Context Engineering from Scratch
The art and science of filling the context window with the right information.
Pods in this Course
Context Engineering for LLMs
The art and science of filling the context window with just the right information for the next step
Prompt Design Principles
Master the science of steering LLMs through system prompts, few-shot learning, chain-of-thought reasoning, structured output, and prompt chaining.
Retrieval-Augmented Generation (RAG) Systems
Build RAG systems from first principles — from chunking and embeddings to hybrid retrieval, reranking, and end-to-end evaluation with RAGAS.
Memory Architectures for LLM Applications
How to give your LLM the ability to remember — from simple buffers to hybrid long-term memory systems.
Context Optimization & Evaluation
How to compress, budget, measure, and continuously improve the information you feed your LLM — from token budgeting and prompt compression to RAGAS evaluation, A/B testing, and production monitoring.
Build Your Own LLM Wiki from Scratch
Build Your Own LLM Wiki from Scratch