The harness: the loop, made real
The idea: A harness wraps the model in a real loop: it reads the running notes, the model proposes an action, a tool runs, the result joins the notes — repeat. The model is the same frozen predictor; the harness makes it act.
What you'll be able to do: You can explain what an agent harness is — the tool loop around a frozen model — using Claude Code / Codex as examples.
The problem it solves: A chatbot just talks. But tools like Claude Code and Codex edit your files and run commands. What's the extra piece?
Builds on: Tools & agents: the loop around a frozen model
← Tools & agents: the loop around a frozen model · Next: What's in the context window →
All lessons