Workshop: How AI agents really work

Casually paced supported workshop. We'll go as fast as our slowest progress & cross the finish line together, thus a 3 hour time-block. Run AI development on AWS - do this on your own account to leave the workshop with an agentic harness you control.

Learn how to deploy open-weight models (Qwen3) & namebrands including Amazon Nova & Anthropic Claude Sonnet 5. Note that promotional credits only cover Amazon Nova brands, so we recommend those models for those using promotional credits

Strands Agents is an open source SDK that takes a code-first approach to building and running AI agents in just a few lines of code. Strands connects two core pieces of the agent together: the model and the tools, simplifying the development of AI agents

important note- this will NOT be a sandboxed workshop - $25 credits will be available to cover anything we tackle in the workshop on your own account - account signup in advance required. We hope participants leave the workshop with a framework they can continue building on

This workshop was created by AWS but will be lead by local community members.

#### AI, Model & Agent Basics

Learn the fundamentals of creating and using Strands agents:
Basic agent initialization and usage

• System prompt customization
  *HTTP tool integration

#### Model Providers

Explore different model providers and configuration options

Note: Some portions of this lab require a pre-existing AWS account for the 'generate_image' tool.

#### AWS Service Integration

Learn to integrate AWS services with your Strands agents:

• Using the `use_aws` tool
  *Examples with Amazon S3 and Amazon DynamoDB

Note: The code in this lab requires a pre-existing AWS account to properly utilize the 'use_aws' tool. An example Amazon DynamoDB Table is used to generate results when querying a table.

#### Model Context Protocol (MCP)

Deep dive into the Model Context Protocol:

• MCP server creation
  *Tool definition and usage
• Calculator and Weather agents examples
  *Interactive Jupyter notebook tutorial

#### Agent-to-Agent Communication

Build multi-agent systems with inter-agent communication:

• A2A communication patterns
  *Employee/HR agent system example
• MCP server for data sharing
  *REST API integration

#### Observability & Evaluation

Monitor and evaluate agent performance:

• Restaurant recommendation agent example
  *LangFuse integration for observability
• RAGAS evaluation framework
  *Performance metrics and tracing