AWS Generative AI Essentials

This course introduces developers to Generative AI with AWS. Designed for developers looking to plug in AI into their workflows and applications, the course highlights many AWS AI offerings—from ready-to-use services to customizable solutions. We begin by showcasing Generative AI within the development landscape, highlighting success stories from a multitude of industries. You'll explore how a sports league changed the story on athlete performance analytics, how a marketing platform scaled to support a 150% increase in image generation demand, and how a global travel company processes 150 petabytes of data to deliver personalized travel recommendations—all fueled by the AWS services covered in this course. At this course's core are three AWS AI services. We'll start with Amazon Q Developer, an AI assistant that integrates into your IDE and command line to accelerate code generation, troubleshoot issues, create documentation, and optimize your development environment. We will then advance to Amazon Bedrock, which provides access to foundation models from many different providers. The course introduces Amazon Bedrock Knowledge Bases for implementing Retrieval Augmented Generation (RAG), AI agents for task automation, Prompt Management for designing and optimizing prompts, Amazon Bedrock Flows for orchestrating AI workflows, and Amazon Bedrock Guardrails for ensuring compliant AI applications. For scenarios requiring more control, you'll learn about Amazon SageMaker AI, a fully managed platform that provides a complete set of tools for data scientists and developers to build, train, and deploy high-quality machine learning (ML) models quickly and at scale Throughout the course, you'll learn how these services integrate with the broader AWS ecosystem, including AWS CodeBuild and CodePipeline for CI/CD workflows, AWS Lambda for serverless AI applications, API Gateway, and S3 for storing training data and model artifacts. You'll gain hands-on experience installing and experimenting with Amazon Q, working with prompts in Amazon Bedrock, setting up Amazon Bedrock Guardrails, and implementing best practices for building applications. Advanced topics include the Model Context Protocol (MCP), Amazon Kiro for spec-driven development, and agentic AI on AWS. By the end of this course, you'll have the skills to select and implement AWS AI services based on what you need and integrate AI capabilities into your workflows and applications. 38:T

• Integrate Amazon Q Developer into your IDE
• Build applications using foundation models available through Amazon Bedrock
• Implement Retrieval Augmented Generation (RAG) to connect AI models with your organization's private data sources
• Design effective prompts and manage them at scale
• Create and launch AI agents that can perform complex tasks through orchestrated workflows
• Implement guardrails to ensure responsible and compliant AI applications
• Select the best AWS AI service based on your use case and required level of control
• Explore-Model Context Protocol and spec-driven development with Amazon Kiro