AI Pattern · Safety
Human-in-the-Loop Pattern
The agent requests human approval before it acts.
For consequential actions, the agent pauses and surfaces what it intends to do, waiting for a human to approve, edit, or reject before executing. It keeps a person accountable for irreversible steps while still letting the agent do the planning and the safe work autonomously.
How it works
- 1Agent plans an action (send, delete, charge, deploy)
- 2Pause and surface the proposed action to a human
- 3Human approves, edits, or rejects it
- 4Execute only on approval, and log the decision
Strengths
- Safety on irreversible, high-impact actions
- Accountability and a clear audit trail
- Builds trust in autonomous systems
Watch-outs
- Slower, gated on human availability
- Approval fatigue if overused
- Needs a flow to surface decisions clearly
When to use it
Destructive or irreversible actions, and anything touching money, production, or external parties. Reserve auto-execution for safe, reversible steps.
Example prompt
Before any action that sends a message, spends money, or deletes data, output a PROPOSED ACTION block describing it and stop. Proceed only after an explicit “approve”.