Skip to Content
View all events

AI Agents with AWS

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Develop intelligent agents with Bedrock, AgentCore, and Strands Agents

What you’ll learn and how you can apply it

  • Build and deploy agents in AWS using AgentCore and Strands Agents
  • Integrate LLMs (AWS Bedrock, Anthropic, or Amazon Nova) into agent workflows
  • Implement strand-based orchestration, agent memory, toolchains, and context
  • Monitor, secure, and scale AgentCore/Strands Agents deployments in production

Course description

Learn to design, build, and deploy intelligent AI agents on AWS. In this hands-on course, you’ll discover how to use Amazon Bedrock, AgentCore, and Strands Agents to create single-agent and multi-agent systems that automate complex enterprise workflows. Through practical exercises, you’ll build agents with conversational memory, planning capabilities, and tool integration.

AWS expert Eduardo Mota covers the complete production lifecycle: agent design, LLM integration, agent orchestration, and deployment best practices including monitoring, security, scaling, and error handling. You’ll come away with the skills to implement production-ready AI automation systems that deliver measurable business value.

This live event is for you because...

  • You’re a cloud developer, architect, or product leader building AI automations.
  • You work with Python and AWS and want to leverage AgentCore/Strands Agents.
  • You want to orchestrate complex workflows and autonomous tasks with modern agents.

Prerequisites

  • A computer with an AWS account set up
  • Python 3.x and AWS CLI installed on your machine, with access to Bedrock, AgentCore, and Strands Agents
  • Course GitHub repo downloaded (link to come)
  • Test Bedrock and AgentCore access
  • Local notebook or editor ready for hands-on development
  • Python proficiency (functions, classes, async)
  • Familiarity with AWS basics (CLI, cloud resources)
  • Exposure to LLMs, GenAI, or prior automation projects (helpful but not required)

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

AgentCore and Strands Agents introduction (30 minutes)

  • Presentation: Agent architecture—what problems do agents solve?; agent frameworks (AgentCore, Strands Agents, and AWS Bedrock Agents)
  • Hands-on exercise: Run base agent in AgentCore
  • Q&A

LLM integration and tool use (55 minutes)

  • Presentation: Connecting Bedrock models (Claude/Nova) to Strands Agents
  • Demonstration: Building your first agent tool
  • Hands-on exercise: Create an agent with 2–3 custom tools
  • Group discussion: Tool selection patterns and common pitfalls
  • Q&A
  • Break

Orchestration and strand planning (70 minutes)

  • Presentation: Visualizing strand flows and multistep planning; strand orchestration concepts and patterns; visualizing strand flows
  • Hands-on exercises: Build a three-strand sequential workflow; add memory and context to your strands
  • Group discussion: Error handling strategies and recovery patterns
  • Q&A
  • Break

Advanced deployment (50 minutes)

  • Presentation: Deployment architecture and AWS service integration; monitoring, security, and scaling patterns; live agent monitoring and debugging
  • Hands-on exercise: Deploy your agent to AWS with CloudWatch logging
  • Q&A
  • Break

Production patterns (35 minutes)

  • Presentation: Cost, scalability, and security for agent-based systems
  • Group discussion: Real-world example of agent in enterprise workflow
  • Q&A

Your Instructor

  • Eduardo Mota

    Eduardo Mota is an accomplished AWS Cloud Architect and Machine Learning Specialist. He holds a Bachelor of Business Administration and multiple Machine Learning certifications, demonstrating his relentless pursuit of knowledge. Eduardo's journey includes pivotal roles at DoiT International and AWS, where his expertise in AWS cloud architecture and optimization strategies significantly impacted operational efficiency and cost savings for multiple organizations. Eduardo's commitment to AWS mastery is underscored by his AWS certifications including Machine Learning and Data Analytics, making him a trusted guide in the realm of cloud innovation and artificial intelligence. Beyond his technical prowess, Eduardo's diverse interests, including photography and biographies, reflect his insatiable curiosity and multidimensional perspective.

Skill covered

DevSecOps