The exact subset of permissions and actions an AI agent is permitted to execute at a specific moment in time, calculated by combining static grants, runtime policies, environmental factors, approval states, and remaining budgets.
Static permissions describe what an agent could do in theory. Effective authority determines what the agent is allowed to do right now given current risk, budget, location, and approval conditions.
An agent has static authorization to refund up to $500. However, because its daily budget is 90% exhausted, its effective authority is temporarily capped at $50.
Prevents overprivilege and protects against runaway agent actions during changing conditions.
EnterpriseACP dynamically calculates Effective Agent Authority before every tool call or API execution.