Episode 71: Durable Agents - How to Build AI Systems That Survive a Crash with Samuel Colvin

About this episode

Hugo Bowne-Anderson and Samuel Colvin discuss the importance of engineering principles in building durable AI systems.

Our thesis is that AI is still just engineering … those people who tell us for fun and profit, that somehow AI is so, so profound, so new, so different from anything that’s gone before that it somehow eclipses the need for good engineering practice are wrong. We need that good engineering practice still, and for the most part, most things are not new. But there are some things that have become more important with AI . One of those is durability . Samuel Colvin , Creator of Pydantic AI , joins Hugo to talk about applying battle-tested software engineering principles to build durable and reliable AI agents. They Discuss: * Production agents require engineering-grade reliability: Unlike messy coding agents, production agents need high constraint , reliability , and the ability to perform hundreds of tasks without drifting into unusual behavior; * Agents are the new “quantum” of AI software: Modern architecture uses discrete “agentlets” : small, specialized building blocks stitched together for sub-tasks within larger, durable systems ; * Stop building “chocolate teapot” execution frameworks: Ditch rudimentary snapshotting; use battle-tested durable execution engines like Temporal…

People in this episode

Host: Hugo Bowne-Anderson

Guest: Samuel Colvin

Topics covered

• AI engineering
• durability in AI
• software engineering principles
• production agents
• AI observability
• reliable AI systems

Keywords

• AI
• durability
• engineering
• production agents
• observability
• software principles
• reliability

Mentioned in this episode

Organizations: Temporal

Products: Pydantic AI

More episodes of Vanishing Gradients

• The Future of Agentic Data Science · May 25, 2026 · 1h 5m
• Agent-Harness.ipynb* · May 20, 2026 · 1h 20m
• Agentic Engineering and the Lost Art of Verification · May 12, 2026 · 1h 32m
• Next Level AI Evals for 2026 · April 23, 2026 · 54 min
• Privacy Theater Is Not Privacy Engineering: What It Actually Takes to Ship Safe AI · April 15, 2026 · 1h 7m
• LLM Architecture in 2026: What You Need to Know with Sebastian Raschka · April 13, 2026 · 1h 18m