This hands-on workshop brings together generative AI, cloud, application development, Infrastructure as Code, containers, and CI/CD to build a complete AI document assistant on AWS. Unlike my regular Hands-On Introduction courses, this workshop isn’t focused on teaching one technology from scratch. Instead, we’ll start with an empty folder and use an AI coding agent inside Cursor to build and deploy an application that lets users upload their own documents and ask questions grounded in those documents. And just like in the other workshops in this series, we’re not going to hand-write the application or infrastructure code ourselves.
We’ll direct the AI agent, review what it produces, test its decisions, and work through the problems we encounter along the way. The application we’ll build is an AI-powered document assistant. Users will be able to upload documents through a Next.js application, store them in Amazon S3, and make them available through an Amazon Bedrock Knowledge Base. Once the documents have been processed and indexed, users can ask questions and receive answers grounded in their own content, together with citations pointing back to the source documents.
