In this episode, we dive into why AI agents often feel fragile and what it takes to make them reliable in real-world systems. The discussion covers state and memory, planning vs execution, long-horizon tasks, failure recovery, and the tooling needed to ship agents into production.A practical conversation for anyone building or deploying AI agents beyond simple demos.
Chapters:
Intro
Agent Fragility
State & Memory
Planning vs Doing
Long Tasks
Failure Recovery
Tooling
Production Lessons
Wrap-Up
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.