The creator of Clawd: "I ship code I don't read"
📚 Main Topics
- Peter Stainberger's BackgroundCreator of PSPDF Kit, a widely used PDF framework, who took a break from tech after burnout.
- Return to TechPeter discusses his comeback to software development and the evolution of his workflow with AI.
- ClawbotHis new personal assistant project that leverages AI to enhance user experience.
- Changing Software Development PracticesThe impact of AI on coding practices, including the concept of "prompt requests" instead of traditional pull requests.
✨ Key Takeaways
- AI in DevelopmentPeter emphasizes that AI tools allow for rapid development and iteration, enabling him to merge hundreds of commits in a day without sacrificing quality.
- Closing the LoopEffective AI coding requires a feedback loop where the AI can validate its work, making it easier to debug and test.
- Shift from Code Reviews to Prompt RequestsPeter suggests that traditional code reviews are becoming obsolete, replaced by a focus on the prompts that guide AI in generating code.
- Importance of ArchitectureWhile he may not read every line of code, Peter stresses the importance of system architecture and understanding how components interact.
- Curiosity and ExperimentationNew developers should cultivate curiosity and engage with open-source projects to gain experience and learn how to effectively use AI tools.
🧠 Lessons Learned
- Embrace ChangeThe software development landscape is rapidly evolving with AI, and adapting to these changes is crucial for success.
- Focus on OutcomesPrioritizing the end-user experience and the overall product feel is more important than obsessing over every detail of the code.
- Iterative ImprovementContinuous learning and improvement are essential, especially in a world where AI can automate many coding tasks.
- Collaboration with AIDevelopers should view AI as a collaborative partner that can enhance their productivity and creativity rather than a replacement.
🏁 Conclusion
Peter Stainberger's insights highlight a transformative shift in software development practices driven by AI. His experiences with Clawbot and the evolution of his coding philosophy suggest that the future of software engineering will be characterized by a more fluid, collaborative approach that prioritizes user experience and leverages AI's capabilities.
Transcript excerpt
0:00 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 who built PSP PDF kit, the PDF framework used on more than 1 billion devices. Then he burned out, sold his shares, and disappeared from tech for 3 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
0:31 Clawbot, his wildly popular personal assistant project, which feels like the future of Siri, the closing the loop principle that separates effective AI assistant coding from frustrating vibe coding. Why he says code reviews are dead and PR should be called prompt requests, and many more. If you're interested in how the software engine workflow could change in the coming years thanks to AI, this episode is for you. This episode is presented by Statsig, the unified platform for flags, analytics experiments, and more. Check out the show notes to learn more about them, the pragmatic summit on the 11th February in San Francisco that I'm
🔒 The full, searchable transcript is available with Pro.
Related summaries
DHH’s new way of writing code
Martin Fowler & Kent Beck: Frameworks for reinventing software, again and again
Catholic Priest Interns at PSYCHIATRIC Institute, THEN THIS HAPPENS
Dal Profilo di Funzionamento al PEI -Secondaria 2° g.-
O ASSUNTO PROIBIDO em 2026 na INTERNET: PORQUE NINGUÉM + FALA DISSO?
