Agent loop
The control structure where a model decides an action, it is executed, and the result feeds the next turn until the task is done.
By Lattice editorial · Entry last reviewed · method
What it implies
Twenty lines, and the least interesting part of an agent system. The engineering is in the host around it: surviving a deploy mid-loop, idempotent side effects, and a hard ceiling on turns and tokens. Prompts are advisory; only the host can stop a loop.
Related terms
- Tool callingA model emitting a structured request to call a function, which your code executes and returns the result of.
- Durable executionA workflow engine that checkpoints progress so work resumes after a crash, rather than restarting from nothing.
- Budget ceilingA hard limit on turns, tokens or wall-clock time, enforced by the host rather than requested in the prompt.