Skip to content

AI Glossary · Concepts

What is Agent Harness?

Agent Harness

An agent harness is the software around a model that runs its action loop, supplies context, routes tool calls and returns results for the next step.

Also known as: agentic harness

· Updated · Chain of Thought

AI Agents

  • 2 explainers
  • 7 episodes
  • 1 guest clip
  • 2 sources

Separate the loop from its state and tools

The model proposes actions; the surrounding software supplies context, routes calls and feeds results into the next iteration. Anthropic’s April 2026 account separates that harness loop from a durable session log and the sandbox that performs work. Other implementations draw these boundaries differently. A saved session is not the same object as the model’s current context window or the external service’s records.

In episode 69 at 15:29, Joel Hron describes a simple harness exposing Thomson Reuters applications during training. The harness supplies access; training changes how the model uses it.

Diagnose a restart before repeating an action

Fictional example: an AI agent requests a document-conversion job using an application operation ID, J17. The worker stops before it saves the tool response. The request might already have reached the conversion service. A missing local response does not prove the external operation failed.

RecordStatusNext step
Local request onlyUnknownAsk service for J17
J17 acceptedNot confirmed completeCheck job status
J17 completedRecorded completeCheck output artifact
No service statusUnknownFlag for review

An operation ID helps correlate records; it prevents duplicate work only if the service actually supports and enforces that behavior. Inspect the service contract before retrying a write.

LangGraph’s checkpointer documentation explicitly says replay runs nodes after a selected checkpoint again, including API calls. Its durability modes also differ in when state is written. A generic claim that an agent “has checkpoints” does not tell you which external effects can repeat.

Test what survives an interruption

In a controlled environment, interrupt before a tool call, after the service accepts it and after the result is durably recorded. Inspect the session, execution state and external result separately. Test an unavailable status service too; an unresolved outcome should remain visible rather than becoming a confident completion message.

AI observability connects recorded calls and results for diagnosis. If the tool returns an authorization error, inspect access and execution controls; repeated wrong choices with working access point to different questions about instructions, context and the model. Use the framework decision guide to compare implementations, and LLMOps to track the application versions involved in the failure.

Hear it from the guest

“We will put the model into a harness, like a very simple agentic harness, with access to our TR applications and tools.”
Watch on YouTube

Quotes lightly edited to remove filler words.

Sources

  • Anthropic: Scaling Managed Agents — April 2026 account that separates the harness (the loop that calls the model and routes tool calls), the append-only session log and the sandbox; checked November 2, 2026.
  • LangChain: LangGraph checkpointers — Replay re-executes nodes after the selected checkpoint, including LLM calls and API requests; the exit, async and sync durability modes set when state is written; checked November 2, 2026.

Go deeper

From the conversation