Why Hard-to-Eval AI Products Need Designs That Support Verification

Hamel Husain argues that an AI product whose output is hard to verify is a product design problem, not just an evaluation problem.

He shows before-and-after sketches for an AI data agent, a PE lesson planner, and a workers' compensation report tool, each adding provenance, scoped edits, and checkable evidence.

He notes that designing for verification also makes evals easier to build and grade.