T4Autonomous Red Team Operations
Supervision Models for Agents
Human-in-the-loop, on-the-loop, and out-of-the-loop supervision, when each is defensible, and how to map the supervision model to the blast radius of what the agent can do.
Foundational4 min readfoundation streamUpdated Sat Aug 01 2026 00:00:00 GMT+0000 (Coordinated Universal Time)
Part ofGoverning Autonomous Agents
Learning objectives
- Distinguish human-in-the-loop, on-the-loop, and out-of-the-loop supervision
- Match a supervision model to the blast radius of a given action
- Define an approval boundary and place it correctly in an agent's loop
- Explain why some actions must never be delegated regardless of convenience
Academy subscription
Subscribe to unlock this module
This module is part of the StrikeOps Academy subscription. Unlock every paid module, with hands-on labs and knowledge checks.
- Every paid module across all tracks
- Hands-on labs and knowledge checks
- New content as it ships
$59/ month · or $590 / year
The Reference library and Foundation starters are free to read now.