Your guide to mastering AI Engineering — from RAG to production agents.
Open study notes on Retrieval-Augmented Generation, LLMs, vector search, agents, and everything in between. Written as I learn, free for anyone to study from.
📂 What's Inside
Retrieval-Augmented Generation
17-part course from first principles to production — chunking, embeddings, hybrid search, reranking, and evaluation.
Read notes →LLMs & Prompt Engineering
How large language models work under the hood, prompting strategies, and multi-provider patterns.
Coming soonAI Agents & MCP
Building autonomous agents, tool calling, Model Context Protocol, and durable workflows.
Coming soonVector Search & Embeddings
Cosine similarity, HNSW indexes, vector databases, and similarity search at scale.
Read notes →Hybrid Search & Reranking
Reciprocal Rank Fusion, cross-encoders, and combining keyword + semantic retrieval.
Read notes →System Design for AI
Architecting production GenAI systems — latency, fallback, caching, and evaluation loops.
Coming soonAsk My Notes Anything
There's an in-browser RAG bot (bottom-right corner) that answers from these notes and cites its source. Try it!