Developing Generative AI Applications on AWS

– • Describe generative AI and how it aligns to machine learning
– • Define the importance of generative AI and explain its potential risks and benefits
– • Identify business value from generative AI use cases
– • Discuss the technical foundations and key terminology for generative AI
– • Explain the steps for planning a generative AI project
– • Identify some of the risks and mitigations when using generative AI
– • Understand how Amazon Bedrock works
– • Familiarize yourself with basic concepts of Amazon Bedrock
– • Recognize the benefits of Amazon Bedrock
– • List typical use cases for Amazon Bedrock
– • Describe the typical architecture associated with an Amazon Bedrock solution
– • Understand the cost structure of Amazon Bedrock
– • Implement a demonstration of Amazon Bedrock in the AWS Management Console
– • Define prompt engineering and apply general best practices when interacting with foundation models (FMs)
– • Identify the basic types of prompt techniques, including zero-shot and few-shot learning
– • Apply advanced prompt techniques when necessary for your use case
– • Identify which prompt techniques are best suited for specific models
– • Identify potential prompt misuses
– • Analyze potential bias in FM responses and design prompts that mitigate that bias
– • Identify the components of a generative AI application and how to customize an FM
– • Describe Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs
– • Identify Amazon Web Services (AWS) offerings that help with monitoring, securing, and governing your Amazon Bedrock applications
– • Describe how to integrate LangChain with LLMs, prompt templates, chains, chat models, text embeddings models, document loaders, retrievers, and Agents for Amazon Bedrock
– • Describe architecture patterns that you can implement with Amazon Bedrock for building generative AI applications
– • Apply the concepts to build and test sample use cases that use the various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach