experiments
LLM Expect
A Lightweight, Developer-First Way to Test LLM-Powered FunctionsOver the past year, I’ve watched the LLM evaluation ecosystem get more complicated, not less. Teams are now building agent workflows, re
Scaling Qualitative Research with AI
Sometimes you want a quick, dirty review of a product idea from people who you think are your target market. The standard playbook would have been: recruit 8-12 participants, schedule 45-minute calls