YOLO mode
YOLO mode is the informal name for running an AI agent with approvals disabled, letting it edit files and run commands without asking each time. It is much faster and removes the review step that would otherwise catch a bad change before it lands.
There are legitimate uses. Throwaway prototypes, scratch branches, and generated projects you would rather regenerate than debug all justify it, because the cost of a bad change is close to zero.
The risk is not the model doing something malicious; it is the model doing something reasonable-looking and wrong across twenty files while you are not watching. Unattended runs on code you care about are how that becomes expensive.
What this means in practice
If you use it, make the blast radius small first: a clean working tree, a branch you can throw away, and no production credentials in the environment. Git is the safety net, and it only works if you committed before you started.
Prompts for the tools this applies to
Related terms
- Agent mode
Agent mode is the setting in an AI coding tool where the model can act rather than only answer: creating and editing files, running terminal commands, and iterating on the result.
- Autonomous coding agent
An autonomous coding agent completes a described task without step-by-step supervision: it plans, edits, runs, and verifies on its own, reporting back when done.
- Plan mode
Plan mode makes an AI coding tool propose an approach before it edits anything.