Vibeleaderboard
← All Intel
Intel / post

A2A course: cross-framework agent interop after ACP merged in

Source
x.com
Date
Andrew Ng@AndrewYNg

New course: A2A: The Agent2Agent Protocol, built with @googlecloudtech and @IBMResearch, and taught by Holt Skinner, @ivnardini, and Sandi Besen. Connecting agents built with different frameworks usually requires extensive custom integration. This short course teaches you A2A, the open protocol standardizing how agents discover each other and communicate. Since IBM’s ACP (Agent Communication Protocol) joined forces with A2A, A2A has emerged as the industry standard. In this course, you'll build a healthcare multi-agent system where agents built with different frameworks, such as Google ADK (Agent Development Kit) and LangGraph, collaborate through A2A. You'll wrap each agent as an A2A server, build A2A clients to connect to them, and orchestrate them into sequential and hierarchical workflows. Skills you'll gain: - Expose agents from different frameworks as A2A servers to make them discoverable and interoperable - Chain A2A agents sequentially using ADK, where one agent's output feeds into the next - Connect A2A agents to external data sources using MCP (Model Context Protocol) - Deploy A2A agents using Agent Stack, IBM's open-source infrastructure Join and learn the protocol…

Read the full post on X

Context

A2A gives agents built with different software frameworks a shared way to discover and communicate with one another. The Agent2Agent course teaches developers to expose each through an A2A server, then create clients that communicate with those servers. This lets one agent's output feed another within a coordinated workflow. The distinction from is the connection being standardized: A2A connects agents to other agents, while MCP connects them to external tools and data. The healthcare scenario is a teaching example of that coordination.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
More from Andrew Ng
Recommended reads
Comments

Checking sign-in…

Loading comments…