Developing Generative AI Applications in AWS

After this course participants should be able to:

• Define the importance of generative AI and explain its potential risks and benefits
• Discuss the technical foundations and key terminology for generative AI
• Recognize the benefits and use cases of Amazon Bedrock
• Describe the basic functions, types, and various use cases of foundation models
• Define prompt engineering and apply general best practices when interacting with FMs
• Describe Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs
• Describe architecture patterns that can be implemented with Amazon Bedrock for building useful generative AI applications
• Describe how to integrate LangChain with large language models (LLMs), prompt templates, chains, chat models, text embeddings models, document loaders, retrievers, Agents for Amazon Bedrock
• Build and test several examples of use cases that employ various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach

Day 1

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 result

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

Day 2

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 Base

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

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

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

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

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

• Official course book provided to participants