A2A Protocol Explained: How Agent Cards Let AI Agents Discover Each Other Across Frameworks
goyalshaliniuk · x · 2026-11-05
First post in a series explaining the Agent2Agent (A2A) protocol, covering how agents discover each other before collaborating.
- Every agent exposes an Agent Card describing its capabilities, skills, and connection details
- Other agents use these cards to find the right specialist for a given task
- Most useful for ecosystems where agents come from different teams or frameworks
The author links to the official A2A spec, which covers protocol operations, streaming events, push notifications, auth, JSON-RPC/gRPC/REST bindings, and its relationship to MCP.
More from coding & agent
- Tim O'Reilly at AgentCon: open architecture beats open-source licenses for the agentic web — bibryam · 2026-11-05
- Dev tip: install GitHub CLI for agent dev so agents can see issues, PRs and CI — DanielLockyer · 2026-11-05
- Compacting with the same model cuts Claude Code session costs by ~75% via cache hits — JoshuaJosephson · 2026-11-05
- Microsoft's HCU unifies programmatic, semantic, and visual channels for computer-use agents — MicrosoftResearch · 2026-11-05
- NOFire deleted most of its agents: single loop gave 1.5x diagnoses at 60% lower cost — tianyin_xu · 2026-11-05
- Microsoft Details Running Coding AI Locally on 128GB RTX Spark Windows PCs Without Token Fees — lee_stott · 2026-11-05