Agentic AI Foundations

This course is intended for:

- Software developers new to agentic AI seeking foundational knowledge

- Technical professionals exploring AI capabilities and interested in core components and applications of agentic AI

- Development teams evaluating agentic AI solutions and needing to differentiate between agent types

- AWS Users expanding into agentic AI, including current users of Amazon Q Developer, Amazon Quick Suite, and Amazon Bedrock AgentCore

After this course participants should be able to:

• Summarize the evolution of agentic AI and define what makes something agentic
• Identify core components of agentic systems
• Distinguish between workflow, autonomous, and hybrid agents
• Identify basic implementation patterns for agentic AI
• Compare AWS service options for agentic AI
• Describe capabilities and use cases of Amazon Quick Suite, Amazon Q Developer, and Kiro
• Explain Strands Agents framework and its applications
• Build and customize a basic AI agent using Strands Agents SDK
• Develop a simple task-specific agent for real-world application using Strands Agents SDK
• Explain Amazon Bedrock AgentCore
• Describe observability and interoperability patterns for production agentic AI systems

Day 1

Module 1: From LLMs to Agents

• Limitations of Large Language Models (LLMs)
• Innovations powering agents 
• Evolution from LLMs to agentic AI systems

Module 2: Exploring Agentic AI

• Understanding agentic AI
• Types of AI agents
• Agentic AI applications

Module 3: Understanding Agentic AI Workflows

• Workflow patterns
• Amazon Bedrock flows overview

Module 4: AWS Agentic Development and Productivity Tools

• AWS agentic AI solutions
• Amazon Quick Suite
• Amazon Q Developer
• Hands-on lab: Accelerating software development using Amazon Q Developer
• Kiro: AI-powered integrated development environment (IDE) with spec-driven development

Module 5: Implementing agentic AI Frameworks with Amazon Bedrock AgentCore

• Agentic AI frameworks
• Hands-on lab: Getting started with Strands Agents
• Amazon Bedrock AgentCore

Module 6: Building Custom Solutions

• Customizing agentic infrastructure
• Observability and monitoring
• Agent interoperability

Module 7: Course Wrap-up

• Next steps and additional resources
• Course summary

We recommend that attendees of this course have:

• Generative AI Essentials or equivalent work experience
• Basic AWS knowledge and software development experience

• GK4501 - AWS Technical Essentials
• GK910027 - Generative AI Essentials on AWS

None

The following courses are recommended for further learning and development:

• GK910010 - Developing Generative AI applications on AWS

Activities :

This course includes presentations, hands-on labs, and group exercises.