This is the surface for anything your AI writes. It runs two deterministic prose donkeys that read what your AI wrote, find the exact lines that give it away, and refuse to pass the text until it reads clean. They never rewrite for you. They tell you what is wrong, the same way every time.
AI text has three diseases a reader feels even when they cannot name them. This surface names them and points at the exact line.
Flat sentences that all run the same length. Power words doing the work evidence should do. Openers that clear the throat before the point. Hedges that refuse to commit. The reader cannot say why, but it feels machine made.
The prose turns to point at its own parts ("that is the map"), count its own list ("the second point is"), aim the reader's eye ("notice the shape of it"), or name itself ("this section argues"). The reader notices the pointing more than the point. Coined by Gaurav Rastogi, 2026.
Words the writer understands and a newcomer does not. Terms used before they are defined. All we-and-our and no you. Copy written to the people who made it, not the person reading it.
Same surface, two checks. Both are deterministic: same text in, the same verdict out.
Why: catches the writing that reads as machine made, manages the reader, or talks
only to insiders.
How: fixed rules for the tells and the six forms of the stoolworm, plus a cheap
reader that checks whether a newcomer understands. Every term it learns becomes a rule for next time.
Why: catches prose that is correct but lifeless, the sentences that do not breathe.
How: measures cadence variance, escalation words, throat-clearing openers, and hedge
density on the EPLS framework. No model, pure rules.
Deworm run on a paragraph stuffed with stoolworms. Every line it flags is a place the prose stopped delivering and started managing the reader.
$ check "In this essay, we lay out the argument. That is the map.
The second position is the one that matters most. Notice the
shape of it. So the fact can be conceded. The honest word is
compromise. Having established that, let me now turn to the cure."
verdict: FAIL stoolworms: 6 inward: 100%
"In this essay" names the container self-reference
"That is the map" points at its own parts self-pointing
"The second position is" counts its own list enumeration
"Notice the shape of it" aims the reader's eye reader-gaze
"So the fact can be conceded" announces its own move move-announce
"The honest word is" grades its own diction diction-grading
cure: open inside the substance, hand off through the material,
trust the reader to feel the shape without being told.
Same paragraph in, the same six findings out, every time.
Call a donkey on its own, or run the surface inside a machine that remembers. Same checks either way. The difference is state.
Send a block of text, get the findings back. Stateless and simple: same text in, the same verdict out. Nothing to set up, nothing remembered. The fast, free way to check one piece of writing.
Connect your own AI to the doloop machine in writing mode and the donkeys run inside the loop: your AI drafts, the donkeys judge, your AI fixes the exact lines, and only clean copy ships. The machine remembers. Every rule it learns becomes your house style, owned by you.
Want this on your writing pipeline? Talk to us, or see the other surfaces.