AWS AI/ML Solution Labs

A collection of example code and resources for AWS AI/ML services, created and maintained by AWS Specialist Solution Architects.

Overview

This repository provides AWS users with practical examples and use cases for AI/ML services including Amazon Bedrock and Amazon SageMaker. The code includes Jupyter notebooks for experimental use cases and deployable Infrastructure as Code (IaC) artifacts.

Contents

• Jupyter Notebooks: Interactive examples and experiments
• IaC Templates: Deployable infrastructure code
• Code Artifacts: Production-ready implementations
• Use Cases: Real-world AI/ML scenarios

Featured Use Cases

Amazon Returns & Refunds Assistant

A Strands AI agent demonstrating country-specific policy retrieval using Amazon Bedrock Knowledge Base with metadata filtering. Perfect for learning how to build policy-based Q&A systems.

View Use Case →

AWS Cost Analysis Agent

MCP-based agent for calculating and analyzing AWS service costs including Bedrock, AgentCore, and EMR.

View Use Case →

Services Covered

• Amazon Bedrock
• Amazon SageMaker
• Related AWS AI/ML services

Getting Started

1. Clone this repository
2. Navigate to the specific service folder
3. Follow the README instructions in each folder
4. Ensure you have appropriate AWS credentials configured

Prerequisites

• AWS Account with appropriate permissions
• AWS CLI configured
• Python 3.11+ (for Jupyter notebooks)
• Jupyter Lab/Notebook (for interactive examples)

Authors

AWS Specialist Solution Architects

License

This project is licensed under the MIT License - see the LICENSE file for details.