Research
What we measured, and how.
Notes on writing, strategy and what makes content hold up. Numbers first, method shown.
01 01 Nov 2026
A style score for AI drafts, and where it stops
W10V4 gives a draft one number out of 100 for how closely its habits match writers people read on purpose. It catches habits well. It does not grade writing.
5 min read 02 01 Nov 2026Qwen tied Opus at a tenth of the cost, so we made it our Writer
Qwen 3.7 Plus won our blind rounds fair and square, at two cents a draft. Nine days later a different test, with a new brief and new prompts, put Opus ahead, and we moved again. Here is the method, the bills, and what we would repeat.
4 min read 03 01 Nov 2026Twenty rules cut the stink in our drafts and showed us what they can't fix
We wrote house rules for every agent, measured them, and found that each rule worked at the spot it named and often cost something somewhere else.
5 min read 04 01 Nov 2026A second pass by the same model took our draft from 67 to 88
What a review pass did to our style score, what it did to a blind reader, and the new habit it brought with it.
15 min read