Domain

LLMs & Generative AI

How large language models work and how to reason about tokens, context, pretraining, prompting, RAG, tools, and agents.

1. Tokenization & Context Windows
2. Transformer Architecture
3. Pretraining, Fine-Tuning & Instruction Tuning
4. Prompting & Decoding
5. Retrieval-Augmented Generation (RAG)
6. Tool Calling & Agents