Glossary · Phase 10 · Agent harnesses
Managed agents
A hosted option where Anthropic runs the agent loop and a sandbox container for each session.
Try it now
Each reply is one model call. Two ask for tools, so the loop runs them and goes round again; the third ends the turn.
Learn it properly
What an agent harness is · The software around a model that turns it into an agent. About 30 minutes.
Other terms from the same lesson
- agent harness: The software around a model that turns it into an agent: the loop, tools, permissions, context management, memory and logging.
- Claude Agent SDK: A library that packages Claude Code's harness: built-in file, shell and web tools, permissions, hooks, subagents and sessions, run on your own machines.
- scripted model: A stand-in for a model that returns prepared replies in order, so harness code can be tested quickly and repeatably.
- test harness: Code that runs other code under controlled conditions and checks the results.
- tool runner: A helper in the Anthropic SDKs that runs the agent loop over tools you define.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.