Advanced · Systems

Agent-to-Agent Intent

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A structured statement of purpose one agent sends another so the request can be understood, authorized, and negotiated.

Technical Definition

A structured statement of purpose one agent sends another so the request can be understood, authorized, and negotiated.

How it works

When agents interoperate, prose requests are ambiguous and unverifiable. Agent-to-agent intent packages the request as data: the desired outcome, the acting principal and delegation chain, constraints such as budget or deadline, acceptance criteria, and a correlation identifier. The receiving agent can then match the intent against its published capabilities, check authorization, and respond with acceptance, counter-offer, or refusal — the basis for machine-speed negotiation in agentic commerce.

Related Concepts

• Intent Description Language (IDL) — A structured, machine-readable format for expressing what an agent intends to do, for whom, and under what constraints.
• Agent Delegation — Handing part of a task, and the authority needed to complete it, from a human to an agent or from one agent to another.
• Agent Protocol Semantics — The shared meaning layer of an agent protocol — what messages, verbs, and capability names actually denote.
• Agentic Commerce — Commerce driven by AI agents that compare, negotiate, and purchase on behalf of buyers or sellers.