Agent2Agent (A2A) Protocol
Agent2Agent (A2A) is an open, versioned protocol for AI agents to discover skills, exchange messages, and manage tasks. Each implementation must name a supported protocol version.
Agent Card → message → task → artifactprotocolVersion: 1.0A planning agent reads a remote agent's Agent Card and sees its skills and endpoint. It sends a task, follows status updates, and receives an itinerary artifact.skills + authtask submittedworking → doneAgent Card → message → task/status → artifact over a versioned bindingOPSAnother example
A planning agent reads a remote agent's Agent Card and sees its skills and endpoint. It sends a task, follows status updates, and receives an itinerary artifact.
Main parts
- 01Client agent
- 02Agent Card
- 03Interface, version, and identity
- 04Messages and parts
- 05Task and status
- 06Artifacts and updates
Use it when
Use it when independent agents in different systems need a shared, versioned task interface. Check identity, permission, transport, and version support.
Do not use it when
Do not use A2A as a loose name for any multi-agent chat. It does not replace MCP, tool calling, or application permissions.
Name used in code
Agent Card → message → task/status → artifact over a versioned binding Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate Agent2Agent (A2A) Protocol to make AI behavior measurable and tied to evidence. User context: A planning agent reads a remote agent's Agent Card and sees its skills and endpoint. It sends a task, follows status updates, and receives an itinerary artifact. AI method or concept: Agent2Agent (A2A) Protocol. Why it fits: Use it when independent agents in different systems need a shared, versioned task interface. Check identity, permission, transport, and version support. Do not use it when: Do not use A2A as a loose name for any multi-agent chat. It does not replace MCP, tool calling, or application permissions. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): A formal document may still be a draft, release candidate, or final version. Check its status and browser or platform support. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of Agent2Agent (A2A) Protocol. Definition: Agent2Agent (A2A) is an open, versioned protocol for AI agents to discover skills, exchange messages, and manage tasks. Each implementation must name a supported protocol version. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.