What we are building, testing and learning.

Every entry answers the same eight questions: what we asked, why it matters, its state, what we built, the evidence, what we learned, what it does not prove, and what changes next. Negative results are published as results.

LIVERUNNING INTERNALLYRUNNING LABBUILDINGWORK IN PROGRESSDIRECTIONPLANNED RESEARCH
We are testing whether a tiny decision model can handle the hundreds of semantic judgments surrounding frontier-model work — without giving it authority to act. What if the expensive AI is doing the wrong job?
Featured · Experiments · RUNNING LAB · updated 2026-09-17

Tell us what is true about your business.

A few questions, in your own words — type them or talk. A person reads what you send and follows up. Nothing is published and nothing is sent on your behalf.