Agents & tools · Glossary term

What is Agent Harness?

The runtime around a model that assembles context, exposes tools, manages state, enforces limits, records traces, and decides when the agent should continue, retry, ask, or stop.

Why does Agent Harness matter?

Two systems using the same model can perform very differently because their harnesses provide different context, tools, feedback, and safety boundaries.

Agent Harness in practice

Your harness can limit an agent to five tool calls, persist a checkpoint after each accepted patch, and require a passing test command before completion.

What is the common confusion about Agent Harness?

A harness is broader than a prompt template and narrower than the complete product.

Learn Agent Harness in the course

Start with

  • The Minimal Agent Workbench

    The smallest useful workbench is three files: a root instructions router, a state file, and a task board. Everything else is layered on top. If a repo cannot carry these three, no model will save it.

    Phase 14: Agent Engineering

Lessons that name Agent Harness in a title or section

  • Agent Harness Loop Contract

    The harness is the agent. The model is a coprocessor. This lesson freezes the loop contract you can wire any model into.

    Phase 19: Capstone Projects

Taught in Phase 14: Agent Engineering.

Also covered in Phase 19: Capstone Projects.

  • AgentA software system that lets a model select actions toward a goal, observe tool or environment results, and continue under an orchestration…
  • Tool ContractThe complete agreement for a tool boundary: purpose, typed inputs, outputs, validation, permissions, side effects, errors, timeouts,…
  • Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
  • Verification GateA control point that blocks progress until defined evidence satisfies a correctness or quality criterion.
  • SandboxAn isolated execution environment that restricts an agent's access to files, processes, network destinations, credentials, and host…
  • Coding AgentAn agent specialized for software work that can inspect a repository, edit files, run development tools, and use their outputs to advance…
  • LLM (Large Language Model)A language model with enough capacity and broad training to perform many language tasks through prompting or adaptation.
  • OrchestrationThe control logic that sequences, branches, delegates, retries, pauses, resumes, and terminates work across model and tool steps.
  • Termination ConditionAn explicit rule that ends or pauses an agent run when it succeeds, fails, exhausts a budget, reaches a safe boundary, or requires…

More terms in Agents & tools

Open the Agents & tools list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.