A clear line that defines what an AI agent is allowed to do and what it must not do. Includes tool access, decision rights, dollar limits, contact lists, and human approval requirements. Authority boundaries should be encoded in code or configuration, not just in prompts.
Why it matters
Without an authority boundary, "autonomous" means "unbounded." That is how agents make $4,000 mistakes at 3 AM.
Related terms
Escalation Over Autonomy
A design principle where agents flag and recommend rather than act unilaterally when outside their authority boundary. The defa...
Guardrails
Rules and checks that prevent an AI agent from doing things it should not do. Built into prompts, code, or review processes. Pr...
Override Authority
The power to overrule an AI agent's decision or action. Defined in advance with clear conditions and escalation paths. Override...
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.