Course Overview
In this advanced two-day course, software developers learn to build and customize AI solutions by using Amazon Bedrock programmatically. Through hands-on exercises and labs, participants will invoke foundation models through Amazon Bedrock APIs, implement Retrieval Augmented Generation (RAG) patterns with Amazon Bedrock Knowledge Bases, and develop AI agents with tool integration. The course focuses on the practical implementation of prompt engineering techniques, responsible AI practices with Amazon Bedrock Guardrails, open source framework integration, and architectural patterns for real-world business applications.
Who should attend
This course is intended for:
- Software developers.
Prerequisites
We recommend that attendees of this course have:
- Completed the Generative AI Essentials AWS instructor-led course
- Intermediate-level proficiency in Python
- Familiarity with AWS Cloud
Course Objectives
In this course, you will learn to do the following:
- Develop generative AI applications using Amazon Bedrock.
- Design architecture patterns of generative AI applications.
- Configure Amazon Bedrock APIs to invoke foundation models (FMs) programmatically.
- Develop agentic AI applications by integrating Amazon Bedrock tools and open source frameworks.
- Build custom solutions with Retrieval Augmented Generation (RAG) and Amazon Bedrock Knowledge Bases.
- Integrate open source SDKs with Amazon Bedrock to build business.
- Optimize model responses by applying prompt engineering techniques.
- Evaluate generative AI application components.
- Implement responsible AI practices to protect generative AI.
Outline: Developing Generative AI Applications on AWS (DGAIA)
Day 1
Course Introduction Module 1: Exploring Components of Generative AI Applications on AWS
- Understanding generative AI concepts
- Identifying AWS generative AI stack components
- Designing generative AI application components
Module 2: Programming with Amazon Bedrock
- Guiding model response generation
- Using Amazon Bedrock programmatically
Hands-on lab: Develop with Amazon Bedrock APIs Hands-on lab: Develop Streaming Patterns with Amazon Bedrock APIs
Module 3: Applying Prompt Engineering for Developers
- Introducing prompt engineering
- Introducing prompt techniques
- Optimizing prompts for better results
Module 4: Using Amazon Bedrock APIs in Common Architectures
- Implementing architecture patterns with Amazon Bedrock APIs
- Exploring common use cases
- Adding conversational memory to extend context
Hands-on lab: Develop Conversation Patterns with Amazon Bedrock APIs[/b]
Module 5: Customizing Generative AI Responses with RAG
- Implementing Retrieval Augmented Generation (RAG)
- Using Amazon Bedrock Knowledge Bases
Hands-on lab: Develop Retrieval Augmented Generation (RAG) Applications with Amazon Bedrock Knowledge Bases[/b]
Module 6: Integrating Open Source Frameworks with Amazon Bedrock
- Invoking a foundation model in Amazon Bedrock using LangChain
- Using LangChain for context-aware responses
Hands-on lab: Develop a Generative AI Application Pattern using Open Source Frameworks and Amazon Bedrock Knowledge Bases[/b]
Day 2
Module 7: Evaluating Generative AI Application Components
- Evaluating application components
- Evaluating model output
- Evaluating RAG output
- Optimizing latency and cost
Hands-on lab: Evaluating Retrieval Augmented Generation (RAG) Applications[/b]
Module 8: Implementing Responsible AI
- Understanding responsible AI
- Mitigating bias and addressing prompt misuses
- Using Amazon Bedrock Guardrails
Hands-on lab: Securing Generative AI Applications Using Bedrock Guardrails[/b]
Module 9: Using Tools and Agents in Generative AI Applications
- Using tools
- Understanding AI agents
- Understanding open source agentic frameworks
- Understanding agent interoperability
Module 10: Developing Amazon Bedrock Agents
- Implementing Amazon Bedrock Flows
- Designing Amazon Bedrock Agents
- Developing Amazon Bedrock Inline Agents
- Designing multi-agent collaboration
- Using Amazon Bedrock AgentCore
Hands-on lab: Developing Amazon Bedrock Agents Integrated with Amazon Bedrock Knowledge Bases and Guardrails
Course Wrap-Up