Agent2Agent Protocol
Also called A2A, A2A protocol.
The Agent2Agent (A2A) protocol is an open specification that lets AI agents built by different vendors and frameworks discover each other's capabilities, delegate tasks, and exchange results.
Description
Google announced A2A in April 2025 and later contributed it to the Linux Foundation. It is designed to complement the Model Context Protocol. MCP connects an agent to tools and data, while A2A connects agents to other agents. Agents advertise what they can do in a machine-readable agent card.
Sources
- Google (2025). Announcing the Agent2Agent Protocol (A2A).
- Linux Foundation A2A Project (2025). A2A Protocol.
Cite this entry
Protologue. (2026). Agent2Agent Protocol. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0147). https://protologue.com/t/agent2agent-protocol/
BibTeX
@misc{protologue_agent2agent_protocol,
title = {Agent2Agent Protocol},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
note = {Entry PTL-0147},
url = {https://protologue.com/t/agent2agent-protocol/}
}New terms, as they're coined
One email a week with the newest techniques, each defined and sourced like this entry.
Delivered through Beehiiv. Unsubscribe from any issue.