Hamel Husain

How To Make PDFs Your AI Can Actually Read

Giving AI a Credit Card Is Still Painful

8 Claude Code skills I use for building better AI evals

Why The Prompt Matters Less Than The Context

How to Apply Data Science Skills to AI Engineering

How to Design a Data Agent People Can Verify

Putting Claudes "AI Slop" Solution to the Test

Trying the new Claude Eval tool

How To Build And Evaluate Search Agents

How to Stop Building Products Nobody Wants

Continuous discovery transforms product development by replacing speculative, idea-first roadmaps with structured, customer-centric feedback loops. Product management expert Teresa Torres emphasizes that effective discovery requires moving beyond superficial customer interviews—which often trigger confirmation bias—tow...

Stop Picking Embedding Models Off The MTEB Leaderboard

Don't Build Agents, Build Environments Instead

How Multi-Vector Retrieval Works at Scale

How To Turn Evals Into A Better Model

How to Cut Your LLM Classification Costs by 90%

How To Use Open Models Effectively

How to Build Agents That Answer Data Questions

How To Make Codex Run Itself

How To Choose The Right OCR Model

How To Build AI Evals

Implementing robust evaluation systems for AI agents requires a systematic approach that prioritizes observability and high-quality, human-labeled data. Lucas, a developer at Nova Escola, details his transition from manual, spreadsheet-based assessments to an automated pipeline integrated with Claude and Langfuse. By i...