Permissions & safetyPatternValidated

AFK

Also called: away from keyboard, autonomous

AFK means running an agent unattended for long stretches while you are away from the keyboard. It is only safe with strong guardrails and automated checks, since no human is watching each step.

James Phoenix
Understanding Data Updated July 2, 2026

AFK stands for away from keyboard: running an agent unattended for long stretches while you do something else. You kick off a task, walk away, and let the agent grind through it in agent mode without approving each step.

What makes it safe (or not)

AFK is where agents start to feel like real leverage: hours of work happening while you sleep. It is also where they are most dangerous, because there is no human in the loop to catch a wrong turn early. The whole thing rests on guardrails standing in for the attention you have removed:

  • [Automated checks](/ai-coding-dictionary/automated-check): tests, typecheck, lint, and build that the agent must pass before its work counts.
  • A sandbox so a mistake cannot reach anything you care about.
  • A tight, well-specified task so the agent has less room to wander.

Trust is earned per task

Autonomy is a graduation, not a default. The move is to start with a human in the loop, watch where the agent goes wrong, and only remove yourself once your checks reliably catch those failures. An agent left alone without gates will happily spend an hour producing confident, broken work, and you will not know until you come back.

Watch out
Do not run AFK on work you have not first watched the agent do well while supervised. If no automated check can tell whether the result is right, you are not running unattended, you are gambling unattended.

Related terms

PatternProven

Human in the loop

Human in the loop means keeping a person in the agent's decision path to approve, steer, or verify its work. It is the deliberate counterweight to full autonomy.

Read definition →
Concept

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.

Read definition →
Concept

Automated check

An automated check is a machine-verifiable gate that agent output has to pass, like tests, a type check, a linter, or a build. It either passes or fails with no judgment, which makes it the backbone of trusting agent code, especially when you are running unattended.

Read definition →
AntipatternProven

Lethal trifecta

The lethal trifecta is an agent having access to private data, exposure to untrusted content, and a way to communicate outward, all at once. Any two are usually survivable; all three make data theft a matter of someone asking.

Read definition →
AntipatternEmerging

Agent trap

An agent trap is content placed where an agent will find it, designed to work on an agent rather than a human reader. The target is not a person browsing but an automated reader that acts on what it reads.

Read definition →
Concept

Blast radius

Blast radius is how much damage an action can do if it turns out to be wrong. It is the measure that lets you scale review and permissions to consequence instead of treating every change the same.

Read definition →

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