What is an Agent Harness?

Harness engineering is how we build systems around models to turn them into work engines. A harness is every piece of code, configuration, and execution logic that isn't the model itself. A raw model is not an agent, but can become one when a harness gives it things like state, tool execution, feedback loops, and enforceable constraints. Concretely, a harness includes things like: • System Prompts • Tools, Skills, MCPs + and their descriptions • Bundled Infrastructure (filesystem, sandbox, browser) • Orchestration Logic (subagent spawning, handoffs, model routing) • Hooks/Middleware for deterministic execution (compaction, continuation, lint checks) Learn more about Deep Agents, LangChain's open-source harness: LangChain Academy → https://academy.langchain.com/courses/foundation-introduction-to-deepagents Docs → https://docs.langchain.com/oss/python/deepagents/overview Agent Harnesses & Deep Agents 101 Workshop (Recording) → https://events.langchain.com/register/apac-anz-agent-harnesses-and-deep-agents-workshop/