← Artificial Intelligence

Large Language Models

Understanding and using LLMs effectively — from pretraining and alignment to prompt engineering, RAG, and autonomous agents

Large language models are the application layer of transformer-based AI. These lessons cover how LLMs are trained, aligned to human intent, and deployed in production systems — from the raw next-token prediction objective through the agent architectures that extend LLM capabilities beyond text generation.

8. LLM Pretraining 12 min
9. Fine-Tuning and Alignment 12 min
10. Prompt Engineering 11 min
11. Retrieval-Augmented Generation 12 min
12. AI Agents and Tool Use 12 min
13. LLMs Check quiz
14. Lab: Build a RAG Pipeline 30 min lab