Getting Started with AWS Generative AI for Developers

Overview

Get introduced to generative AI with this foundational course designed for developers looking to use AWS' generative AI services. This course serves as your gateway to understanding and implementing generative AI solutions using Amazon Bedrock. You'll begin by exploring the fundamentals of generative AI, understanding its place within the broader AI landscape, and learning key concepts such as foundation models, prompts, and inference. Through hands-on labs and demos, you'll gain practical experience invoking foundation models and interpreting their responses. The course then dives into Amazon Bedrock Runtime APIs, covering operations like InvokeModel and asynchronous invocations. You'll learn to implement streaming responses, manage provisioned throughput, and apply guardrails to ensure responsible AI use. A significant portion of the course focuses on working effectively with foundation models. You'll explore model selection criteria, learn the art of prompt engineering, and understand how to optimize your interactions with generative AI tools. By the end of this course, you'll have an understanding of generative AI concepts and hands-on experience with Amazon Bedrock. You'll be ready to start integrating AI capabilities into your applications, setting the stage for more generative AI development in subsequent courses. Please note: The hands-on exercises are optional and require access to your own AWS account. Completing these activities may result in minimal usage charges.

Syllabus

Module 1: What is Generative AI?

In this module, you will gain foundational knowledge of generative AI, including the differences between AI, machine learning, deep learning, and the role of large language and foundation models. You will explore key concepts such as prompts, inference, and responses, and see how these are practically applied using Amazon Bedrock. Through demos and hands-on labs, you will invoke foundation models to generate outputs like text, images, and code. This module also introduces Amazon Q Developer and how generative AI can enhance the software development lifecycle.

Module 2: Accessing Amazon Bedrock Foundation Models

This module focuses on integrating generative AI into applications using Amazon Bedrock’s APIs and runtime features. You will learn to invoke foundation models using synchronous, asynchronous, and batch methods, understanding important configurations like temperature and throughput options. The module also covers choosing the right foundation model, applying prompt engineering techniques, and implementing responsible AI practices such as guardrails. You will also explore real-world developer tasks enhanced by Amazon Q Developer, such as infrastructure generation, automated documentation, and feature development.