Agent Frameworks Considered Harmful — Rémi Louf, .txt

Aug 22, 2026 · 0:20:29

Listen to Episode

✨ AI Summary

Initial agent framework failures led to a runtime analysis.
Lost notes became an append-only log; duplicates formed a real queue.
Unversioned prompts were addressed by content-addressed storage.

Guests on This Episode

researcher · 1 podcast appearance

More from AI Engineer

The Agent Behind the Curtain: Building the Oz Cloud Agent Platform — Safia Abdalla, Warp

Aug 22, 2026 · 0:20:51

Inside 847 Production Clinical AI Notes — Sebastian Fox, Composo

Aug 22, 2026 · 0:19:48

Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl

Aug 22, 2026 · 0:22:06

Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean

Aug 22, 2026 · 0:15:54

View all episodes →