One donkey per kind of output, all of them here. Run any of them and you get the specific problems, where each one is and the evidence for it, with the same verdict on every run. Writing starts on our own homepage copy, because we check our writing with the thing we sell.
Dead prose, hedging, jargon, self-management tics, flat cadence. Paste any AI text.
Sycophancy (the Mirror), a dialogue stuck in one register (the Wall), flat task-talk, narrowing. One turn per line, or "Speaker: text".
Upload a chart or slide. Reviewed substance first (does it carry a real finding?), then style (chartjunk, direct labels, color, title-as-finding). This one reads the image with a vision model, so it is not byte-deterministic, and it is rate-limited here.
Upload a PDF. The extraction donkey detects the table structure and pulls the cells deterministically, the same numbers every run. Byte-identical across 90 runs, 2,332 cells audited with 0 errors. (For the full visual overlay on the source page, the extraction donkey also runs standalone at wysiwyd.doloop.io.)
Paste a link. The website donkey crawls the site and runs all four faces in one pass: Structure (one header, one menu, no orphans), Voice (AI-writing tells), Words (a caged reader on the headlines and copy), and Design (the CSS audit plus a vision pass on the layout). Same site in, same verdict out.
Paste code. The donkey flags security gaps (a network length reaching a copy with no bounds-check, CWE-125), smells (long parameter lists, swallowed errors), hardcoded secrets, and documentation drift (a docstring naming a parameter the function does not have). Same code in, the same verdict out, no model.
Routes you to a real page, asks when ambiguous, or refuses. No model on the answer path, so it never invents.