Agent2Agent
A protocol for interoperability between autonomous agents built by different vendors on different frameworks — capability discovery, task delegation, and structured message exchange across organizational boundaries.
Why it matters
Interoperability protocols distribute capability faster than they distribute accountability. A2A defines how agents talk; it does not define whose balance sheet absorbs the outcome when a delegated task goes wrong.
What it is not
These are routinely confused with Agent2Agent. The distinctions are not pedantic — each one has consequences for how a system is governed.
A2A is agent-to-agent. MCP is agent-to-tool. Using them interchangeably obscures which boundary a given interaction actually crosses.
Relationships
Typed edges into the rest of the ontology. These are what make the canon traversable rather than merely readable.
| Verb | Target | Meaning |
|---|---|---|
produces | Agent Card | The subject emits the object as an output. |
addresses | Systemic behavior | The subject speaks to the object as a question or concern. |
dependsOn | A2A | The subject cannot function correctly without the object. |
Record
| Canonical identifier | QIS-TERM-00018 |
| Status | Canonical industry term |
| Adoption | Emerging |
| Domain · Layer | Protocol · Intelligence |
| Origin | Originated at Google; contributed to the Linux Foundation. |
| Semantic aliases | None recorded. |
| First published | 2026-08-02 |
| Last reviewed | 2026-08-02 · 180-day cycle |
Cite the identifier, not the URL. Identifiers are stable; URLs may change. This entry is free to read, quote and index under the dual license. Corrections to [email protected] are published.