Human in the loop for coding agents

By Arun Dass · Published 1 October 2026 · Updated 2 November 2026

Human in the loop means you can see what a coding 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. Friday, the free open-source app, gives you each of these on your own computer.

What controls should you look for?

ControlWhat it does
See every stepShows what the agent is doing as it happens
RedirectYou send the agent a new instruction or a note on a line
InterruptYou can stop a run without restarting it
LimitsSets what the agent is allowed to do
ReviewLets you accept a change or send it back
UndoRolls a run back

How do you set limits in Friday?

Each agent works in one of three modes: Plan (read and propose only), Manual (change files, and ask before running commands) or Auto (edit files and run commands without asking). Pick the mode per agent.

Every run ends in a change set you read before you keep it. Leave a note on a line or a range and send it back to the agent. Tasks on the shared task board are checked before they count as done: their tests run and another agent reviews them. Each agent can work in its own git worktree, so a run you reject leaves your own branch alone.

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. Friday itself is free and MIT licensed; the download page has the installers.

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 stop a run, and stopping an agent ends its task, not the agent: it stays ready for the next message.

Where do I see what an agent did?

In the session, which shows every message, command and file change, and in the change set at the end of the run.

Run your next task in Friday.

Free and open source (MIT), on your own computer: the desktop app for macOS, Windows and Linux, or one command with Node.js 22.