#a2a

Part 4 · One Agent, Five Platforms In Part 3 I drew the reference architecture: five layers from...

Two agents, on two different frameworks, detect a real AWS incident and hand it off over A2A. One proposes a fix. Nothing executes until a human approves, enforced by Cedar.

Copy-paste ways to read and post on Agent Commons from curl, an MCP client, or an A2A client. No key, no account.

Agent work is long: research, multi-step tool calls, code generation. Blocking on one JSON response hides progress and hits timeouts. The Agent2Agent protocol models a task with explicit states, streams status and artifact updates over Server-Sent Events, and can deliver completion as a push...

We maintain a small open extension for the A2A agent protocol, conduct-v1, and a public register...

We tested Google A2A 1.0 between local Python agents, including discovery, task lifecycle, artifacts, authentication, and migration from pre-1.0 agent cards. Here is what worked, what broke, and where an adapter layer remains necessary.

MCP connects one agent to tools and data. A2A connects autonomous agents to each other through discoverable, long-lived tasks. They are not competitors; they sit at different layers, and getting the boundary wrong is where agent architectures become unmaintainable.

An Agent Card is the public resume of an A2A agent: where it lives, which bindings it speaks, and what skills it offers. Fetching it is easy; trusting it is the part teams get wrong. Here is how discovery and signature verification actually work.

You do not need to rewrite a working HTTP service as an agent framework to be reachable over A2A. A thin, stateless adapter can expose one authenticated business handler as JSON-RPC, REST, and native gRPC, while being honest about which agent capabilities it does not provide.

sprix-sage-router is a Sprix AI research preview for deciding mid-task whether an A2A agent should continue, recruit collaborators, or hand

Short answer: Advanced RAG architecture for AI agents is not a cleverer retriever. It is four stages...

We just opened the task board on Agent Colony with two real, narrow tasks. One delivery already done...