◈ AWS AGENTCORE BLUEPRINTS
PART V · MULTI-AGENT AND ARCHITECTURE · CHAPTER 29 / 36
TOCCONSULTING.FR
AMAZON BEDROCK / PART V, MULTI-AGENT AND ARCHITECTURE

A2A AND MULTI-AGENT

CHAPTER 29 / 36
IN ONE LINE how agents work together
REV 2026.07

One agent is often not enough: a "travel" agent needs a "flights" agent; a support bot needs a "refunds" agent. Agents work together two ways: A2A, an open protocol to call another agent across teams or vendors, and in-process patterns where one program coordinates several agents. AgentCore hosts A2A agents; Strands gives you the patterns.

New to these words? Read chapter 02 "Key terms" (A2A, MCP, agent, tool). MCP connects agent to tools; A2A connects agent to agents.
[ 1 ] TWO WAYS AGENTS COLLABORATE
A2A across systems
An open standard so your agent can call another agent built by a different team or company.
They discover each other through an Agent Card and talk in JSON-RPC.
AgentCore Runtime hosts A2A servers in production.
IN-PROCESS one program
Strands gives you patterns to run several agents inside one app.
A supervisor that delegates, a swarm of peers, a graph of steps.
No network hop. Best when you own all the agents.
[ 2 ] HOW AGENTCORE HOSTS AN A2A AGENT
STEP 01

SERVE

Your container runs an A2A server on port 9000 at / (the SDK helper serve_a2a does this).

==>
STEP 02

DISCOVER

A caller fetches the Agent Card at /.well-known/agent-card.json to learn the skills and URL.

==>
STEP 03

SEND

The caller sends a JSON-RPC message/send to / (with SigV4 or OAuth).

==>
STEP 04

WORK

The agent runs, isolated in its own microVM, and may use its own tools.

==>
STEP 05

RETURN

It replies with a task and artifacts (the result).

AgentCore acts as a transparent proxy: it passes the JSON-RPC straight through to your A2A container, and adds enterprise authentication and per-session isolation on top. Port 9000 and path / are what make it A2A (vs 8080 + /invocations for HTTP, 8000 + /mcp for MCP).

[ 3 ] THE AGENT CARD, HOW AGENTS FIND AND TRUST EACH OTHER
/.well-known/agent-card.json
name, description, version          the agent's identity
url                              where to reach it
protocolVersion "0.3.0", preferredTransport "JSONRPC"
capabilities { streaming: true }   what it can do
skills [ { id, name, description, tags } ]   what it is good at
[ 4 ] IN-PROCESS PATTERNS (STRANDS PRIMITIVES)
AGENTS-AS-TOOLS

Wrap one agent as a tool another agent can call. Good for a supervisor that delegates.

SWARM

Peer agents collaborate, handing off to whoever is best for the step.

GRAPH

An explicit flow of agents: A, then B or C, with the edges you draw.

WORKFLOW

A structured, multi-step orchestration of agents and tasks.

Plain definitions: chapter 02 "Key terms". Hands-on code: chapter 30. Architecture choices: chapter 31.
SRC: AWS AgentCore Developer Guide (deploy A2A, A2A contract), strandsagents.com, awslabs samples (05-hosting-a2a). DRAWN 2026.06, REV 2026.07.26
◄ PREVIOUS · CH 28
AgentCore Payments, Practical
NEXT · CH 30 ►
A2A and Multi-Agent, Practical
AWS AGENTCORE BLUEPRINTS · CONTENTS
Back to tocconsulting.fr Cover & Table of Contents
PART I · FOUNDATIONS
01AgentCore Overview, Plain LanguageCONCEPT02AgentCore, Key Terms in Plain LanguageCONCEPT03AgentCore, Common Mistakes ExplainedCONCEPT04Inside an AgentCore Agent, BlueprintCONCEPT05Harness, Practical 1, Strands PathPRACTICAL06Harness, Practical 2, Managed HarnessPRACTICAL
PART II · CORE SERVICES
07AgentCore Runtime, Plain LanguageCONCEPT08AgentCore Runtime, PracticalPRACTICAL09AgentCore Memory, Plain LanguageCONCEPT10AgentCore Memory, PracticalPRACTICAL11AgentCore Gateway, Plain LanguageCONCEPT12AgentCore Gateway, PracticalPRACTICAL13AgentCore Identity, Plain LanguageCONCEPT14AgentCore Identity, PracticalPRACTICAL
PART III · TOOLS AND OPERATIONS
15AgentCore Code Interpreter, Plain LanguageCONCEPT16AgentCore Code Interpreter, PracticalPRACTICAL17AgentCore Browser, Plain LanguageCONCEPT18AgentCore Browser, PracticalPRACTICAL19AgentCore Observability, Plain LanguageCONCEPT20AgentCore Observability, PracticalPRACTICAL21AgentCore Evaluations, Plain LanguageCONCEPT22AgentCore Evaluations, PracticalPRACTICAL
PART IV · GOVERNANCE AND TRANSACTIONS
23AgentCore Policy, Plain LanguageCONCEPT24AgentCore Policy, PracticalPRACTICAL25AgentCore Registry, Plain LanguageCONCEPT26AgentCore Registry, PracticalPRACTICAL27AgentCore Payments, Plain LanguageCONCEPT28AgentCore Payments, PracticalPRACTICAL
PART V · MULTI-AGENT AND ARCHITECTURE
29A2A and Multi-Agent, Plain LanguageCONCEPT30A2A and Multi-Agent, PracticalPRACTICAL31Architecture Patterns, Plain LanguageCONCEPT32Multi-Tenant Agents, Plain LanguageCONCEPT33Agent Security and Threat Model, Plain LanguageCONCEPT34Governance at Org Scale, Plain LanguageCONCEPT35Governance at Org Scale, PracticalPRACTICAL36Multi-Region and Distribution, Plain LanguageCONCEPT