Async supervision: how to run coding agents while you are away from the desk

The promise of an agent is that it works while you do something else. The reality, for most people, is that they watch it. Supervision that requires presence cancels the parallelism it was supposed to create.

The switching tax

Rubinstein, Meyer and Evans' task-switching experiments found that alternating between tasks carried a measurable time cost on every switch, larger for complex or unfamiliar tasks; the American Psychological Association's summary of that line of work puts the productive-time loss from heavy switching at up to 40%. Watching an agent is a switching machine: you look, it is fine, you look away, it asks, you look back.

Two ways to supervise

Synchronous: you watch the session, answer as it asks, and do nothing else. Safe, and no faster than doing the work yourself for anything short. Asynchronous: you start the session and leave; the agent works until it needs you, the ask reaches you where you are, you answer, and it continues. This is the mode in which agents pay for themselves, and it needs three things: the ask has to reach you, it has to be answerable in seconds, and unanswered asks have to fail safe.

What makes async supervision safe

Deny on timeout, so an unanswered request never becomes a yes. Arguments in the request, so you are not approving a verb. A summary on demand, so you can rebuild context in one screen after an hour away. And a session list ranked by who is blocked, so three parallel sessions do not become three parallel anxieties.

The wrist as the supervision surface

PeakWatch is built for the asynchronous mode. Sessions are listed by what needs you; a blocked agent sits at the top with a countdown. Tap to approve, dictate the next prompt, or ask for a summary of what happened. Sessions you started at a keyboard are mirrored too, and you can take one over from the watch. You are somewhere else. The work continues.