Skip to content
Glossary

Agent Delegation

Agent delegation is the controlled granting of a scoped, time-bound authority to an AI agent to act on behalf of a user or another agent. The delegation specifies exactly which capabilities, tenants, and actions are permitted, so an agent operates under explicit, revocable, and auditable limits.

Synonyms: delegated authority, scoped delegation, agent authorization, agent grant

Agent delegation answers a hard governance question: how can an autonomous agent act for someone without inheriting unlimited power? The pattern issues a scoped, time-bound grant that names precisely which capabilities, tenant, and actions the agent may exercise, and that can be revoked at any time. Because the grant is explicit, every action the agent takes is attributed to both the agent and the principal that delegated it, and high-risk actions still pass through the same approval policy as any other. Default-deny scoping keeps delegation safe: an agent can do only what it was specifically granted.

Frequently asked questions

What does a delegation scope define?
The capabilities an agent may use, the tenant it may act within, the actions it may propose or execute, and an expiry, so authority is narrow, time-bound, and revocable.
How does delegation stay accountable?
Every delegated action is attributed to both the agent and the delegating principal and recorded in the audit trail, with sensitive actions still routed through approval policy.