AI Fundamentals & Large Language Models
AGAI 102
Understand the foundations of modern AI and the large language models (LLMs) that power agentic systems. Learn how neural networks learn, what makes LLMs special, and how they generate text one token at a time.
The Foundations of Modern AI
To understand agentic AI, you need to understand the engine that powers it: the large language model. This course builds that foundation systematically, starting from the basics of machine learning and working up to the transformer architecture that underlies GPT, Claude, Gemini, and every other leading LLM.
From Rules to Learning
Early AI systems were built on hand-crafted rules. Modern AI systems learn from data. This shift — from programming behavior explicitly to learning it from examples — is what makes modern AI so powerful and so different from what came before.
What Makes LLMs Special
Large language models are trained on vast amounts of text and learn to predict what comes next in a sequence. From this simple objective emerges a remarkable set of capabilities: understanding language, answering questions, writing code, translating between languages, and reasoning through complex problems.
What You Will Learn
This course builds your understanding of LLMs from the ground up — how they are trained, how they represent and process text, what the transformer architecture actually does, and why scale matters so much. You will finish with a clear mental model of LLMs that serves you throughout the rest of the curriculum.
Who This Course Is For
This course is for learners who want to understand the engine that powers all modern AI agents. Whether you are a developer who has used LLM APIs and wants to understand what is happening under the hood, a technical manager evaluating AI systems, or a researcher moving into AI from another field, this course gives you the conceptual foundation you need.
What you will learn
- Explain how machine learning differs from traditional programming
- Describe how neural networks learn from data
- Explain what tokens are and how LLMs process text
- Summarize the key ideas of the transformer architecture
- Distinguish between pre-training and fine-tuning
- Identify emergent capabilities in large language models
Major topics
Why this course matters
Every agentic AI system is built on top of a language model. Understanding how LLMs work at a conceptual level helps you use them more effectively, diagnose failures, and make informed decisions about which models to use for which tasks.
Course modules
How Language Models Work
Understand the core mechanics behind modern language models, including tokens, context windows, attention, and the transformer architecture.
Training and Fine-Tuning LLMs
Learn how large language models are pretrained, scaled, fine-tuned, and aligned to become useful assistants and agentic system components.
Common misconceptions
LLMs understand language the same way humans do
Bigger models are always better
LLMs retrieve information from a database like a search engine
Fine-tuning teaches a model entirely new knowledge
Ask your AI guide
Ask anything about AI Fundamentals & Large Language Models, or choose a suggested question below.
AI responses are educational and may not be perfectly accurate. Press Enter to send, Shift+Enter for new line.
Related courses
Introduction to Agentic AI
A broad, conceptual introduction to Agentic AI as a discipline. Explore what AI agents are, how they reason, plan, and act in the world, and why agentic systems represent a paradigm shift in how we build and deploy AI.
Prompt Engineering
Master the art and science of writing effective prompts. Learn how prompt structure, context, and framing dramatically affect model outputs, and explore advanced techniques like chain-of-thought, few-shot prompting, and system prompt design.
Memory & Context Management
Learn how AI agents store, retrieve, and manage information across interactions. Explore the different types of agent memory — in-context, episodic, semantic, and procedural — and the techniques used to give agents effective long-term recall.