aws-solutions-library-samples

Guidance For Multi Agent Orchestration Agent Squad On Aws

Name: Guidance For Multi Agent Orchestration Agent Squad On Aws
Author: aws-solutions-library-samples

DevOps community

SOURCE https://github.com/aws-solutions-library-samples/guidance-for-multi-agent-orchestration-agent-squad-on-aws

Description

This Guidance demonstrates how to effectively orchestrate multiple specialized AI agents to solve complex customer support challenges through different coordination mechanisms on AWS. Modern customer service environments demand sophisticated handling of multi-step interactions, personalized responses, and seamless access to various data sources.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Guidance for Multi-Agent Orchestration with Agent-Squad on AWS

A demonstration of how AI agents and human support can work together in an e-commerce customer service environment. This project showcases intelligent query routing, multi-agent collaboration, and seamless human integration for complex support scenarios.

🎯 Key Features

Multi-agent AI orchestration with specialized models
Real-time and asynchronous communication modes
Seamless integration with human support workflow
Tool-augmented AI interactions
Production-ready AWS architecture
Mock data for realistic scenarios

Architecture Design

![agentsqaud](./img/agentsquad.png)

The user accesses the web application through Amazon CloudFront, which delivers content from the Amazon S3 Website bucket, while Amazon Cognito handles authentication and provides temporary credentials via Identity Pool.
The authenticated user sends messages through the web UI, which communicates with AWS AppSync GraphQL API to process queries, mutations, and subscriptions for real-time communication.
AWS AppSync routes customer messages to the Amazon SQS Customer Messages Queue, which triggers the AWS Lambda Customer Message Handler function to process incoming customer inquiries.
AWS Lambda Customer Messages initializes the Agent Squad orchestrator, which uses Amazon Bedrock Classifier to analyze the message content and determine which specialized AI agent should handle the request.
Based on the classification, the message is routed to one of three agents: the Order Management Agent (using Claude 3 Sonnet), the Product Information Agent (using Claude 3 Haiku), or the Human Agent for complex cases requiring human intervention.
The Order Management Agent handles order-related inquiries using tools for order lookup, shipment tracking, and return processing, while the Product Information Agent retrieves product details from the Amazon Bedrock Knowledge Base connected to OpenSearch Serverless.