How RAG Actually Works
A practical walkthrough of retrieval-augmented generation — what to retrieve, how to chunk, and where systems fail.
Library
Articles
Practical notes on ML, LLMs, agents, and shipping AI systems.
Prompting That Survives Production
Move past clever one-off prompts. Structure instructions, constrain outputs, and evaluate like you mean it.
Building an Agent Loop You Can Trust
Agent demos look magical. Reliable agents look boring: tight loops, tool contracts, and hard stop conditions.
Ship a Tiny RAG App in One Afternoon
A concrete path from folder of docs to a working Q&A endpoint — without drowning in framework soup.