Introduction to Generative AI

Introduction to Generative AI introduces learners to the foundations of artificial intelligence and explains how modern tools such as ChatGPT, Gemini, Claude, and other generative AI platforms work. The course explores the differences between artificial intelligence, machine learning, deep learning, and generative AI, while introducing large language models, tokens, context windows, response generation, and common limitations such as inaccurate or misleading outputs. Through focused lessons, learners develop practical prompt engineering skills and explore Retrieval-Augmented Generation, embeddings, vector databases, AI agents, tools, memory, planning, workflows, automation, and the Model Context Protocol. The course also introduces APIs, no-code tools, chatbot architecture, document integration, deployment, and responsible AI use. In the final module, learners bring these concepts together by building a simple AI-powered application. Learning Outcomes: > Understand how generative AI, large language models, tokens, and context windows work. > Design effective prompts using clear instructions, roles, context, examples, constraints, and structured outputs. > Explain how Retrieval-Augmented Generation, embeddings, and vector databases connect AI systems with external information. > Understand how AI agents use tools, memory, planning, workflows, automation, and the Model Context Protocol. > Build a simple AI-powered application using APIs, no-code tools, chatbot architecture, document integration, and deployment. > Earn a certificate of completion.