What Is Hamel's Blog (hamel.dev)?

Updated

Hamel's Blog at hamel.dev is the personal site of Hamel Husain, a machine learning engineer with 20+ years of experience. It publishes long-form notes on applied AI engineering, machine learning, and data science, with a strong emphasis on evals—the practice of debugging, analyzing, and measuring AI systems. It is a blog and teaching hub, not a product or documentation site, so expect essays, course pointers, and a newsletter rather than API references.

Who runs it

The site describes the author as a machine learning engineer who has worked at Airbnb and GitHub, including early LLM research used by OpenAI for code understanding, and who has led and contributed to popular open-source machine-learning tools. His current stated focus is "bringing data science back to AI"—helping teams debug, analyze, and measure their systems through evals.

This background matters for how you read the posts: the writing tends to come from hands-on product work rather than pure theory, and several articles are framed as lessons from building AI products.

What the site covers

The homepage organizes content into three areas:

  • Learn With Me — a co-taught course, AI Evals for Engineers and PMs, described as having over 5,000 students from 500+ companies (including OpenAI, Anthropic, and Google). The page points to upcoming cohorts and to a separate AI Evals Guide for common questions.
  • Blog — a dated index of long-form posts, listed newest first.
  • Follow Me — newsletter subscription.

Recurring themes in the blog index

Theme Example posts from the index
Evals and measurement "AI Evals: Everything You Need to Know" (9/18/26), "Do Automated Evals Work?" (7/11/26), "Selecting The Right AI Evals Tool" (10/1/25), "Using LLM-as-a-Judge For Evaluation" (10/29/24)
Building AI products "A Field Guide to Rapidly Improving AI Products" (3/24/25), "AI Product Engineering Notes" (8/12/26), "Your AI Product Needs Evals" (3/29/24)
LLM engineering practice "Tokenization Gotchas" (12/17/23), "Optimizing LLM latency" (10/15/23), "vLLM & Large Models" (10/28/23)
Tooling and workflow "Inspect AI, An OSS Python Library For LLM Evals" (6/23/25), "Evals Skills for Coding Agents" (3/2/26), "Why I Stopped Using nbdev" (1/18/26)

The dates in the index run into late 2026, so treat the list as the site's own chronology rather than a fixed archive.

When this site is useful to you

  • You are starting an eval practice and want conceptual grounding plus tool comparisons. Start with the "Everything You Need to Know" post, then the tool-selection piece.
  • You ship an AI product and need to justify measurement work to a team. The product-focused essays ("It's Hard to Eval" Is a Product Smell, Your AI Product Needs Evals) argue the case directly.
  • You want structured learning. The course page is the entry point; check it for current cohort timing rather than assuming a schedule.
  • You want ongoing updates. The newsletter is the subscription mechanism offered on the page.

If you need official library documentation or vendor support, this is not that kind of site—it is one practitioner's writing and teaching.

Practical notes

The site does not publish pricing for the course on the homepage; the page directs readers to check for upcoming cohorts, so confirm cost and dates there before planning around it. Likewise, the newsletter signup is the stated way to follow new posts—there is no indication of a paywall or login requirement for reading the blog itself, but verify on the individual page if access matters to you.