Agentic payments terms in the payments glossary
How AI agents move money — spending limits, human-in-the-loop approvals, agent compliance, and the authorization layer behind agent-initiated payments.
Agentic payments
Payments initiated by AI agents rather than people — screened, bounded, and documented so software can move real money a compliance team can defend.
Agent compliance
The controls that keep AI-agent payments inside a compliance program — a verified principal, screening on every instruction, and a record for every transfer.
Agent spending limits
Caps on what an AI agent may pay — per transaction, per day, or per month — enforced at the account layer rather than inside the agent’s own code.
Human-in-the-loop approval
A control that holds an automated payment until a named person reviews it — the escalation path when an agent’s instruction breaches a limit or trips monitoring.
Model Context Protocol
An open standard that lets AI agents and assistants connect to external tools and data — including payment APIs — through one common interface.
Agent authorization
The scoped, revocable grant that lets an AI agent act on a person’s or business’s money — defining what it may do and how much it may move.