AI Summary
5 min readšļø The Voices & The Context
- The Format: In-depth interview podcast episode with host probing a guest's career highs, burnout, and AI revolution in coding.
- The Key Players:
- Guest: Peter Steinberger, legendary iOS developer who built PSPDFKit (PDF framework powering 1B+ devices), sold shares after burnout, and now builds ClaudeBotāa hyper-personal AI assistant exploding in popularity.
- Host: Gergely Orosz (Gage), Pragmatic Engineer podcaster, bantering on tech origins, AI workflows, and future shifts.
- The Vibe: Energetic and fun, blending nostalgic storytelling, mind-blowing AI demos, and geeky excitementāeducational yet addictive like Peter's "casino slot machine" coding.
šļø Key Themes & Topics
The episode traces Peter's improbable rise, AI-fueled rebirth, and radical workflow reinventionāpacked with "holy f**k" moments on solo-building complex software.
Continue reading the full summary in the app ā free to try.
Read Full Summary āFree ā¢ No credit card required
What you'll learn
- 1 (00:00) **šļø Introduction: Peter Steinberger**
- 2 (01:45) **Early Life and Entry into Tech**
- 3 (04:39) **Discovery of iOS and First App**
- 4 (07:48) **Origins of PSPDFKit**
- 5 (14:36) **Scaling PSPDFKit into a Business**
- 6 (19:15) **Tech Stack and Challenges**
- 7 (20:10) **Company Culture and Blogging**
+ Full timestamped outline available in the app
Show Notes
Brought to You By:
ā¢ Statsig ā ā The unified platform for flags, analytics, experiments, and more.
ā¢ Sonar ā The makers of SonarQube, the industry standard for automated code review
ā¢ WorkOS ā Everything you need to make your app enterprise ready.
ā
Peter Steinberger ships more code than Iāve seen a single person do: in January, he was at more than 6,600 commits alone. As he puts it: āFrom the commits, it might appear like it's a company. But itās 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 Moltbot) and founder of PSPDFKit. Moltbot ā a work-in-progress AI agent that shows what the future of Siri could be like ā 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.
Peterās 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.
ā
Timestamps
(00:00) Intro
(01:07) How Peter got into techĀ
(08:27) PSPDFKit
(19:14) PSPDFKitās tech stack and culture
(22:33) Enterprise pricing
(29:42) BurnoutĀ
(34:54) Peter finding his spark again
(43:02) Peterās workflowĀ
(49:10) Managing agentsĀ
(54:08) Agentic engineering
(59:01) Testing and debuggingĀ
(1:03:49) Why devs struggle with LLM coding
(1:07:20) How PSPDFkit would look if built toda
More from this podcast
The Pragmatic Engineer ā