<p><strong>Brought to You By:</strong></p><p>• <a target="_blank" href="http://statsig.com/pragmatic"><strong>Statsig</strong></a> — ⁠ The unified platform for flags, analytics, experiments, and more.</p><p>• <a target="_blank" href="https://www.sonarsource.com/pragmatic/?utm_medium=paid&#38;utm_source=pragmaticengineer&#38;utm_campaign=ss-ai&#38;utm_content=podcast-sonar-ai-lp&#38;utm_term=ww-all-x&#38;s_category=Paid&#38;s_source=Paid%20Other&#38;s_origin=pragmaticengineer"><strong>Sonar</strong></a> – The makers of SonarQube, the industry standard for automated code review</p><p>• <a target="_blank" href="https://workos.com/"><strong>WorkOS</strong></a> – Everything you need to make your app enterprise ready.</p><p>—</p><p>Mario Zechner is the creator of Pi, a minimalist, self-modifying AI coding agent, that is the foundation upon which OpenClaw (created by Peter Steinberger) is built. Meanwhile, Armin Ronacher is the creator of Flask, and a longtime user of Pi. The pair are also friends.</p><p>I sat down with Mario and Armin for the latest episode of the Pragmatic Engineer Podcast for an interesting conversation about AI and their reservations about it – even though both are heavily invested in building AI-powered tools.</p><p>Mario explains why he built Pi, and gives his take on why it has become so popular. Armin walks us through how he uses AI tools, including building a game with Pi, and why he always puts human judgment firmly at the heart of his approach.</p><p>We cover the risks of over-automation, the limits of agentic workflows, and why strong engineers with informed judgment still matter. We also get into the challenges of working with code written by non-engineers, and whether open source can withstand a tidal wave of agent-generated code.</p><p>—</p><p><strong>Timestamps</strong></p><p>(00:00) Intro</p><p>(07:30) How Mario, Armin, and Peter Steinberger met(15:15) How 30 dev teams use AI agents: learnings</p><p>(21:50) The importance of judgment</p><p>(24:26) Challenges when non-engineers write code</p><p>(28:30) Downsides of over-automation</p><p>(32:18) Pi</p><p>(48:09) OpenClaw + Pi</p><p>(50:54) “Clankers”</p><p>(57:32) Open source and AI</p><p>(1:00:22) Complexity as the enemy</p><p>(1:02:50) Building an AI-native startup</p><p>(1:11:52) “Slow the F down”</p><p>(1:16:40) MCPs vs. CLI</p><p>(1:25:03) Predictions and staying up to date</p><p>—</p><p><strong>The Pragmatic Engineer deepdives relevant for this episode:</strong></p><p>• <a target="_blank" href="https://newsletter.pragmaticengineer.com/p/the-impact-of-ai-on-software-engineers-2026">The impact of AI on software engineers in 2026: key trends</a></p><p>• <a target="_blank" href="https://newsletter.pragmaticengineer.com/p/cycles-of-disruption-in-the-tech">Cycles of disruption in the tech industry</a></p><p>• <a target="_blank" href="https://newsletter.pragmaticengineer.com/p/the-ai-engineering-stack">The AI engineering stack</a></p><p>• <a target="_blank" href="https://newsletter.pragmaticengineer.com/p/the-creator-of-clawd-i-ship-code">The creator of OpenClaw: "I ship code that I don't read"</a></p><p>• <a target="_blank" href="https://newsletter.pragmaticengineer.com/p/what-is-inference-engineering">What is inference engineering? Deepdive</a></p><p>—</p><p>Production and marketing by <a target="_blank" href="https://penname.co/">⁠⁠⁠⁠⁠⁠⁠⁠</a><a target="_blank" href="https://newsletter.pragmaticengineer.com/p/engineers-leading-projects">https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠</a>. For inquiries about sponsoring the podcast, email [email protected].</p> <br/><br/>Get full access to The Pragmatic Engineer at <a href="https://newsletter.pragmaticengineer.com/subscribe?utm_medium=podcast&#38;utm_campaign=CTA_4">newsletter.pragmaticengineer.com/subscribe</a>