AWS releases multi-agent reference architecture based on the A2A protocol
What happened
On 12 November 2026, the AWS Machine Learning Blog published an article introducing a reference architecture for building composable, interoperable multi-agent systems on AWS based on the A2A protocol. In the architecture, a SaaS compliance agent built with the LangChain enterprise orchestrator and Strands Agents collaborates across AWS accounts and organisational boundaries, without either side depending on the other's framework or SDK and without sharing keys. Public information so far comes only from this single first-hand report; the story remains at the stage of architecture release and solution introduction, with no disclosure yet of subsequent deployment or expansion.
Written by AI from the reports · updated 3 d ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogBuild composable, interoperable multi-agent systems with A2A on AWS
Build a composable, interoperable multi-agent system on AWS with the Agent-to-Agent (A2A) protocol. A LangChain orchestrator on Amazon ECS communicates with a Strands agent on Amazon Bedrock AgentCore across organizational boundaries, using bidirectional, OAuth-authenticated calls, with neither side depending on the other's framework or SDK.
Heat of this event
Current heat 3·Peak in the comparable range 9(Nov 13 04:00)·Change over 24 hours in the comparable range -49%
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.