Agents & tools

Agent mode

Agent mode is a setting where the model runs the loop autonomously, planning and acting on its own, rather than giving a single chat reply or edit. More capable, and it needs more trust.

James Phoenix
Understanding Data Updated July 2, 2026

Agent mode is the setting where the model stops being a chat partner and becomes a worker. Instead of answering your message once, it runs a loop: plan a step, take an action, look at the result, decide the next step, and keep going until the task is done or it needs you. The same underlying model powers both modes. Agent mode is about giving it the leash to act on its own.

What changes when you switch it on

In a plain chat, the model produces text and stops. You read it, you decide, you act. In agent mode the agent closes that loop itself:

  • It chooses actions, calling tools to read files, run commands, and edit code without asking between each one.
  • It works multi-step, chaining many actions toward a goal rather than answering a single question.
  • It keeps going until it finishes or hits something it is not allowed to do.

That autonomy is exactly what makes it powerful and exactly what makes it risky.

Capability buys you trust problems

More independence means more can happen without you in the loop, good and bad. This is why agent mode leans hard on guardrails. The permission mode decides which actions still need your sign-off, and keeping a human in the loop for the consequential steps is what makes running autonomously safe rather than reckless.

Tip
Match the leash to the stakes. Let an agent run freely on a throwaway branch or in a sandbox, and tighten the permissions when it is touching anything you cannot easily undo.

Related terms

Building with AI agents?

This dictionary is part of how I think about agentic engineering. If you want the same thinking applied to your codebase, that is what I do.

See how I can help