Temporal Agent Harness: An early look at durable agent infrastructure

This post introduces the Temporal Agent Harness, an "outer harness" designed to provide control and durability for AI agents. It emphasizes bringing your own inner harness (e.g., OpenAI Agents SDK, LangGraph), introduces a "turn"-based model for agent interactions, strongly typed agent interfaces for composition, and a "code mode" for executing model-generated Python code in durable, secure sandboxes. Key principles highlighted are durable execution, meeting developers where they are, providing strong control points, and treating agents as application components rather than just chat loops.