# What is Agent harness? Definition and meaning

An agent harness is the software that wraps a language model and runs it as an agent, handling the loop, tools, context, permissions and limits.

## Definition

**Agent harness**: An agent harness is the software that wraps a language model and runs it as an agent, handling the loop, tools, context, permissions and limits.

In short: The model thinks, the harness acts.

## When it is used

It powers coding agents, research agents and any system where a model takes many steps with tools.

## Where it fits

Agent harness belongs to **Frontier topics** in the [Agentic AI](/topics/agentic-ai) topic. These are the other terms in the same group:

- **[Agent identity and delegation](/glossary/agent-identity-and-delegation)**: Agent identity and delegation is the set of methods that give an AI agent its own identity and a limited, traceable right to act for a person.
- **[Agentic commerce](/glossary/agentic-commerce)**: Agentic commerce is buying and selling in which an AI agent finds products, makes choices and completes payment on a person's behalf.
- **[Generative UI](/glossary/generative-ui)**: Generative UI is an approach in which a model decides, at run time, what interface to show the user, rather than relying only on fixed, pre-built screens.

## Learn more

The full guide to **[Agent harness](/tools/agent-harness)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Advanced RAG](/glossary/advanced-rag) · Next term: [Agent identity and delegation](/glossary/agent-identity-and-delegation)
