the best iOS developers in Austria at a bar at 2 a.m.
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 I went to the Nokia development days.
And 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 it was like a magazine viewer, right?
This was back when the iPad just came out, and Steve Jobs said that like 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 I'll I'll help you out.
And I opened the app and it was like, oh, the worst code I've out iOS that I've ever seen in my life.
It was literally one file with like thousands of lines.
Double objective C.
Yes, where they used Windows as tabs.
I didn't I didn't know that worked.
I was surprised it worked at all.
But it felt like a house of cards.
And I I tried to I tried to surgically fix things, but like as soon as you touch something, something else would break.
Um, so I got it, I got it somewhat stabilized and told him like, look, this is this is like madness.
Um, I'm gonna rewrite this for you.
Yeah, but it took half a year.
I'm gonna do it in a month.
Well, it took me two months.
Um, I wasn't that far off.
And and then here I was working on a on a PDF viewer.
You know, another technical problem.
The domain is I wouldn't say like completely unimportant, but you can always find interesting problems in every domain.
And that was a lot of infringement 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 like uh very careful what you do in the background and when uh the the OS would just kill you.
I got really fixated at like making it good, like when rotation is like that the page would like animate.
And so you know, I I like 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.
Um, and then I I worked with them for a while, and then a friend texted me up, is like, yeah, I'm working on this magazine app and it's really hard.
I'm like, there's no way it's hard.
I know, like I did it.
You just built one.
And um and he was like, Yeah, can you can you can you get me the code?
I'm like, sure.
So I sold him, like I extracted the part that was PDF from this magazine app.
And I I made sure I made sure like the other person was okay.
And then I sold him that.
I was like, well, if he's interested in that, then why let's not try to sell it to other people?
I used uh a WordPress template and mutilated it to run on GitHub pages, and then and then when you did the the Fastland flow, at the end you got a Dropbox link to my personal Dropbox with a source code SIP.
And I've built this in on one afternoon, and I tweeted it, and and then in that week, three people bought it.
And 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 who complain 10 people who complained about it.
Um, because they wanted it, but it didn't have the features they wanted.
You know, it's like I got nerd sniped.
It's like, oh, I didn't have text selection.
Oh, how hard can it be three months later?
Oh, yeah, it's really hard.
Text selection in a PDF specifically.
Yeah, yeah, yeah, yeah.
You you know the saying?
The saying like uh the companies are built by young people because they don't know how hard it is.
Yes, yeah, yeah, I had no idea what an insane madness this file format is.
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 it 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 you to StatsIC, our presenting partner for the season.
StatsIC 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 StatsIC.
They shipped over 600 features behind feature flags, moving fast while projecting against metrics regression.
Microsoft, Atlashian, and Brex use StatsIC for the same reason.
It's the infrastructure that enables both speed and reliability at scale.
StatsIC has a generous freeze here 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 Statsig.com/slash pragmatic.
And now let's get back to Peter and why rendering PDFs was a surprisingly hard problem.
But now I remember there was a few weeks ago.
Someone emailed me.
They did something PDF when they wanted my help.
And I just put them like, I'm sorry, like I I did my deed.
I I know more about PDF than any any sane human person ever should know.
And when I went to therapy, good luck.
But that took off and I just I well was waiting for my visa.
I I worked on this project and it just kept on more people kept on buying it.
And you know, it was like it was like summer, I was, I was like lying at the lake, and I got another email that someone bought it for 600 bucks, 800 bucks, or just up the prices as it had more features.
And by the time I 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 I still thought like I have to be there, you know.
So I I did it, and also interestingly, at this company I had to do.
So you say that you moved to San Francisco?
Yeah, and and of course, also it ended up being something where I had to build some 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, uh Sabine, my manager came over and said this, Peter, are you okay?
And they gave me a choice uh to either keep working at this company and drop my project, or 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 on a complicated visa.
And well, the decision was quite easy.
It's like, yeah, I want to do my own thing.
And then at this point, it was already taking off.
You already saw that this is there's a big business here.
Yeah, it it will probably pay you as much as your US job would have paid.
Uh it was never money driven.
Uh it was more about what what what what were you driven by?
I wanna make stuff that other people find amazing.
Like I I love tweaking the details, I love those little delights.
It wasn't even that the space, there were competitors in the space, but my angle was always like I built something as if Apple would have built it.
Like like with with like all the love and care and and polish and and those little delights that a lot of people in industry don't get uh so even though we had competitors that had way more features and were around way longer my company was more successful and my product was more successful.
Because developers tried the the different ones and mine just felt the best.
I think soft is all about about how it feels much more so than the feature set.
Like why did we buy Apple stuff?
It hasn't more features than than Windows um but it it feels better.
So how did you go from like you you love 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 when I went back to Vienna then I was like okay I have to go all in and that's where I I started working with freelancers a little bit and way too late to be honest also like I I could have could have hired much earlier but you know you know it's it's it's a big step.
And that's kind of where it it started having a life of its own, and I spent pretty much 13 years of my career um 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 stuck PSVDF kit.
PS PDF finally get a renamed.
But I wouldn't have I wouldn't have renamed it.
But now it it it it's it's it's a mouthful, but it's very unique.
Well, you get it if you do objective C because it's just a namespace.
Yes.
And by by the time it it it made perfect sense.
My marketing my strategy for marketing was always I only care about the developer.
Like I know like 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 like cold cold emails or aggressive, it was all inbound.
All we did was like make good stuff and write insightful technical blog posts that and I went to a lot of conferences.
Like the for me part of it was okay.
If if people understand that the people who built this product are like know what they do and and love what they do, that reflects on the product.
And that worked really well.
And then what was the text type behind PS PDF kit?
Was it Objective C?
Was it later Swift?
Were there other technologies like C or or anything else?
We eventually expanded to to all the platforms.
Um big shift was to switch out Apples renderer, which was and years still quite buggy, to like a big C1 that one then we used across all the frameworks.
Um we we were we were really early with Web.
We were one of the first PDF frameworks that ran in WebAssembly.
And I I did the most clever thing that I did was in the very early days when WebAssembly was just taking off, and we built a benchmark.
And that benchmark was eventually used by by Google and Microsoft and Apple.
And I basically had all these companies like working really hard and making my renderer faster.
Cause cuz because they used their benchmark as one of their benchmarks, and the benchmark was just like rendering our stuff with our shit.
Oh nice.
And then as as a company grew, one thing that I remember about PSPDF kit, uh you did write a lot of blogs.
And one blog in 2019, so this was about like I think you know year nine or ten in the company.
It was about how the team worked.
And you you mentioned things there, like every feature starts with a proposal.
You mentioned that you are conservative because it's uh it's a big API that the people use, you want to be careful.
Things like the Boy Scout rules to refactor.
How how how did you kind of put together the the the culture of this now this team which was now closer to 30 or 60 people?
You were actually 70 when I sold my shares and now it's almost 200.
And I I knew right from the get-go, is like I'm not gonna find the people that I need in Vienna.
So it was always just like remote first, and eventually we we we ended up with some kind of hybrid model, uh, which made things a bit more complicated.
I learned a whole lot on the go.
Like I I never had the urge to be CEO, I always was coding.
I eventually I even I brought people in, two people that that helped me a lot with other other parts, uh, and on the business side.
I can do it, and I I think I think I'm I'm quite good at it, but just don't enjoy it.
Like being on sales calls where you like have to like think about the magic number, how much it would be worse because that's how enterprise works.
Ugh, worse.
Peter just said, uh, 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 season 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 WorkWas introduced MCP Auth, which gives teams a way to authenticate AI agents with explicit permissions, auditability, and enterprise great security.
Instead of sharing over scoped API keys, you can define clear boundaries for the data that agents can access and the agents they can perform.
If you're building AI power features and want to share fast without compromising security, check out workouts.com/slash mcp.
And with this, let's get back to Peter and enterprise pricing.
But that's also the only thing that that really works on a model like this.
Yeah, you mean enterprise sales specifically.
Yeah, right.
Meaning custom pricing.
So can you sell us for for for you know 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?
Oh, that's that's right, because we're 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 tear it down to a specific number, like it it's it makes a difference if uh a freelancer contacts us or one of the big Fortune 500s, let's not say names.
Yeah, 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 if I if I go to low, they're gonna see this fishy.
It's like uh procurement for like 500 bucks, we're not gonna even start the process.
And if we we target it too high, we're 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, you know, on software, there is I would say there's like four axes.
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 gonna be a hard sell.
It's it's a hard sell anyhow.
Yeah, selling anything to developers is a hard sell.
Yeah, but if it's 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.
You you you need to tell me, tell me one or two hard things about parsing PDF.
How hard could it be?
Yeah.
If there's a specification.
I'm an engineer, I know specifications.
I what's so hard about it?
Yeah, I mean, there's not this one example where you know, like PDF has they have links.
So like there's 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 the assumption, oh yeah, maybe there's like a hundred or four hundred links in there.
But then we got this one customer who like paid really good money, and then it's send us like, 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.
And it had like it had like more than 100 links per page.
500,000 links.
My data model completely exploded because my assumptions were off by a number of what 1000.
But by then you have like a mature product with an API.
So, like, how do you how do you completely redesign the internal part without breaking things for everyone?
Like suddenly everything has to be lazy.
But before parsing 101 was easy, but now they were like this was like so difficult to keep it working for people.
Um I think I spent like two months just on that, completely redesigning like the internals and like making sure it's still easy for people.
They don't have to know what we what we load easy, what we load lazy, or if you copy the thing, it still has to like have to keep some connection.
It needs to keep the references and and some of those things.
So and I I love to do support, and I think that that was also a confining factor why the company worked.
Because if if you send a ticket and then the the CEO replies and helps you out, um, that has impact.
And my my strategy was always like I always used to list in reverse.
Because if you 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.
Yeah.
So yeah, and then this uh this was one of the problems where I worked uh two months and I finally got it down to almost like this.
That must have been satisfying.
And and it was that was very satisfying.
And you were writing a lot a lot of the code, or you were involved in in a bunch of the code.
Like obviously, big big team was now here, but you're still kind of overseeing it, right?
Or in the details.
I mean, of course, I had a really great team, and and some parts I was more involved.
I was always more involved in mobile because that's where my my heart was, but I was always very deep in the tech and and uh the marketing side, the business side, I had like Jonathan's hub, I had Martin's out, those I I found good people.
The 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.
This is what I remember at PSPDF kid that your blog was every now and then it with me, it's a hacker news as well, but it was just interesting to read.
And I couldn't name again, I 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 or ship is still there, by the way.
I I I myself also sometimes ask myself, like, hmm, interesting.
Do more companies not see this?
Or is is the question that you 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.
I like sharing and and and like inspiring people.
Um 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.
Um I just you know, and there's also like when you when you write something down, there's 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 like preserve it and like help others.
So so I I got I got a gig off it.
Of course, of course, I liked the attention.
Um, but really it it was this sometimes.
I just referenced a year later to my own post.
It's like, yeah, this this is a it is supposed company documentation.
This is like my my own lookbook.
It's helpful in so many ways, and a lot of those bigger companies, oh, they put on too much red tape.
There's a lot of developers who don't really like to write.
So I I I forced everyone once a month, a full day, just to write a blog post.
But you gave them the time.
You're like that day, you don't need to do any other work, but write something.
Yeah, you have yeah, you have a day to come up with a post.
Uh a day is is quite much, actually.
I mean, when I'm 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 the starting time of the company is the most interesting.
The then the the growth phase, you get more red tape, you get more people.
It's much more gardening your product instead of like doing doing white hacks.
Um and more iterative.
So it got a little bit less interesting uh over the years, and there was like more people drama, because the more that's just so 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.
What what burnt you out, do you think?
Uh I was just burning too hard.
I was working most weekends.
I I I tried to shuffle all my material needs.
And you know, as a CEO, you're basically the waste bin.
Because everything, everything that other people don't manage or or can do or or mess up, you have to fix.
And it's also quite lonely because you you can't openly talk about a lot of things.
I mean, I I I I I structured the company to be quite open.
But still, like you cannot, you cannot be negative.
You have to even if even if like even if like really bad stuff happens.
I know that was like there was like one weekend where my co-founder called me at 5 a.m.
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 proof that they messed around with our source code to try to triggering a uh triggering a license key fallback uh that eventually like cost you should they had.
But that was like a if the sue us company's gone and more moment.
Um and that's just on top to all additional stress, and there were quite a few of those things.
You can do that for a while.
And I I also believe like burnout doesn't necessarily come from working too much.
It it comes more from, or at least for me, when you when you work on something, but you don't believe in it anymore, or you have like too many conflicts, and and uh we also had a uh we did find a lot in the team uh with like management team.
And by the time I I I made this mistake and I thought you have to like lead a company more democratically.
Um so that was also something that burned me out.
I wouldn't I wouldn't want to miss it for the world though.
Yeah.
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 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 is 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 uh outside again on your blog, the blog post completely stopped for several years.
What what did you do uh in in this time?
Uh and and what what what did you learn in this time you know before you came back to where we are now?
I needed a lot of time to decompress.
I I catched up a lot on the things I thought I missed.
I I party a lot.
Um 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 would definitely was like why border, you know, you're not you're not supposed 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 that was some that was some hard years.
And then in in April, I was like, I there was this idea that I had years ago, and even a side project that I started, it's like, oh yeah, I wanna I want to continue in that.
And then after after after more than three years, I just sat back to my computer and started hacking again.
But the thing was, this was like a a Twitter analytics thing, and it was written in in Swift and Swift UI, and uh back then I already knew uh this would have would be so much better if I would build as a website.
So, was this an existing idea that you kind of had at the back of your your mind something, something Twitter analytic?
Yeah, it was just like something I wanted to build for myself, yeah.
Cause uh 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 I went back and I I wanted to build it in in with web tech.
But web was really was always even at my company the one thing uh that I looked into the least because I had I had someone really smart who took care of of that side in the company that I brought in Martin so I never had to worry about it.
That was one of the you're not hands on what React or any of that stuff yeah and when I came back I was like what's a prop.
You know that that level where you really and you know this is like this is a a a trap I see with many developers the the better you get at one technology the hard it is to jump somewhere else it's not that you can't do it but it hurts so much you're like I can't I can program in in in in in in Apple Stack.
I can program blind but then in that stack I have to Google the most mundane stuff and it it just like an idiot again.
Yeah, and and I guess the more experience you have it it it kind of sucks feeling.
I mean, I'm sure you say embrace and and all that, but it's it's not great.
You're not as efficient, you know that you could be faster, etc.
Yeah, so so I came back and I was like, gosh, there has to be there has to be what is this AI?
What is this AI stuff that I re that that that people are dismissing?
Let's look into this.
Yeah, and in April, a lot of us were dismissing it, uh, probably for rightfully so, but and I and I and I like it and I to a degree I 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.
Yeah, the the people who like as about to say, so you missed out on you didn't do the beta of GitHub Copilot, you know, glorified autocomplete, which is GPC three, or or maybe not even.
There was then of course 3.5, which is a big jump, and it it got increasingly better than GPT four.
And so by the time you came back, what tool did you first use when you because you missed out on like two years of like like devs us devs using, dismissing, finding some niche use cases for it.
Oh, cloud code.
So you start with clock code.
That I think I came out.
It came out of May, but there was a beta beforehand.
Yeah, yeah, uh, I think they had something, didn't they have something in February already?
Uh they had a beta from February, correct.
Yeah, so so clo clock was was your first you you you come back after like uh you know hiatus and you immediately turned on clock code and you missed everything else before.
And you know, you know, it was like I I remember I took this big, messy side project that I built, and I have this browser extension where that that converts a GitHub repository into one big markdown.
So it was like a 1.3 megabyte markdown file, and I dragged it into into Google CI Studio with Terminat 2.5 or two to something, and I type, 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, um, and eventually told me like it's 100% production ready.
And I started it and it crashed.
I'm sure we can all relate to the story of the AI saying the code is production ready and 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 seasonal sponsor, Sonar.
So let's look at some data.
A new report from Sonar, the state of code developer server 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.
Sonarcube is precisely built to solve this code verification issue.
Sonar has been the 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 slash Skype, and a bunch of teams already use Sonar Cube to improve the quality of their code.
I've been advanced 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.com/slash pragmatic.
With this, let's get back to Peter and how AI agents cannot exactly be trusted.
But then I had then I edit edit an MCP so it could use the browser.
I think a playwright 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.
And this was like in April or May this year, right?
Yeah.
It was, it was it was just good enough that I could see the potential.
And I I understood it's like, yeah, this is this is where it's going.
And and from that moment on, I I had a few months where I had really trouble sleeping.
And I in I I remember because once uh on on Twitter I sent you a direct message.
I was up early for valid reasons, you know, my my kids or something like that.
But it was 5 a.m.
and I 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 I usually I'm still usually awake.
And and I asked, like, why?
And you said, like, oh, I'm I'm just like using Claude and it's really, really addictive.
And I was like, really?
And you're like, yeah, I'm I'm not joking.
Like, it's really good.
And I think that was the thing.
You said something or wrote something, like just one more prompt.
Like you told me how.
Like, what what made it so addictive?
Or what what still makes it so addictive?
Oh, it's the same economics as as you go to a casino.
That's that's it's my little slot machines.
You know, you you you you you you press the trigger and it's like ding ding-ding ding ding and it's like nope.
You have in the prompt and it it it was like and it does it, it does crap, or it does something that actually blows your mind.
And it's this and and you're saying it does it blows your mind as like you're a really experienced developer, like it's it's not easy to blow your mind, right?
Like you've you you you've seen good code, you you can differentiate like crap code, decent code, good enough code, like you have a bar, right?
It's so funny, you know.
I 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?
That the customer doesn't see it the insights.
Of 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 did I bike shit there?
Is like estupido.
You say that, but then you also just said that people loved PSPDF kit because it was the most polished, it worked the best.
Do you not think that that that amount of caring, bike shedding, as you call it, being obsessed?
It sounded like you were keeping tech depth at bay, you know, like being obsessed with white spaces, it's it's not gonna be messy.
And we know it's not just the white spaces.
We know you're gonna care about testing and all that.
Like it sounds to me that PSPDF kit, like you know, like 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.
Is how do you think about it?
Yeah, yeah, yeah.
To a degree, yes.
And and even now, like I I mean, like my my last blog post was uh confession that I I ship coded on read.
And yeah, we have to talk about that.
And at the same time, I spend so much time to like restructuring.
I mean, I mean, heck, even today, like I I really wanted to get this PR in where it was like 15,000 line change, right?
In my list, for 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 like you parse it, you package into a different form, you store it in a database as a different form, it comes out again into different form.
Then it's like HTML or whatever, and you're typing something, it gives it's a different form again, and all you do is like you're massaging data in different forms throughout your app.
This is what most apps are.
We are pretty JSON printers.
And the and the the really the hard part is solved by Postgres 30 years ago by some neckbirds.
Uh that's that's really what a lot of software is.
Like there's always some interesting parts, but I don't have to care how this button is aligned or which Tailwind class is used, or or like many details are boring, and many other details are interesting.
But it I think it's much more about system architecture than having to read every single line.
Right now, jumping forward, what is your workflow like?
Like when you're working on CloudBot, are you using a terminal, multiple terminals, which which tools and and how are you, you know, like you said you're not you're kind of like not reviewing the the code, but you're still thinking about architecture.
Like, what is your average day look like in terms of tooling?
You know, you had to explain to a developer who might join the team, you know.
At one point you think, like, what does it look like?
It's interesting.
Let's let's let's go a little bit.
We were we were in in 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 did it.
I I I used Gemini 2.5 a bit, then we had this phase with Opus 4.
I hooked up a lot of my friends.
Like I know, I know both Armin and Mario from Vienna.
They got they got AI pilled because I I was addictive.
My my entheism was like confusing them, and then they tried it out, and then and then eventually they also were up at 5 a.m.
And I called it like the black eye club.
I mean, I mean there's a reason.
Like I I started a meetup in London that I called called uh Cloud Code Anonymous.
Because it's so it's so much fun.
Like to me, what 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 like I I'm this this friction where I talked about where I'm so good at this at this technology and I'm like so bad at this.
And I'm like, oh let's make the CLI and go.
I have no clue about Go, but I have I have a good system understanding.
And once you have that, it's like you you develop a feeling what's right, what's wrong.
Like it's it it it is a skill in itself.
I remember there was this tweet where someone said, Oh, yeah, when you write the code, you you feel the friction, and that's why that's how you make good architecture.
I feel the same friction when I prompt.
Because I I see the code flying by, I see how long it takes, I see if if like the agent pushes back.
Um I see if what it creates looks like messy or like makes sense.
When I prompt, I I have a hinge already how long it's gonna take.
If it takes much longer, I understand that I messed up somewhere.
You kind of feel the model.
You you you know you know how usually it's like this, or if it runs.
I feel I feel it's very much a symbiosis.
Like I I learned to to talk, may I even say there or that language more?
So it's like my my knowledge how to use those things improved, and also the models improved, and then and then like over the time between between April and now, I would say yeah, the inflection point was summer, where it just got so good that you could you create software without actually writing code by hand.
But the real that change that like sold it for me is was again GPT 5.2.
That was again, I think it's underrated.
I don't know, I don't know why why all these people still use cloud code.
I I I kinda get it, it's it's a different way of working.
But whatever open AI cooked there is insanely good.
Pretty much every prompt I type gives me the result I want, which is insane.
Like like on on CloudBot, the my latest product, 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 met that team, and and they created a whole new category.
Like cloud code is is is a category defining product, and it is amazing for general purpose computer work, and it is is really good for coding.
And I I still use it almost every day.
But for writing code in complex applications, codex is just so much better because it it takes 10 times longer.
Um cloud would read three files and then be confident enough to just like create code, and then you really have to steer it and push it so it reads more code, so it gets it sees a bigger picture of your code base so that it it weaves in new features better.
And codex will just like be silent and just read files for 10 minutes.
And if you are if you only work on one terminal, I completely understand how you how you find this unbearable.
But I rather have something where it's also you don't tell it what to do, you know.
It's just this is also something that people don't get.
Like I have a conversation with the model.
It's like, oh, let's look at this.
What what what options do we have for this structure?
Did you consider this feature?
It's like because every every session is like the model starts from having no understanding about your product, and you have and 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.
Uh, there's some trigger words because it 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.
Um so a lot of 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.
Yeah, it's like what about like I say then you remind him it's like okay, we need documentation.
What would be a good spot?
It would like give me some recommendations or 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 I have this system understanding about how is my my product, how it is shapes looking.
I don't have a line-by-line code understanding.
That's that's what codex does for me.
But I'm the architect, you know.
It sounds a little bit like you're almost, you know, for ever years back, this this totally came out 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 fell 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 you you know, again, like I I think as people you kind of want more.
The architect is never on call for for this stuff, and so it just kind of breaks out 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 make 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 who do the code, except in this case, you are, of course, full responsible because you're still an individual contributor.
You're not, you're not like a okay, you might say you're a manager of agents or whatnot, but the code is is yours, it's your responsibility.
You're gonna be on call if you know if you push out code that takes down Claudbot, which it did just recently, you're on the hook for it, right?
Like and I think the the difference in this system when when it was in in companies, it was the architect was kind of shielded from the output of their work because there's so much people and so much process, etc.
Well, I wouldn't say architect, I I like the word builder, builder, yeah.
And and and I think also that's there's a few categories that I see for people that are highly successful using 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 to the not the biggest detail.
And then there are people who really love to to code on hard problems, like think about algorithms, don't really like the I'm building a product with like all the marketing or the they they more like they like to solve hard problems, and those are the people who really struggle and and and often reject AI or get really sad because that's exactly the job where that AI does.
Like it solves the hard problems.
Now sometimes I give it some pointers but many times I learned I learned more this year than the last five years around around software architecture and designing I the there's so much inside those monsters um on knowledge and everything is just a question away but you have to know what question to ask.
Of course I also put this Twitter thing and it's still not done and I and I I really hope I I'll get back to it that one one time.
Everything worked but if I used it more at some point things got really laggy and weird and then it worked again.
And I just couldn't figure it out and it was like 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 like software in in in in PSQL like in Postgres that would be triggered when certain inserts were were were doing and then the database would would get really busy and the model couldn't see it because it was it was it was so far abstracted from all the you know like the those 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, um, 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 uh, I everything is just the right question away.
Yeah, but you you you need to have like knowledge, expertise, yeah, yeah, you know, experience.
I mean, so so these are the people who rejected, and then the people who 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 you know, when you run a company and then you hire people, you can't breed on everyone's neck and like make them have the line of code exactly that way.
And there's a lot of people who who didn't manage a team and had this experience, how to 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 like not perfect, we can always make it better and like 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 so then when I when I had cloud code, it kind of felt like I have like I have like imperfect, sometimes silly, but sometimes very brilliant engineers that I have to steer and where we where we work together on a common goal.
It felt a lot like being the boss again.
Yeah, and interesting.
Now, you know, you you built kind of software, I guess, the traditional way, you know, pre-AI for 15 years or even more than 15 years, and you got really good at being also leading a team and then how to have high standards.
You really cared about the the craft there as well.
You've now kind of been, I guess, byte coding or working with agents for a year.
You're comparing the two.
What do you think?
What do you think really really changed?
And what do you think are things that kind of stayed the same despite of first of all?
I don't like I don't like the term vibe code.
All right.
How should we call it?
I I think I think I think vibe coding is by now almost a slow.
Oh yeah.
I I I call it I tell people I do what I do is a gentic engineering with a little star.
Vibe coding starts at 3 a.m.
Now, like because all the the mundane stuff of writing code is automated away, I can move so much faster, but also means like I have to think so much more.
I'm still very much in the flow.
Like it it is it is completely the same feeling as for me as uh I I very much get in this flow state.
But it is mentally even more taxing because I have I don't have one employee that I manage, I have like five or ten 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 in a subsystem or like this feature, and then I know that it will probably take codex like 40 minutes or or one hour to build.
So like I wanna like have the plan right and then I build it, and then I'll 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'll go back to this one.
So, like I I I I switch around a lot in my head, and wish I wouldn't have to do that.
Like I I'm sure this is a transitionary problem, and uh at some point, we have we have models and and systems that are so fast that I can paralyze a little less, but to stay in the float flow state, I need to massively parallelize.
So that that's that's how it works.
Now I go back to there and and maybe tweak it a little bit more, but usually just like try it out.
Uh maybe then this is ready because this took only took like 20 minutes.
So like I constantly jump around.
Usually there's there's one main project that has my focus, and I have like some satellite projects that also need attention.
But where I can make maybe I spend five minutes, it does something for half an hour, and and then I try it, and it doesn't need uh so much capacity up there.
This almost sounds, you know, like two things come to mind.
One is there is these like games where you have to manage a kitchen with the employee, and and you see like the recipes or something come out, and you need to jump and do it.
You know, they have like your main base and you have like your side bases that give you resources.
That as well, and also one thing that just came to mind as you said, like I go there and I watch this and I make a decision.
Is when I see the chess grandmasters play multiple boards at once, you know.
See you see like sometimes they have 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 brain, you're occupying your bay, and you're you're kind of just scaling yourself as long as you can context switch.
The difference, the difference was uh up until this with cloud code.
I 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 it forgot to update three other things, it crashes, or uh you give it uh the the good thing about 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.
Um that's also something I I think that's part of why I got so much more effective.
Um but yeah, with cloud code, you I often had to go back and like fix up the stuff.
Um it just takes a lot of iterations.
So in the end, it's not that much faster, it's just more interactive.
And and these days with Codex, it just almost always gets it right.
My my general strategy is always I I build a feature, of course, you and then you of course you always let it write tests and you make sure that it runs itself.
It runs them, yes.
So even when I write a Mac app, I don't know.
I guess I I just yesterday I debugged this feature where the Mac app couldn't find a remote gateway, but like the the same coding type script could, but it Macup 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 tell it like, you know, you're gonna 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 there was a race condition here and here, and like a misconfiguration, blah, blah, blah.
I'm like, yeah, sounds sensible.
I don't need to, I don't need to see that code.
It's like but 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 I guess it's not too dissimilar to like sometimes when you work on a large project in a large company, when all the tests pass, I mean it doesn't mean that 100% is there, but it's it's a pretty good and and all the new new new code has tests as well.
You know, someone thought about it and tested it and all that.
So even even on my on the very latest project, we always had bugs for like anti-gravity has like a certain a certain weirdness with how it takes tool calls in the loop in the in the format, so you have to do like some filtering.
Yeah.
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 live 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 still tell tool calling.
Make it work.
And then it solves itself.
It took forever, but it it it tested all my API keys, like from from Entropic over SETAI 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 and that's that's and closing the loop, you mean just have a way to have the agent be able to validate its work.
That's why that's the whole reason why those models that we currently have are so good at coding, but like 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, even now for websites, I built the core in a way that can be run via a CLI.
So like I have this, I have this perfect uh execution loop because the browser loop is insanely slow.
You want something that that loops fast.
So it sounds like one thing that is not really changing from like before is we had this before, like backend or business logic heavy heavy thing could easily be or more easily be verified that it's correct.
Surprise, actually, using agent decoding makes you a better coder because you have to have to think harder about your your your architecture so that it's easier verifiable because verifying is the way how to make things good.
Well, then remember back back even before AI, for complex systems, like once you got someone who built these things before what they started with, how do we make it testable, right?
Like you you need to design interfaces, classes, testable.
You need to think about like, 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 like really hard architectural decisions, and once you make them it, they're, I guess, harder to change.
And in your in your word, you know, like the model would cook a lot longer if you asked it to make a massive refactor.
And you know, if you have tested, I'll get it, right?
But you know how these we we still have these trade-offs.
It's still it's still software.
It's it's I I would say I write better code now that I don't write code myself anymore.
And I wrote really good code, but uh, but like even back at the company, uh, sometimes testing was so tedious.
And you come up with all those edge cases and and and the branching.
I mean, outside of Ken de Beck, who I deeply respect, and he was on the podcast, and we we we talk, like he he still writes tests first, and he tells me that he's not mad at me for not writing it, but if you want to write like you know, poor quality code, it's on you.
Uh, but I don't know many developers, myself included.
I never liked writing tests.
And even when I pretended that I did, I I just never did it's a little bit like writing documentation and writing tests.
To me, it was never a creative expression.
It is so good now.
Like, I I would say for my last project, I have really good documentation, and I didn't write a single line myself.
Like, no, I don't write the test, I don't know the documentation.
I explained the model the trade-off.
So, so like, why we did something like this, and then tell it like it like 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 we design a feature, this is a part of this a part of the process.
And also like testing.
I'm almost like, okay, we built this.
How are we gonna test this?
Yeah, we could do this and this and this.
What if you build it this way?
And oh yeah, then we can test it better.
So it's like this is now part of my thinking because I I always think like, how do I close the loop?
How do I the model always needs to be able to verify the work itself?
Um, which automatically steers me to better architecture.
So why do you think there's you know a bunch of like experienced devs who are still pushing quite a bit back on on just like the idea that AI can do a lot of this?
That was a week ago.
I I stumbled over uh a blog post by McGallagher, Coco with Love, that I deeply respect and learn a lot from.
And this blog post was just a dissing of the current way how models work.
And and what he did was he he tested like five or six models, including some that make no sense, like the the open EI 120 billion open source one.
It's not good enough to write good code, you know.
It's like and he just he wrote a prompt.
As far as I understand it, there was there was not a lot of information on the episode, but uh to me it sounded like he wrote a prompt, he put it on cloud web, and and he pressed send.
And then he took the output and ran it, and it didn't compile, and then he was disappointed.
But he's like, of course it will not work.
Do you think I can write buck free code on the first attempt?
And then those little those 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.
Like 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.
It's like yo, you do he complained that it used old API.
Yeah, you didn't specify the macOS version.
So it's so so it made an assumption to default to like old API because that information was missing.
And it is 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 the better you get at prompting.
Um then and then he he spent maybe I don't know, a day or so on 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.
You know, it's it's like it's like you know how to play guitar, and I put you on the piano and you tried a bit, it's like, oh, this sucks.
I'll go back to my guitar.
No, no, it's like it's it's it's a different way of building, it's a different way of thinking.
You have no idea how often I screamed that like 3 a.m.
to cloud code because it did something silly.
Uh I slowly started to understand why those things do what they do, with like exactly the way I tell it to do things, and sometimes you can literally ask, you can even even last like I for this project, uh the last project, like Cloudboard, I feel like a human merge button because the community is like blowing off, and all I do is like reviewing PRs.
I I I have very little time to actually write code myself anymore.
And in the beginning, it would often like just cherry pick things and would close the PR and it was like so annoyed.
So I'm like, why are you doing this?
Yeah, when you say this and this, I interpret this this and this.
It was like, ah, like I I learned the language of the machine a little bit more.
I tweaked my my prompting, and now I get exactly what I want.
Because it's it's a skill like any other skill.
Yeah, and this is like Simon Willison has been saying the same thing, even though he's been using it for years.
And I think everyone, I think once I start to use it, I also realize like I'm not I'm okay at it, but I I 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 CloudBot, which is a you know, it's it's not something that generates revenue, there's a lot of users and it's blowing up, and it's it's a really cool tool, but it's not PSPDF kit, which is a business that it's a lot of revenue is hinging over it.
If today, you know, we just wiped PSPDF kit does not exist, you need to rebuild PSPDF kit.
You now have these agents.
How differently would it look?
How much would you trust it?
What would you delegate?
What you would you validate?
And and when you know you built up a team uh around it because now it's a profitable business, at the very least, you need to hire salespeople or whatnot.
How do you think the team would look different today with that same product?
Because you you know exactly what it took to build it, and you also know what these tools can do 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 you you want you want to have really senior engineers that really understand what they build, but uh that are also comfortable in in delegating and know which parts are actually important to to work on and which parts I can vibe.
That's still something I don't see, I don't see a lot.
Like especially in the AI world, there's so much crap on Twitter.
There's so many people that are loud but clearly have no clue what they're doing.
Uh yeah, there's so many there's so many dumb concepts around.
Like, I'm sorry, but the Ralph Wiggum one, uh, like this is again another another silliness people use to work around uh model limitations of of of opus.
You don't even need when you use codecs.
There'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 like beads that automatically creates tickets, and then your agent does tickets, and then your agent emails the other agent, and then you build up this this elaborate mess.
What for?
Oh yeah, they did they design the spec for like a few hours and then you just like the machine builds it in the whole day.
I don't I don't believe this works.
Like this is this is you this is the waterfall model of software building.
This we learned long ago that this doesn't work.
Like maybe yes, people work differently, and maybe it does work for some.
I just I just I don't see how this how this could work for me.
Like I have to start with an idea, and often I purposefully underprompt the agent so it would do something that would give me new ideas.
You're like maybe like 80% of the things assumed by like crap, but like there are like two things are like, oh I didn't think about that way.
And then I I I iterate and and and shape the project, and I have to I have to click it, I have to like I have to feel it.
I feel I feel to make good software.
I you know the one thing that those those things often lack is taste.
I have to feel like how does this feature feel?
And then the beauty now is that features are so easy, I can just like throw it away or like 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, no, let's do this.
And it's like it's like shaping.
I love how this like you start with a rock and then you like sizzle away at it, like pick different areas and then and then slowly like this statue emerges out of out of marvel that's that's how I see that's how I see building something.
I I guess reflecting on how software engineers changing this seems like a change because before before we had AI or any of these agents upfront planning did make a difference.
You know writing at PSPDF could you 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 to build to to ex Do you think this is changing because of the the cost of just writing code is is going down or I mean it's still I still I feel plan.
And I but you still do yes but I don't put as much into it because I it's now so much easier to just like try and look at the results and then see if oh yeah this this shape could work or no we have to like the tweaking and even even like oh no we have to like do it a completely different way is now so much cheaper that it's to me it became much more playful.
Yeah, yeah, I guess because because like you know, when you're working, even if you have like a new grad on the team or an intern, you know, you give them something, they work in it for a day or two.
Now you give them another, it's another day or two.
You know.
And and we're not talking days here, we're talking minutes, or like if it's a long-running task, like 10, 20 minutes up at worst.
Plus, you're not just waiting on that thing, you have parallel things running.
So it's not that much of a waste, if you will.
In in the in in in in in cloud, but in at the beginning I had this assumption of like one agent, and then eventually changed to multiple agents.
And there was an assumption of like one provider like WhatsApp, and now it's multiple ones.
And changing that was like such a pain.
Would 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 I could have realized that in the beginning, but now I I know that like I can just change things.
And it's it's much it's 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 the project.
That's why I don't believe in I don't know, things like guest town, where like you write up the spec and then it builds itself and then it's done.
Uh how can you even know what you want to build before you build it?
You learn so much in the process of building it that will go back into your thinking of how this how the how the system actually will end up being.
To me, it it this is very much it is very much a circle.
Um until I you don't I don't you don't walk up the mountain like this.
You go you go around, and sometimes you like you you you stray off a little bit of paths, but uh but eventually you you you reach the top.
That's that's how I I feel soft serious.
Then you know you've been building CloudBot for what like two months, three months non-stop-ish.
Or like how long let me let me let's switch a little bit gear.
So, one of the ideas that got me back was even even in in April, May, was I I wanted to have this hyper personal assistant.
Not like 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 and then uh when I go home, it would ping me, hey, how was 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 he's in town right now because I checked his Instagram account.
They wanna 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, something that is deeply personal, um, like almost uh the anti-ORM.
It's kind of like the movie her, but but that's where the technology is going.
Those models are really good at understanding text.
They the the bigger the context is, the more patterns they see.
And even though they are like matrix canculations without a soul, it very often feels different.
So this was like one of these ideas, and I even created a company I called a Mantus Machina, like the loving machine.
But in summer, when I explored it, the models weren't quite there yet.
I got some results so that it was like, okay, this is like I'm a little too much on the edge of what I need right now.
Which it was very exciting because I know that the the state of AI goes so fast that oh, I can just revisit that in like a little later.
And and one of the ideas also was is that I assume that all of the big corporations right now are very much working on personal assistance.
In the future, yeah, everyone will have you will have your best friend who is uh a freaking machine that will understand you, that will know everything from you, that will 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 like more and more people as we learn how to build more efficient systems and and and hook up on chips.
No question, this is where the things are going.
You see, like the first things with like OpenEI who launched Pulse with some proactivity, but we just don't have enough compute yet to offer this as a feature, and also it's it's quite difficult.
My idea was like uh I kind of want something that runs on my computer and where the data is yours, is is actually mine, and not and it's also quite scary that like you you give open air and tropic access to your email, your calendar, your your dating apps.
I don't know if you talk to to to your normie friends, but a lot of my friends in in that they use that a lot to basically have a therapist, and it it does work incredibly well.
Like it's it's a really great listener, it understands your problems.
And unless like some of the versions of 4.0 that are like, sure, this is a great idea.
I want to put French fries into a salad.
It it works really well.
And I did that too.
Like to like re I mean uh part of it just is like the the act of reflecting already is helping you.
So you it would even work if the machine would only repeat exactly what you wrote to a degree, but it actually gives insightful questions.
It's actually it it got really good.
So I had this idea of this like assistant, but the tech wasn't there, so I did other part and I I built a whole bunch of fun stuff with like of course like a built vibe tunnel and to this in your career to become like an athletic engineer, you have this phase, it's a trap phase where you you're looping and building your own tools to like optimizing your own workflow.
But th this idea of like this hyper personal agent stuck a little bit.
And then over the last few months, I I really started.
I built it, but funny initially I didn't even had the the scope that it has now.
Like I called it WhatsApp relay.
I just I just I just wanted to do to trigger stuff on my computer with WhatsApp.
So I built like a WhatsApp relay where I had an agent that could do stuff with my computer.
And then I 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 it was guiding me through the city, it was making jokes, it could text other friends via WhatsApp from me.
It and I remember I was blown away because I in the beginning the tech was very scrappy, but I 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 the LM a f a string and it could do the read tool to like read the string.
And then I was in Morocco and it was just like just like not thinking and sending it a voice a voice message, but I didn't build that.
And then like like 30 seconds later, it replied to my voice message.
And like, how the f did you do that?
Oh yeah, you sent me a file, and then I looked at the header and I found that it's OGG, so I used FFmpack to convert it.
And then I I looked for VISP on your computer, but it's not installed.
But I found the open AI key, so I did a curl to open the ice server, let it translate, and I'm like, holy cow!
Like this was Opus 4.5, and it's so incredibly resourceful.
Like, you just did this.
You know, other people say, Oh, you need a skill or some system.
No, it's just like it just figured it out.
I slowly got hooked on the thing.
I I used it, I used it to wake me up.
And it was running.
Uh it was running on my Mac Studio in London and was connecting over SSH to my MacBook in in Morocco and was turning on the music and making it louder and louder is because I didn't reply.
And to make that work, I I added a heartbeat.
So which in a way is insane from a security perspective.
You have a model with that you prompt with do something cool and surprise me.
That you send every few minutes to make it proactive and like go through your task list.
Uh like probably the most expensive alarm clock ever, but it was just hilarious.
And also the text it sent, like, because I I I was I had a balloon float and it 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 I showed it to the the friends I was with, and everybody was like hooked.
Like this is something magical.
And I was hooked too.
Um and then I I went on Twitter and I got the most muted responses because nobody would get it.
I feel it's somewhat of a of a new category of product.
Um that's a little bit like your story with like you know, when you didn't get the iPhone uh from the marketing campaigns on TV on anywhere, and then you have to use it.
Yeah, so I I worked on it, but only the last two months.
And it did the name changed from VAR relay to at some point a Claude.
Uh say, like then what is this name?
Like it doesn't fit the feature set anymore because like I had like Telegram in there and other features.
So I renamed it to Claudus because it's an inside joke because I like Doctor Who.
I felt CloudBot is a better name, had a better domain, and explained the product better.
So I hit it on the domains, and then I I also quietly build up my army because to make this work, you want you want everything to be a CLI.
So it was just building CLIs for everything, like for Google, for my bed, for lamps, for music.
Why CLIs, why not MCPs?
And what do you think about MCPs anyway?
Uh as a crutch.
It's it's I think that 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 is silly.
You 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 like imagine imagine you have a better service.
So the model could ask for list of available cities and then get like 500 cities back.
And then it has to pick one city out of 500 cd, but it cannot filter that list because that's not part of how MCP works.
And then it'd say, okay, give me the better for London, and you would get like 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, I could use just it could use GQ and because a filter for exactly what it needs.
But doesn't not seem like a limitation that everything is loaded around the MCP and 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.
Yeah, that's that's what that's what companies are building now.
But there's still the problem of that like I cannot chain them.
I cannot, I cannot easily build a script that says, hey, get me get me like all the all the CDs that are over 25 degrees and then and then filter out only that part of information and like pack it in one command.
That's it's all individual MCP calls.
I cannot, I cannot script it.
Yeah, but but I guess this is just a matter of time.
Because if we think about like, you know, when you're when I'm building a weather app right now, I know that uh, 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 one what kind of trade-offs for pricing, for covering, etc.
And then I choose that API and uh I could chain APIs because I I could get that result and look up uh et cetera.
So I I I guess this is you know, like it it sounds pretty much we've solved this so as free AI, we're gonna solve it.
It'll just take some time, and who knows what the format for that will be.
Uh uh I mean, I mean I I built Macporter, which is uh which is a a small TypeScript thing that converts an MCP to a CLI.
So it's uh you can you can just package it up.
Yeah, but basically you're you're saying CLIs right now are a lot more efficient.
Yeah, yeah.
So so my in in in in in Cloudbot I don't have MCP support, but you can via Mac Porter, you can use any MCP.
You can you can literally be on your phone and say, hey, use the use the Vercel MCP to do this and this, and we'll it will go in 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 MCP, you have to restart cloud code, which is like very user unfriendly.
So I quietly build up my army to like automate everything, which was a lot of work.
Uh I think Teo did a video a few days ago where he told me like, yeah, this guy is insane.
Because the list is really long by now, but like I I as I was playing with my my my agent, I just I want him to do more and more stuff.
You know, I felt it really hard to convey what it does.
Uh it's still hard to me.
In January January 1st, just a week now, I did okay, let's let's try something.
Let's let's do the insane really insane thing of like making a Discord and then adding my agent to Discord.
There was somebody who contributed Discord support to it, and uh, even though I wasn't unsure sure if I should merge it, then I eventually did.
So I put on my agent who has full read-write access to my computer in a public Discord.
What could possibly go wrong?
Yeah, it's like this is absolutely insane.
And then of course, like some people joined the Discord, and then they saw me, they saw me using the full power of this thing, like checking my cameras, doing home automation, it playing DG for me.
Like I was in the kitchen, and I told him, like, look at my screen, and are my agents 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 like it can tell me your codex say this and this because it just sees the screen.
I mean, I'm I'm working on optimizing that.
Yeah, like I actually want to stream out it because it would be much it would be much better if it's text.
But it works already.
Like it it's it's in the background.
It's time to look at my screen and like make some rants if I do some shit.
And everybody who experienced that for a few minutes got hooked.
Like this was this was the craziest blow up from a hundred stars to like what 3300 stars in a week.
Um, and I think I merged 500 pull requests already.
That's why I say I feel like a human merge button.
So that that's why that's why I'm like I'm a little I'm a little all over the place these days because this project is blowing off and and and you know the beauty of it is the technology disappears.
You just you just talk to a a friend on your phone that is infinitely resourceful, has access to your the email, your calendar, your files, can build websites for you, can like do administrative work, can scrape websites, can call your friends or can call a business.
I'm just about to to merge the call feature.
It like literally can call a business and like make it make a reservation for you.
And you don't have to think about compactation or or in all of that context blends away.
I have like a you have a memory system that will remember.
Um not perfect, nothing's perfect yet.
But it's already feels magical.
Because all because now I I walk around, I see like this event, I I send Claude a picture.
It will it will not only tell me the reviews of this event, if there is a conflict in my calendar, if like 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 the current tools that live in their own little box can give me.
Well, sounds like you built whatever Apple was hoping Siri to do, but they've been unable to do it.
I honestly I built the best marketing tool for Entropic to sell them more subscription.
I don't know how many people signed up for the 200 subscription because of CloudBot.
And like many people already had one and used a second subscription because of that, because it's so token hungry.
It's it's not it is 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 the technology blends away, they don't see that it spawns sub agents and does like a whole bunch of things in the background to just make it feel easy, but like there's some actual engineering, and like there's a lot of work in the back to make it feel easy.
You know, this is like the hard part.
Like you hide complexity to a degree that it it feels magical.
Well, but yeah, but this is interesting because like I I I can sense from where we're talking, you you know, you put so much thought into architecting this thing, and right now, like you've been building this for a few months, and yes, it blew up.
But in your head, like, do you have a structure of how CloudBot is structured?
Like what parts you need to modify, you know, like like you kind of you can get your your mindset into it.
You you know where modification needs to do, you know what you want to refactor because it's not gonna be efficient.
Are you thinking about like things like memory consumption, token consumption efficiency, those kind of things?
I mean, token consumption is more like how to how to structure the prompt uh and memory.
It's it's TypeScript that shows Jason around in the end.
Let's be honest.
Yeah, like like I get text from from an LLM, I save text to disk, I send text to WhatsApp or to now we have like MS Teams, Slack, Discord, uh signal, iMessage, WhatsApp, uh, and and there's there's two more that are landing, like metrics that will will expand this thing even further.
It's like it's it's really poly by now.
But but mostly I I again I I move around text in different shape, and maybe maybe it goes to different providers, or there's like now it's different agents, and there's like the agentic loop, and there's like a lot of configuration, and there's it's it's a lot of plumbing, but nothing's there's nothing in there that is really difficult.
Yeah, well, but it it's it's it's a lot of small things, right?
Like I I feel in software, right?
Like we we know for software, even before AI, there wasn't much difficult.
Of course, you need to learn and understand the language and all that.
But no, the the difficulty is how do I 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 it that you pice in your command.
I will I will check if you have node installed, homebrew installed, I'll uh 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 and everything.
And then I I'll guide you through uh setting up a model.
But again, I will I will pre-find if you have codex or or cloud installed, so you can just press enter.
So you don't have to 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 and then I'll ask you, do you want do you want to hatch your bot?
And you can press yes, and then and then like a two yeah, a two ye comes up because you're still in the terminal, right?
You want a good experience.
Yeah.
So put that but just a tool basically for that, and where you where you just see, wake up my friend, and then the the I programmed the model, I added a bootstrap file and then to explain the model that it is now being born to like create an identity and a and a in a in a in a soul where like the values of the user are in and then the model will be like hello like stretches who are you um who I who I am what's my name you know and this this is this like I watch people do that and that's where the magic starts that's where that's where they're like they no longer think about I'm talking to to GPD 4.2 no I'm now talking to my friend created Vahorn like a a unicorn with part of his name or like I'm talking to Claude and then it's like well what what's important to you what do you do it's like curious I 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 like information about you a soul.md with like all the core values and an identity with the like what's his name what's his core emoji what are the things that are like inside jokes and and but it's like evolving documents that it will maintain and like tweak as you interact with it.
And then you it will just like send you a message on on WhatsApp, and you just like suddenly you talk on WhatsApp.
Like making this flow easy, that's hard.
Yeah.
Also, like even even get coming up with the idea of you're no, you're you're not 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, yeah, I have new features.
Blending the technology away so far, that's the magic.
That's why that's what I but it feels it's very similar to what you would with PS PDF kit, right?
You kind of blended away the complexity of a PDF so that it was just there, you could rotate, you could do.
Yeah, yeah, even at the API level back then.
But it's uh it's a bit bizarre.
Like what you described reminds me of this Black Mirror episode I just watched, which is called Plaything, uh, where it's a it's a digital little uh creature that creates, of course, the black mirror, so it has a black bit of a dark ending, but but it it had it was also a game.
It also kind of feels you know, we talked about how you you don't play as much games because you like, but this also feels a little bit like a game, right?
But it it's it's kind of like more connected with reality, just fascinating how we're we're we're here put pulling back into the the realm of of software engineering.
So you build this this product and it's it's now it's a production software, you're merging porous people are using it.
Now, thinking back to PSPDF kit and and companies that are like that, which which have you know like like tens or hundreds of developers working on 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 one thing I see is 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 it's not really uh okay, people use it for this or that.
But but it's it seems a huge divide between the two worlds, and you've kind of been the CEO for this company.
What what might that be?
Or is it just more of a timing thing where every new technology often comes with with hobbies, you know, pick it up uh earlier?
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, you know, you know, like you know, like at Google, they 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 you build it or you you design it.
But this new world needs people that that have a product vision that that can be able to do everything and you need like far fewer of them, but ultimately just very high agency and and high competency people, but you can you can like probably like trim the company down to like 30%, which is very scary because like I mean economically this will all this will all lead into a fiasco.
Um and a lot of people will like have trouble finding a 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 you have to do a big refactor first, you know?
Like not just on your code base, but also on your company.
I design even on code bases.
I design the code base not so it's 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 and and have the 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 had I deal with the the overall structure and architecture, and I can still do that in the way that I like everything has to be resort, you know, pull requests.
Uh I see them more as prompt requests now.
Like I don't I I so somebody opens a pull request, I don't I a lot of do we 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 very it's tricky bugs, right?
But I I basically rewrite every pull request and and uh and weave it in.
Also also a lot of people, let's just say the overall code quality of of PR is went down a lot because people vibe code and and building a successful feature still needs a lot of a lot of understanding of your overall design.
And if you if you cannot do that, you will have a harder time steering your agent and the output will be bad.
Yeah, and if you don't have a feedback group to close it, uh yeah, yeah.
So so I found it highly effective like I know it at my at at PS3DF kit sometimes a pull request was like a week in the work yeah and then you comment on it and then somebody has to contest context switch and you wait for CI for 40 minutes.
No I have the discussion I see okay how would this affect something like I I let the model review they will already bring something up I have some some ideas as well we're gonna 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 um and sometimes you have to like change the structure so it would fit.
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 keep want to keep doing what you're doing how do you think things like code review CI CD would change?
I don't I don't I don't care much about CI I why why why why not?
You used to care a lot.
Like a PSB kit you used to care a lot right and and and I still do this there's value but I I have local CI'm I'm a little bit I I'm a little bit of DAH pill now that because because the agent runs the test, right?
Yeah.
And it's just way faster.
I don't I want to push on the on the on the on the back on the PI and then wait for 10 minutes to wait for for CI.
Because you've waited 10 minutes on the agent already.
If if the tests pass locally we merge and then yes, sometimes main slips a little bit, but it's 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.
This gate full gate is like linting and building and checking and running all the tests.
And I almost think it like because it's uh it's a wall, you know, like it's like you call cylinder and like the the build and the tester, it's almost like a gate before my code goes out.
So I know obviously like oh uh okay, once you're done, like uh commit this, run full gate.
Like I'm I'm slowly adopting their language.
But but and if you hired like one more person to work on this, you probably wouldn't do code reviews either.
Well that's what I'm sensing.
You you would you'd probably trust this person to run like like pick up your working style, right?
Even in Discord, uh we don't we don't talk code, we talk about architecture, like big decisions.
Like you still need to have style.
Like there was like this one pull request that adds voice calling.
So now I like literally I can tell Claude, hey, can you call this restaurant and and and and reserve your seats?
And and it it it can do that.
But it it it's a big, it's quite a big new module that like touches a lot of places.
I'm like, you have to have this feeling.
Is this like this ick?
Like I got a little bit of this ick, it's like I want to merge this, but uh this is becoming bloodware.
So I so I I had this idea of like uh let's 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 unfinished.
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 let's let's 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.
But give me an honest opinion.
Would this to me this sounds like it actually it would fit into the project?
And it's like it was like, yeah, you you would 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 then I will, and you know, like one of the the secret hacks on 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 it there, and all the previous thinking I did to like solve the problem well.
AI is so good at this still to like read the code and understand my ideas.
I don't have to like explain it again.
Uh or if I explain it again, I might like make mistakes that like wouldn't get across exactly the idea that I have in my head.
So in this case, I know that Mario, who does like shitty coding shitty coding agent, which is like a actually very much not shitty coding agent.
That's called Pi.
I know that he had this plugin architecture that would load code via via JD, 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 I came up with yeah, that's what I built last night.
Basically, I mean, sounds like this is gonna be completely uh different.
Like, like you know, PRs are are like in your workflow, you're not using PRs that much.
Uh CI is just different, it's it's tests are still doing there's an important more important feedback loop.
You're using things more like weaving instead of code, you're talking more about architecture and taste.
It sounds like a pretty big shift to me.
Now, in this world, let's assume you get to the point where gonna you're hire the next one and two and three developers on a team.
Let's imagine that this thing gets a life of its own, and you know, maybe it's a business as well.
What skills would you look for?
And what would you advise a an experienced engineer right now?
Who would you be excited to work with?
What kind of either expertise projects would you look for for someone who sounds like who can work in this way or can pick up this way of working?
Someone who is active on GitHub and does open source, and and someone where I have the feeling that they they love the the game.
The way you learn in this new world is by like trying stuff, and it very much feels like a game where you improve your skills as you get better, like like it's like a music instrument.
You have to like keep trying.
And I and I that I'm now this efficient and this fast, and I don't know, like I I think like the other day I I had like 600 commits in a single day.
This is like completely nuts, and it works.
Like it's not, it's not like there was there was a somebody did a code review and said, like, oh, this is actually not slop.
And like, yeah, yeah.
Uh there's a lot of skill that wanted to.
Yeah, it's it's it's 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, you know, you start going to the gym, it's gonna suck.
It's gonna be painful.
Um, but very quickly, you like you get better and you and you feel that that your workflow gets faster, and then you feel the improvement, and then you get slowly get hooked.
So it's a but yeah, play and and yeah, also work hard.
Yeah, I I mean you're you're putting in more hours into this thing.
I've never right now I've I've never I never worked more even when I had my company, I 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 like using the moment where where this has traction and and there's a lot of people who like are pushing me.
Um and I I feel could it be because I think you have pretty good business sense.
Not not 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 a lot of people are worried about is the the new grads, the the people with 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 uh 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 do you would you recommend on focusing on the fundamentals of software engineering on this on the agents, kind of mixing the two?
I would I would recommend them to be infinitely curious.
Yes, it's gonna be harder to enter this market, it's it's absolutely gonna be harder, and you need to build things to like 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 in a really good way.
This is usually something you discover through pain.
It's it's not gonna be easy for new people, but but they have they have the benefit that they are not tainted by all the experience.
Like they would they 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.
And also their friends use it all all the time.
Yeah, like like the other day, I I have this little menu bar app for cost tracking on Cursor and and cloud Code and everything, and it was a bit slow.
So I was like, okay, let's do let's do performance measurement.
And my old way is like I open instruments and click around.
And it would just call XS and do everything by the terminal.
It blew me away.
Yeah, I I think we might be underestimating both like how resourceful people entering tech have been, also how uh 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 that's a big opportunity.
I I'm especially taking like it's uh I have to take it in like all but all the things you mentioned about just your way, you know, weaving code in, not carrying out PRs, not carrying out code reviews.
It's a big change because these things have been bin us with like again for like 15 plus years of your life, there they have been.
In fact, you know, a lot of it has been kind of you know solid building blocks of PSPDF get right.
Yeah, we need we need a lot of new things, even you know, even when I get a PR, I'm actually more interested in the prompts than in the code.
Uh I I ask people to please add the prompts, and some do.
And I I read the prompts more than I read the code.
Because to me, this is 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 than 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 will build it.
So because the 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.
Uh and I and then uh yeah, of course I think about it, but it will will re 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 to review that and just type in fix in c in in codex and wait a few minutes.
So there's there's uh there's like all these insane things that are like would have been completely different, even even in the beginning.
Uh now we have a one-liner, but for the last two weeks, uh like when it got really traction, I told people to just point an agent at the repository to configure it.
So I didn't had I didn't have an onboarding, but we had claude code-based onboarding where Claude would like check out the grid 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 because agents can now do that for you, and the and the and since the the product was built by agents, they structured it exactly the way agents expect things to be named and synced.
There's certain ways that are encoded in in in the in the weights.
How do you expect things to be named?
And everything is exactly ex like how do you expect to they're really good at navigating their product.
So it was not a priority to work on onboarding as much.
I mean, uh eventually I wanted this magical experience, but it was more important to like make sure that your message arrives and that things don't explode.
So onboarding was literally like type disk prompt into your agent.
Um which is would have been mind-blowing even a year ago.
Alright, so to wrap off, 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 you use you like you would recommend.
I buy a lot of gadgets, and many of them dust away.
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 like it has an email address, and friends can send pictures and it will just show pictures.
And I and I put a a few a few in in my house again.
And I mean, even the animations are a little crappy because it runs anywhere, then 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 to it 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 like move the sims around.
And I said, like basically no no feelable benefit.
But like this little this little device gives me infinite joy.
What's something that helps to recharge outside of tech?
Like just or just moving away from tech and screens.
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 like a good hour where I just feel me, and I and I'm like in the moment, and I'm not distracted by notifications or tempted to like touch my phone.
Like we need more time for this.
Or even sometimes I I go for a walk and I I leave my phone at home and it feels very scary.
It's almost like a it's almost like an organ by now, you know?
It's like your your body knows where it is, and if you don't know where your phone is, you freak out.
I I'm having I'm having a blast.
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 built 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.
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 it 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 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 architecture or card ordering 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 Clobbot 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.