What it does
Check whether your team is actually using AI well, measured on context discipline, evaluation maturity, and experimentation rigor.
Currently
Live and browser-only with no signup. You answer a short set of questions and get a read on how well your team uses AI across context discipline, evaluation maturity, and experimentation rigor. Scoring is deterministic and rules-based, not an LLM, so results are consistent and repeatable.
Recently shipped
- Mar 24, 2026Shipped the health check: scoring on context discipline, evaluation maturity, and experimentation rigor.
How it's built
How I built it
I built this as the companion to the maturity assessment, for teams that are already past the question of whether they use AI and stuck on whether they use it well. It measures the things that actually separate good practice from cargo-culting: how much context you feed the model, whether you evaluate output, and how disciplined your experiments are. Keeping the scoring deterministic mattered most here, because a tool that grades your rigor should be rigorous itself.