Same Skill, Different Model
A skill that works beautifully on Opus can quietly fall apart on Haiku, and the reverse happens too....
#evals
4 posts tagged with evals
The Missing Playbook for AI Agents
Most people are building agents the way they wrote their first prompts. But we already know how to...
March 17, 2026
·
20 min read
Building AI Tools You Can Trust
You want to build an AI application. Something useful.
Unit Tests for Intelligence
A few months ago, as I was exploring machine learning while working on a project, one of my models...