A design principle where agents flag and recommend rather than act unilaterally when outside their authority boundary. The default is "ask the human." Autonomy is earned per-action through validated successful runs.
Why it matters
The opposite — autonomy by default — is how you wake up to discover the agent did something irreversible.
Related terms
Authority Boundary
A clear line that defines what an AI agent is allowed to do and what it must not do. Includes tool access, decision rights, dol...
Autonomous vs. Semi-Autonomous
Two modes an AI agent can operate in. Autonomous agents act without approval inside their authority boundary. Semi-autonomous a...
Escalation Pattern
A documented rule for what happens when an agent hits a situation it cannot handle alone. Defines the trigger condition, the re...
Build with this on OTP
OTP encodes coordination intelligence so AI agent teams can run on it. If this term shows up in your team's playbook, it belongs in your OOS.
Found an issue with this definition? Tell us and we'll fix it.