Agentic AI Foundations

Amazon SageMaker Studio helps data scientists to quickly prepare, create, train, deploy and monitor machine learning (ML) models. It does this by bringing together a wide range of features designed specifically for ML. This course trains experienced data scientists to use the tools that are part of Amazon SageMaker Studio, including Amazon CodeWhisperer and Amazon CodeGuru Security Scan Extensions, to improve productivity at all stages of the ML lifecycle.

Course Contents

From LLMs to Agents
Exploring Agentic AI
Understanding Agentic AI Workflows
Introducing Autonomous Agents
Amazon Q and Agentic Development Tools
Agentic AI with Amazon Bedrock
Building DIY Solutions

Target Group

Software developers who are new to the field of agent-based AI and are looking for foundational knowledge and practical implementation skills
Technical professionals exploring AI capabilities and interested in the core components and applications of agent-based AI
Development teams who need to evaluate AI solutions for agents and distinguish between different agent types
AWS users expanding into agent-based AI, including current users of Amazon Q Developer, Amazon Q Business, and Amazon Bedrock Agents

Knowledge Prerequisites

Attendance of the Generative AI Essentials course or equivalent professional experience
Basic knowledge of AWS and experience in software development

Course Objective

Summarize the evolution of agent-based AI and define what makes something "agent-based."</li
Identify the core components of agent systems: Goals, memory, tools, and environment
Distinguish between workflow, autonomous and hybrid agents
Compare AWS service options for Agentic AI (specialized, managed and DIY approaches)
Describe the features and use cases of Amazon Q Developer, Amazon Q Business, and Kiro
Explain the core features of Amazon AgentCore and Amazon Bedrock Agents
Identify basic implementation patterns for Agentic AI
Describe observation and interoperability patterns for agent-based AI systems in production

From LLMs to Agents

Understanding Large Language Models (LLMs)

Innovations powering agents

Evolution timeline from LLMs to Agents

Exploring Agentic AI

Understanding Agentic AI

Types of AI agents

Agentic AI applications

Understanding Agentic AI Workflows

Workflow patterns

Amazon Bedrock flows overview

Introducing Autonomous Agents

How Autonomous Agents work

ReAct

ReWoo

Multi-agent collaboration

AWS Agentic AI solutions

Amazon Q and Agentic Development Tools

Amazon Q Developer

Amazon Q Business

Amazon Q in AWS Services

Kiro: AI-powered IDE with spec-driven development

Agentic AI with Amazon Bedrock

Amazon Bedrock Agents

Amazon Bedrock AgentCore

Hands-on lab: Explore Amazon Bedrock Agents integrated with Amazon Bedrock Knowledge Bases and Amazon Bedrock Guardrails

Building DIY Solutions

DIY solutions

Observability and Monitoring

Agent Interoperability

Course Wrap-up

Next steps and additional resources

Course summary

Classroom training: Do you prefer the classic training method? A course in one of our Training Centers, with a competent trainer and the direct exchange between all course participants? Then you should book one of our classroom training dates!
Online training: You wish to attend a course in online mode? We offer you online course dates for this course topic. To attend these seminars, you need to have a PC with Internet access (minimum data rate 1Mbps), a headset when working via VoIP and optionally a camera. For further information and technical recommendations, please refer to.
Tailor-made courses: You need a special course for your team? In addition to our standard offer, we will also support you in creating your customized courses, which precisely meet your individual demands. We will be glad to consult you and create an individual offer for you.

You can find the complete description of this course with dates and prices ready for download at as PDF.