
80 segments available
Peter Steinberger ships more code than I’ve seen a single person do: in January, he was at more than 6,600 commits alone. As he puts it: “From the commits, it might appear like it's a company. But it’s not. This is one dude sitting at home having fun." How does he do it? Peter Steinberger is the creator of Clawdbot (as of yesterday: renamed to OpenClaw) and founder of PSPDFKit. OpenClaw – a work-in-progress AI agent that shows what the future of Siri could be like – is currently the hottest AI project in the tech industry, with more searches on Google than Claude Code or Codex. I sat down with Peter in London to talk about what building software looks like when you go all-in with AI tools like Claude and Codex. Peter’s background is fascinating. He built and scaled PSPDFKit into a global developer tools business. Then, after a three-year break, he returned to building. This time, LLMs and AI agents sit at the center of his workflow. We discuss what changes when one person can operate like a team and why closing the loop between code, tests, and feedback becomes a prerequisite for working effectively with AI. We also go into how engineering judgment shifts with AI, how testing and planning evolve when agents are involved, and which skills and habits are needed to work effectively. This is a grounded conversation about real workflows and real tradeoffs, and about designing systems that can test and improve themselves. — *Brought to you by our season partners:* • Statsig — The unified platform for flags, analytics, experiments, and more. http://statsig.com/pragmatic • Sonar – The makers of SonarQube, the industry standard for automated code review. https://www.sonarsource.com/pragmatic/?utm_medium=paid&utm_source=pragmaticengineer&ut[…]egory=Paid&s_source=Paid%20Other&s_origin=pragmaticengineer • WorkOS – Everything you need to make your app enterprise ready. https://workos.com/ — *The Pragmatic Engineer deepdives relevant for this episode:* • Inside a five-year-old startup’s rapid AI makeover https://newsletter.pragmaticengineer.com/p/ai-first-makeover-craft • When AI writes almost all code, what happens to software engineering? https://newsletter.pragmaticengineer.com/p/when-ai-writes-almost-all-code-what • Why it’s so dramatic that “writing code by hand is dead” https://newsletter.pragmaticengineer.com/p/the-pulse-160-why-its-so-dramatic • AI Engineering in the real world https://newsletter.pragmaticengineer.com/p/ai-engineering-in-the-real-world • The AI Engineering stack https://newsletter.pragmaticengineer.com/p/the-ai-engineering-stack — *Where to find Peter Steinberger:* • X: https://x.com/steipete • LinkedIn: https://www.linkedin.com/in/steipete • Website: https://steipete.me • OpenClaw: https://www.OpenClaw.ai — *In this episode, we cover:* (00:00) Intro (01:07) How Peter got into tech (08:27) PSPDFKit (19:14) PSPDFKit’s tech stack and culture (22:33) Enterprise pricing (29:42) Burnout (34:54) Peter finding his spark again (43:02) Peter’s workflow (49:10) Managing agents (54:08) Agentic engineering (59:01) Testing and debugging (1:03:49) Why devs struggle with LLM coding (1:07:20) How PSPDFkit would look if built today (1:11:10) How planning has changed with AI (1:21:14) Building Clawdbot (now: OpenClaw) (1:34:22) AI’s impact on large companies (1:38:38) “I don’t care about CI” (1:40:01) Peter’s process for new features (1:44:48) Advice for new grads (1:50:18) Rapid fire round — See the transcript and other references from the episode at https://newsletter.pragmaticengineer.com/podcast — Production and marketing by https://penname.co/.
Peter Steinberger, creator of Clawdbot, shares his journey from building PSPDFKit, a PDF framework used on over a billion devices, to experiencing burnout and stepping away from tech for three years. He discusses how his return to software development is radically different, emphasizing the importance of AI tools in his current workflow.
"What if you could merge 600 commits on a single day and none of it was slopp? This is what today's guest, Peter Stainberger, the creator of Claudebot, claims he's doing. Peter is a standout developer ..."
After a three-year hiatus, Peter Steinberger discusses his comeback to tech and how he is now building Clawdbot, a personal assistant project that aims to redefine AI interactions. He reflects on the changes in his approach to coding and the impact of AI on software development.
"podcast. >> Thanks for having me, Gay. >> It is awesome to meet you in in person. >> Yeah, and I almost messed it up. >> Yeah. What what what what happened? You lost track of time. Does that happen of..."
Peter recounts his early fascination with technology, starting from his childhood in rural Austria. He shares how a summer guest introduced him to computers, igniting a passion that led him to tinker with software and eventually pursue a career in tech.
"get into tech? So I'm from rural Austria. Um always more being the introvert. So eventually I we always had like summer guests and one of them one of them was a was a computer nerd and then I kind of ..."
Peter reflects on his initial experiences with programming, including his first job in Vienna where he learned to navigate complex software challenges. He shares anecdotes about his early coding experiences and the lessons learned from working in a demanding environment.
"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 ..."
Peter describes the moment he encountered the iPhone and how it transformed his perspective on mobile technology. He shares the story of how a frustrating experience with a dating app led him to develop his first application, marking the beginning of his journey into iOS development.
"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 text I I did a few modernizations but then it was too late. I did this a few times in this ..."
Peter narrates the challenges he faced while developing his first app for a dating service, including parsing HTML and navigating the complexities of Apple's App Store. He reflects on the unexpected success of the app and the lessons learned from that experience.
"got one. I was still not thinking about building for it, you know. That was that was >> when was this 2009 10 something like that. >> Yeah. Yeah. And then I I used their browser. I I can see the story..."
After launching his dating app, Peter shares how he made significant earnings in the first month, which motivated him to pursue app development full-time. He discusses the reactions from his peers and the drive that fueled his ambition.
"until anything worked because like I had no idea what I was doing and I was like using all kind of like beta tech but eventually I I got it to work and I I I wrote that company was like hey I'm making..."
Peter recounts the challenges he faced with Apple regarding his app, leading to its eventual removal from the App Store. He reflects on the impact of this setback on his career and how it shaped his future endeavors in tech.
"was so proud and I wanted to like tap him on the shoulder and say I built this and I thought like that would be really weird. So I didn't. And then I I I went to the company I worked for for 5 years a..."
Peter discusses his move to the U.S. tech scene after gaining recognition as a top iOS developer. He shares experiences from his early days in the industry, including working on various projects and the evolution of his career.
"was like, well, f you Apple. >> I did freelance work. I was at dubdub. I was introduced to >> dubdubdubc. >> Yes. Sorry for the insider terms. I was introduced to someone as one of the best iOS develo..."
Peter explains how he transitioned from freelance work to creating PSPDFKit, a powerful PDF framework. He shares insights into the technical challenges he faced and the innovative solutions he developed to overcome them.
"a PDF viewer. You know, on every technical problem, the domain is is I wouldn't say like completely unimportant, but you can always find interesting problems in every domain. And there was a lot of in..."
Peter elaborates on the complexities of PDF rendering and the unexpected challenges that arose during the development of PSPDFKit. He emphasizes the importance of attention to detail and the learning curve associated with mastering such a complex domain.
"if he's interested in that, why let's not try to sell it to other people." I used a a WordPress template and mutilated it to run on GitHub pages and then and then when you did the the fast lane flow a..."
Peter reflects on the growth of PSPDFKit and the entrepreneurial journey that accompanied it. He discusses the challenges of scaling a tech business and the satisfaction that comes from solving real-world problems through software.
"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 mont..."
Peter shares his thoughts on how AI is transforming software development, particularly in terms of workflow and productivity. He discusses the implications of AI tools on coding practices and the future of software engineering.
"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 and they wanted my hel..."
Peter recounts a pivotal moment in his career when he had to choose between continuing at a company in San Francisco or pursuing his own project, PSPDFKit. He reflects on the decision-making process and the realization that his personal project was gaining traction and could potentially match his salary, emphasizing the importance of passion over financial motivation.
"know, it was like it was like summer. I was I was like lying at the lake and got another email that someone bought it for 600 bucks, 800 bucks. I just up the prices as it had more features. And by the..."
In this segment, Peter discusses his philosophy of software development, focusing on creating products with the same care and attention to detail as Apple. He emphasizes that the user experience and how software feels are more important than just feature sets, which has contributed to the success of his products despite competition.
"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...."
Peter explains the early days of PSPDFKit, detailing how he began working with freelancers and the gradual evolution of the product. He reflects on the challenges of scaling a project and the importance of maintaining quality while expanding the team and capabilities.
"a lot of people in the 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 successfu..."
Peter shares his marketing strategy for PSPDFKit, which focused on engaging developers rather than traditional sales tactics. He highlights the importance of building a product that developers love and the effectiveness of technical blog posts and conference appearances in driving interest and sales.
"and I spent pretty much 13 years of my career um building this product with this weird name that I never changed because I took me like I thought like five minutes about it and then stock PSPDF kit. >..."
In this segment, Peter discusses the technical stack behind PSPDFKit, including the transition to C++ for rendering and the early adoption of web technologies. He reflects on the challenges and innovations that came with building a robust PDF framework.
"worked really well. >> And then what was the text type behind PSPDF kit? Was it objective C? Was it later swift? Were there other technologies like C or or anything else? >> We eventually expanded to ..."
Peter describes the evolution of PSPDFKit's team culture as it grew to nearly 200 employees. He emphasizes the importance of a remote-first approach and the lessons learned in managing a distributed team while maintaining a strong company culture.
"[ __ ] >> Ah nice. And then a as as a company grew, one thing that I remember about PSPDF kit, you did write a lot of blogs and one blog in 2019, so this was about like I think you know year nine or 1..."
Peter discusses the complexities of enterprise sales, particularly the need for custom pricing based on the unique needs of different clients. He explains the challenges of selling to developers and the importance of understanding the value proposition for various customer segments.
"the go. Like I I never had the urge to be CEO. I always was coding. I I brought people in to people that that helped me a lot with other other parts. Uh and on the business side, I can do it and I I t..."
In this segment, Peter elaborates on the intricacies of pricing software products, especially in the context of enterprise clients. He explains how different customer types require tailored pricing strategies to ensure fairness and accessibility.
"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 powered features and want ..."
Peter reflects on the importance of identifying a niche market for software products. He discusses the balance between creating something that is both challenging and necessary for developers, which ultimately leads to successful sales.
"would either exclude one or the other. If I if I if I go too low, they're going to see this fishy. It's like uh procurement for like 500 bucks. we're not going to even start the process. And if we we ..."
Peter shares a specific case of a customer with an exceptionally large PDF that revealed flaws in his parsing model. He discusses the technical challenges of redesigning the product to accommodate unexpected user scenarios while maintaining a seamless experience.
"to be in. So 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..."
In this segment, Peter emphasizes the value of providing exceptional customer support. He explains how his hands-on approach to resolving customer issues has positively impacted the company's reputation and customer loyalty.
"redesign the internal part without breaking things for everyone? like suddenly everything has to be lazy where where before parsing 100 one was easy but now they were like this was like so difficult t..."
Peter discusses his motivation for writing technical blogs and sharing insights from his work. He reflects on the benefits of documenting challenges and solutions, both for personal growth and for inspiring others in the developer community.
"that's magical. If you wait one or two days not much difference. Yeah. >> So, yeah, this this was one of the problems where I worked two months and I finally got it down to almost like this. >> Mhm. T..."
Peter explains his strategy for fostering a culture of writing within his team. He shares how he allocated time for team members to write blog posts, emphasizing the importance of sharing knowledge and experiences to attract talent and build a strong community.
"hacker news as well but it was just interesting to read and I couldn't name again I I'm not went into PDFs but if I had to say something a PDF I would have said PSPDF kit because they're the only ones..."
Peter reflects on the transition from the startup phase of PSPDFKit to a more structured growth phase. He discusses the challenges that come with scaling a company and the shift in focus from rapid innovation to managing a larger team.
"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 t..."
In this segment, Peter candidly discusses the emotional toll of being a CEO. He shares his experiences with burnout and the loneliness that can accompany leadership, particularly when faced with high-stakes challenges.
"wild hacks >> um and more iterative. So, so, so it got a little bit less interesting uh over the years and there was like more people drama cuz the more so the more people you have, the more issues th..."
Peter elaborates on the sources of stress in his role as CEO, including managing conflicts within the team and the pressure of high-stakes situations. He reflects on the importance of belief in the work and the impact of internal conflicts on overall job satisfaction.
"also quite lonely because you you can't openly talk about a lot of things. I mean 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 ..."
Peter recounts how he eventually returned to coding after a three-year hiatus, motivated by a long-held idea for a Twitter analytics tool. He reflects on the challenges of adapting to new technologies and the excitement of building something from scratch again.
">> I needed a lot of time to decompress. I I catched up a lot on the things I thought I missed. I I a lot. Um there were months where I didn't even turn on my computer. And for a while I was I just di..."
Peter discusses the difficulties of transitioning back into software development after a break, particularly with web technologies. He highlights the challenge of learning new frameworks and the frustration that comes with feeling less efficient as a developer.
"where you really where and you know, this is like this is a a trap I see with many developers. The the better you get at one technology, the harder it is to jump somewhere else. It's not that you can'..."
Peter shares his initial experiences with AI tools like Claude and how they transformed his approach to coding. He describes the addictive nature of using AI for development and the excitement of discovering its potential to streamline the coding process.
"you missed everything else before. and and and you know, you know, it was like I I remember I took this big messy site project that I built and I have this browser extension where that that converts a..."
In this segment, Peter expresses skepticism about the reliability of AI-generated code. He discusses the importance of verifying AI outputs for security and maintainability, emphasizing the need for a robust code review process.
"leads us nicely to our season sponsor, Sonar. So, let's look at some data. A new report from Sonar, the state of code developer survey report, found that 82% of developers believe they can code faster..."
Peter describes a pivotal moment when he realized the potential of AI in software development. He recounts how a simple project using AI tools led to a significant breakthrough in his understanding of what could be achieved with technology.
"get started for free, head to sonarsource.com/pragmatic. With this, let's get back to Peter and how AI agents cannot exactly be trusted. >> Then I had then I added added an MCP so it could use the bro..."
Peter likens the experience of using AI tools to gambling, highlighting the thrill of unexpected results. He reflects on how this addictive quality can lead to late-night coding sessions and a deep engagement with the technology.
">> I I remember because once 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 5:00 a.m. and I I sent you a message on T..."
Peter discusses the tension between striving for perfection in code and the practical realities of software development. He reflects on his past obsession with details and how his perspective has shifted towards focusing on system architecture and functionality.
"mind as like you're a really experienced developer like it's it's not easy to blow your mind, right? Like you you you've seen good code you can differentiate like crap code, decent code, good enough c..."
In this segment, Peter outlines his current workflow while working on OpenClaw. He explains how he integrates AI tools into his development process and the importance of understanding the underlying architecture while leveraging AI for coding.
"think about it? >> Yeah. Yeah. Yeah. To a degree. Yes. And and even now like I I I mean like my my last blog post was a confession that I I ship code on read and >> yeah we have to talk about that >> ..."
Peter Steinberger humorously describes his and his friends' late-night coding sessions fueled by AI tools, dubbing it the 'Black Eye Club.' He reflects on how AI has transformed his ability to build software, allowing him to tackle multiple projects simultaneously without the traditional constraints of software development.
"both Armen and and Mario from Vinner. They got they got AI pill because I I was addictive. You know, my my enem was like confusing them and then they tried it out and then and then eventually they als..."
Steinberger discusses the unique friction he experiences when prompting AI models, comparing it to the friction felt during traditional coding. He emphasizes the importance of understanding the AI's responses and how this interaction has evolved his approach to software development, allowing him to create without writing code by hand.
""Oh, 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..."
Peter contrasts different AI tools, particularly Claude and Codex, highlighting their strengths and weaknesses in coding complex applications. He explains how Codex often requires more time for setup but can produce better results for intricate tasks, while Claude excels in understanding broader contexts.
"again GBD 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 kind of get it. It's it's a different way of working but whatever O..."
Steinberger shares his strategy of engaging in a conversational manner with AI models, treating them as collaborators in the development process. He explains how this dialogue helps him refine ideas and explore different options before finalizing code, emphasizing the importance of guiding the AI's understanding.
"better because it it it takes 10 times longer. um Claude 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 ..."
Peter likens his role in using AI to that of an architect, where he designs systems and guides the AI in coding. He discusses the balance between high-level design and the detailed execution of code, illustrating how AI tools can assist in both areas while maintaining his responsibility for the final output.
">> So so a lot of a lot 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..."
Steinberger reflects on the evolution of his role from a traditional software architect to a builder who actively engages with AI tools. He discusses the challenges and benefits of this transition, particularly in how it affects team dynamics and the responsibility he holds for the software produced.
"architect you It sounds a little bit like you're almost, you know, for years back this this totally came got out of style. But there was this idea that you would have the architect with a capital A wh..."
Peter emphasizes the importance of iterative improvement in software development with AI. He shares insights on how to manage expectations and outcomes when working with AI tools, advocating for a mindset that embraces flexibility and continuous enhancement of the product.
"difference in this system when when it was 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..."
Steinberger discusses the necessity of asking the right questions when working with AI models. He shares personal experiences of debugging and problem-solving, illustrating how the right inquiries can lead to significant breakthroughs in understanding and utilizing AI effectively.
"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 built this Tw..."
Peter talks about the differences in expectations when using AI for coding compared to traditional methods. He highlights the need for patience and understanding that AI-generated outputs may require additional refinement, drawing parallels to managing a team of developers.
">> Yeah. But you you need to have like knowledge expertise. >> Yeah. You experience >> you you I mean so so so these are the people who rejected and then the people who who care a bit less about how i..."
Steinberger describes his experience of achieving a flow state while working with AI agents. He explains how the speed and interactivity of AI tools allow him to manage multiple projects simultaneously, while also acknowledging the mental demands of this multitasking approach.
">> Yeah. And 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 leadi..."
Peter emphasizes the importance of closing the loop in AI development, ensuring that AI can debug and test itself effectively. He shares strategies for setting up validation loops and the benefits of trusting AI outputs, which can lead to more efficient and reliable software development.
"it work. I go back to there and and maybe tweak it a little bit more. But usually just like try it out and maybe then this is ready because this only took like 20 minutes. So like I constantly jump ar..."
In this segment, Peter explains the significance of closing the feedback loop in software development, particularly when working with AI models. He highlights how effective coding requires a system that can validate its own work, leading to better architecture and improved coding practices.
"read an image, create an image before and then look into the image and see what it sees. So I I don't not just tell the loop, I still tell tool calling, make it work and then it solved itself. It took..."
Peter discusses how AI is changing software engineering, particularly in terms of testing and documentation. He reflects on how his approach to coding has evolved, noting that he now relies on AI to generate documentation and tests, allowing him to focus on higher-level design and architecture.
"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 testa..."
Peter shares insights on how to effectively prompt AI models for coding tasks. He emphasizes the importance of understanding the model's behavior and iterating on prompts to achieve desired outcomes, likening it to learning a new instrument and developing a skill over time.
"don't write the test I don't write documentation I explain the model the trade-off so like why we did something like this and then tell it like like write that write the entrance section beginner frie..."
In this segment, Peter reflects on the mindset shift required when building software with AI tools. He discusses the need for a more playful and iterative approach to development, where upfront planning is less rigid and allows for exploration and adaptation as projects evolve.
"he wrote a prompt as far as I understand it there was there was not a lot of information on the website but to me it sounded like he wrote a prompt he put it on claude web and and he pressed send and ..."
Peter shares his vision for the future of personal assistants, inspired by the movie 'Her.' He discusses the potential for AI to develop a deep understanding of users and provide personalized insights, reflecting on his own experiences and the rapid advancements in AI technology.
"know how to play guitar and I put you on the piano and you tried a bit. It's like, "Oh, this sucks. I go back to my guitar." No. No. It's like it's it's a different way of building. It's a different w..."
Peter addresses the limitations of current AI models in coding and the importance of understanding these constraints. He emphasizes the need for developers to engage deeply with AI tools, iterating on their prompts and learning from the process to improve outcomes.
"business that it's a lot of revenue is hinging over it if today you know we just wiped PSPF kit does not exist you need to rebuild PSPDF kit you now have these agents how differently would it look how..."
Peter discusses the evolving role of senior engineers in the context of AI development. He highlights the importance of having experienced engineers who can delegate effectively and understand the critical aspects of software projects, especially in an AI-driven landscape.
"work around uh model limitations of of of of Opus that you don't even need when you use Codex. There's there's maybe a few cases where you have a really long list of individual tasks that can be autom..."
In this segment, Peter reflects on the iterative nature of developing AI projects. He discusses how the ability to quickly adapt and change direction during the development process leads to more innovative solutions and a better understanding of the final product.
"often lack is taste. I have to feel like how does this feature feel and and 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 ..."
Peter shares his aspirations for creating a hyper-personal assistant that understands users on a deeper level. He discusses the challenges and potential of AI in achieving this goal, emphasizing the need for models that can learn and adapt to individual user preferences.
">> Yeah. Yeah. I guess cuz cuz 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 it for a day or two now you give t..."
Peter Steinberger shares his philosophy on the iterative process of building OpenClaw, likening it to a journey up a mountain where one may stray off the path but ultimately reaches the summit. He discusses the motivation behind creating a hyper-personal assistant that understands users deeply, drawing parallels to the film 'Her' and the advancements in AI technology.
"actually will end up being to me 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 yo..."
In this segment, Peter envisions a future where personal assistants are deeply integrated into our lives, capable of proactive interactions and understanding our emotional states. He discusses the potential for AI to democratize access to personal assistance, making it available to more people as technology evolves.
"like almost the the anti-orem. 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. the the the bigger the context is, the..."
Peter reflects on how AI can serve as a therapist, providing insightful responses and helping users reflect on their feelings. He shares his experiences with AI tools that act as listeners, emphasizing the importance of data privacy and the potential for AI to enhance personal well-being.
"see like the first things with like OpenAI who who launched pulse with some productivity but we just don't have enough compute yet to offer this as a feature and also it's it's quite difficult. My ide..."
Peter discusses the evolution of his project, initially called WhatsApp Relay, into a more sophisticated hyper-personal agent. He recounts his experiences using the agent while traveling, highlighting its capabilities in managing tasks and providing assistance in real-time.
"workflow. But 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 finally initially I didn't even had the the scope that ..."
In this segment, Peter describes the automation features of his agent, including its ability to interact with his devices and perform tasks autonomously. He shares a humorous anecdote about how the agent managed to wake him up and control his music, showcasing the blend of technology and personal interaction.
""How the did you do that?" Oh, yeah. You sent me a file and and then I looked at the header and I found that it's OG. So, I used FFmpeg to convert it. And then I I looked for Visper on your computer, ..."
Peter explains his preference for command-line interfaces (CLIs) over traditional methods in AI development. He discusses the efficiency of using CLIs for automation and how they allow for more flexible interactions with AI systems.
"Like I it was bitching to me and then I I showed it to the 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 I went on Twi..."
Peter critiques the limitations of Model Control Protocols (MCPs) in AI interactions, arguing that they hinder the ability to chain commands and filter information effectively. He emphasizes the need for more efficient systems that allow for seamless integration of AI capabilities.
"music. >> Why CLIs? Why not why not MCPs? And what do you think about MCPS anyway? >> As a crutch it's it's I think that the the best thing that came out of MCPS is that it made companies reync to ope..."
In this segment, Peter discusses the future of API integration in AI development, highlighting the importance of being able to chain commands and access multiple data sources. He shares his vision for a more interconnected system that enhances user experience.
"discover or decide which one to use. >> That's what that's what companies are building now. But there's still the problem of that I cannot chain them. I cannot I cannot easily build a script that says..."
Peter shares the rapid growth of OpenClaw, detailing how the project gained popularity and user engagement. He reflects on the community's response and the excitement surrounding the capabilities of his AI assistant.
"demand. Even right now if you use MCP you have to restart cloud code which is like very user unfriendly. So I quietly built up my army to like automate everything which was a lot of work. Uh I think t..."
Peter discusses the engineering behind OpenClaw, focusing on how he aims to create a magical user experience by hiding complexity. He explains the importance of making technology feel intuitive and accessible, allowing users to interact with AI as if they were conversing with a friend.
"craziest blow up from 100 stars to like what 3,300 stars in a week. Um and I think I merged 500 pull requests already. That's why I feel like I even merge button. So, so that that's why that's why I'm..."
Peter Steinberger discusses how he architected Clawdbot to hide complexity and create a magical user experience. He emphasizes the importance of structuring prompts and managing memory and token consumption effectively. By simplifying interactions, he allows users to engage with the AI without needing to understand the underlying complexities.
"complexity to a degree that it it it feels magical. Well, but yeah, but this is interesting because like I I I can sense from we're talking, you know, you put so much thought into architecting this th..."
In this segment, Peter explains how Clawdbot evolves to create a personal identity for users. He describes the bootstrapping process where the AI learns about the user’s values and preferences, ultimately leading to a more engaging and personalized interaction. This transformation from a generic AI to a 'friend' showcases the potential for AI to develop unique identities.
"lot lot of small things, right? Like I I feel in software, right? Like we we know for software even before AI there was not much difficult. Of course, you need to learn and understand the language and..."
Peter reflects on how AI tools like Clawdbot could revolutionize software engineering practices. He discusses the challenges larger companies face in adopting AI efficiently and the need for a cultural shift within organizations. The conversation highlights the potential for AI to streamline workflows and reduce the size of teams while increasing productivity.
"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..."
Peter shares insights on the evolving roles within companies as AI becomes more integrated into workflows. He emphasizes the need for high-agency individuals who can navigate both technical and product vision aspects. This shift may lead to a reduction in team sizes and a redefinition of how companies operate, raising concerns about job security in the tech industry.
"you built this this product and it's now it's a production software you're merging porocas people are using it now thinking back to PSPDF kit and and companies that are like that which which have you ..."
In this segment, Peter discusses his approach to continuous integration (CI) and how it has changed with the introduction of AI. He explains his preference for local testing over traditional CI processes, highlighting the speed and efficiency gained through AI-driven testing. This shift reflects a broader trend in software development where AI tools enhance productivity and reduce bottlenecks.
"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 eve..."
Peter elaborates on how he collaborates with AI to weave code into existing structures, rather than relying on traditional pull requests. He describes the process of using AI to evaluate and integrate new features, emphasizing the importance of architectural decisions and maintaining code quality. This innovative approach showcases the potential for AI to enhance coding practices.
"where that's coming from. Should I run full gate? So now I call it gate with g full gate is like linting and building and and checking and running all the tests. And I almost think it like because it'..."
Peter outlines the skills and mindset he seeks in potential hires for his AI-driven projects. He emphasizes the importance of hands-on experience, open-source contributions, and a passion for learning. This segment highlights the evolving landscape of software engineering and the need for engineers to adapt to new technologies and workflows.
">> 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. It's called Pi. I know that he had this plug-in archit..."
In this segment, Peter advises new graduates to cultivate an infinite curiosity about technology. He stresses the importance of engaging with complex open-source projects and leveraging AI tools to enhance understanding, while acknowledging the challenges of traditional education in fostering this mindset.
"a group that a lot of 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 experi..."
Peter reflects on how his approach to software development has changed with the integration of AI. He discusses the diminishing importance of traditional code reviews and pull requests, advocating for a focus on prompts and the thought process behind coding decisions.
"they are not tainted by all the experience like they 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 ..."
Peter explains how AI agents have transformed the onboarding process for new developers. He shares his experience of using AI to automate repository configuration, highlighting the efficiency gains and the shift in priorities from manual setups to leveraging AI capabilities.
"code 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 w..."
In a lighter moment, Peter shares his joy in using a simple Android-powered photo frame that brings him happiness through memories. He contrasts this with the latest tech gadgets, emphasizing the emotional value of low-tech solutions over high-end devices.
"like make sure that your message arrives and that things don't explode. So onboarding was literally like type this prompt into your agent. Um which is would have been mind-blowing even a year ago. >> ..."
Peter discusses the importance of disconnecting from technology to maintain mental health. He shares his routines of going to the gym and taking walks without his phone, highlighting the need for moments of solitude away from screens.
"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 bas..."
In the closing segment, Peter reflects on how AI is reshaping software development. He emphasizes the need for a new approach to coding and collaboration, where prompts and AI-driven processes take precedence over traditional methods, suggesting a significant shift in the industry.
">> 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 ..."