CalibratedDecisions.

Repo · Documents & research

snifftest

A prose linter for AI writing tells: regex rules plus Jev for judgment.

Open github.com ↗

How builders describe it

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
Prose linter for Markdown and plain text: free local countable (regex) rules plus optional TypeSafe Jev judgment rules when you confirm sending paragraphs. It flags lines; it does not rewrite your draft.
Sniff Test: a prose linter where Jev is the judge. It reads a draft one paragraph at a time and asks ten Boolean questions (is the claim hedged three times, does the closer restate the paragraph, is there a cost figure with no price beside it) and prints one line per flag with the probability. Runs…

The decision Jev makes

Assign a topic, choose a document category, or answer whether a passage supports a citation.

Where it fits

Sorting, labelling and checking documents is classic decision work: topic labels for papers, categories for files, and whether a source actually supports a claim. All 28 documents & research projects →

Related projects