Human-in-the-loop
A setup where a person approves each action before it happens.
Human in the loop means the person owns the goal and the steps: they tell the agent what to do or approve it at each step (e.g. accounts receivable where the person asks for each reminder draft, reviews it, sends it).
Also called
- HITL
- Human approval
Kind of
- Human oversight Human involvement in an AI process to monitor, govern or stop it, before it acts, after it acts, or only for certain actions.
Often confused with
- Human-as-judge An eval where a person reviews a system's output and judges its quality.
- Meat proxy A person who approves or passes along AI output without verifying or reading it.
The other half
- Human-on-the-loop A setup where an agent acts on its own while a person watches and can step in or stop it.
Related
- AI brain fry Mental fatigue from guiding, steering and overseeing more AI tools and output than you can handle.
- Task runner A level of autonomy where you give an AI system or agent one specific instruction, and it acts only on that task.
How it connects
- Human-in-the-loop approves each action of Agent
- Human-in-the-loop fits the lower rungs of Levels of autonomy