Description
Hamel's Blog is written by Hamel Husain, a machine learning engineer with more than 20 years of experience who has worked at Airbnb and GitHub. The notes cover applied AI engineering, machine learning and data science, with a strong focus on evals: how teams debug, analyze and measure LLM systems. Long-form posts include A Field Guide to Rapidly Improving AI Products, Stop Saying RAG Is Dead, Selecting The Right AI Evals Tool and "It's Hard to Eval" Is a Product Smell, and the blog stays current with AI Evals: Everything You Need to Know and Claude's new auto eval tool from September 2026. A practical source for engineers who ship LLM features and need to know whether they work.
