Overview

This workshop demonstrates how to build durable AI agents that survive crashes and failures by combining OpenAI’s Agents SDK with Temporal’s distributed systems platform. The session covers building agentic loops that can restart from where they left off without losing progress or re-burning tokens.

Watch the Video

Key Takeaways

  • Build agents that survive failures - Traditional agent frameworks lose all progress when processes crash, but combining Temporal with agent frameworks creates durable agents that automatically resume from where they left off
  • Program the happy path, get durability for free - Temporal handles retries, state management, and failure recovery automatically, letting developers focus on business logic instead of distributed systems complexity
  • Event sourcing eliminates token waste - When agents crash on the 1,350th turn, Temporal’s event sourcing means you won’t re-burn those expensive LLM tokens when the agent restarts
  • Microagents enable better architecture - Small, focused agents that do one thing well can be orchestrated together, similar to how microservices revolutionized software architecture
  • Logical processes vs physical processes - With Temporal, developers can think about processes as logical entities rather than worrying about physical process management, making human-in-the-loop scenarios much simpler

Topics Covered