AI And LLMs

You learn what artificial intelligence means, how the field developed, and the difference between writing rules and learning from examples. You also get a clear map of the AI tools and models available today.

You learn how a machine learning model is built from data: features, labels, training, and evaluation. You also learn to spot overfitting and to measure a model honestly.

You learn how a single artificial neuron works, how layers of neurons form a network, and how backpropagation trains it. You build intuition by running a tiny network in Python.

You learn how networks represent words as numbers called embeddings and how attention lets each word look at the others. You finish with a clear picture of the transformer, the design behind modern language models.

You learn how a large language model reads text as tokens, learns during pretraining, and is shaped into an assistant by fine-tuning and preference tuning. You also learn what the context window is and how it limits what a model can use.

You learn a repeatable way to write prompts: set a role, state the task, give examples, define the format, and iterate. You also learn the common ways prompts fail and how to fix them.

You learn four ways to get facts and abilities into a model that was trained months ago: the context window, retrieval (RAG), embeddings with vector search, and tool use. You finish able to choose between them and to build a small retrieval pipeline.

You learn how a model combined with tools and a loop can carry out multi-step tasks, and when a fixed workflow is the better choice. You also learn where agents fail and how human approval keeps them safe.

You learn to measure whether an AI system works, to spot and reduce hallucinations and bias, and to protect users and data. You finish with a small evaluation set and a practical safety checklist.

You write real Python that calls a language model API, keeps a conversation going, returns structured data, and tracks cost and speed. You finish with a working command-line chat app you can extend in the capstone.

You examine how AI is changing jobs, schools, legal questions, and public rules, with a high-level look at the EU AI Act. You leave with a practical framework for using AI responsibly.

You plan, build, test, and present a small AI assistant for a real user, using the skills from all eleven weeks. You finish with a working demo, an evaluation report, and a clear story of what you learned.