ai-evals
Prathamesh Pathak · ·12 min read
Eval pipelines that hold up
A beginner-friendly method for measuring AI quality with golden sets, slices, LLM judges, model comparison, and schedules.
Writing
Thoughts on product management, career growth, and building things people love.
A beginner-friendly method for measuring AI quality with golden sets, slices, LLM judges, model comparison, and schedules.