Generative AI Foundations and Setup

This unit introduces the current generative AI landscape, core prompt-engineering practices, and Amazon Bedrock’s role in model access while addressing multimodal model capabilities and security/privacy considerations. Students will also prepare a local development environment by installing and verifying Python, Jupyter Notebook with LangChain, and the AWS CLI to support subsequent hands-on development and deployment units.

Learning Objectives

• Analyze the current generative AI landscape by comparing foundational and multimodal models, vendor offerings (including Amazon Bedrock), typical capabilities, limitations, and application use cases.
• Apply prompt engineering principles to design, test, and iterate prompts for generative models, documenting expected outputs and common failure modes for text and multimodal inputs.
• Demonstrate installation and configuration of a Bedrock-ready development environment by installing Python, Jupyter Notebook, LangChain, and the AWS CLI and verifying connectivity to AWS Bedrock endpoints.
• Evaluate security, privacy, and organizational considerations when planning end-to-end generative AI projects and produce a basic project plan that includes data handling policies, risk mitigations, and compliance checkpoints.