Human in the loop for coding agents
Human in the loop means a person can see what an agent is doing, steer it, and stop it. For coding agents, that means visible steps, a way to redirect, limits on what the agent may do, and review before anything ships.
What controls should you look for?
| Control | What it does |
|---|---|
| See every step | Shows what the agent is doing as it happens |
| Redirect | Suggests a change that lands at the agent’s next step |
| Interrupt | Stops a run without restarting it |
| Limits | Sets what the agent is allowed to do |
| Review | Lets you accept a change or send it back |
| Undo | Rolls a run back |
How do you set limits in Friday?
When you link a machine, you choose a mode: plan only, edit files, or edit files and run commands. Friday does not go beyond the mode you pick.
The session owner can pause or cancel a run at any time, even while someone else is driving, and chooses which connections agents can use.
When should a person approve something?
- Anything that deletes or overwrites data.
- Anything that touches production.
- Anything that spends money or sends messages to other people.
What does human in the loop not do?
It does not make an agent correct. A person still has to look. See how to review AI-generated pull requests.
Common questions
Does someone need to watch every step?
No. Set limits, review before anything ships, and watch closely when the work is risky.
Can I stop an agent mid-run?
Yes. You can interrupt a run without restarting it.
Who can pause or cancel a run?
The session owner always can, even when someone else is driving.