What it does
It combines countable rules with one judgment model.
Agent tooling
snifftest
A zero-dependency prose linter for common signs of AI-generated writing.
Bookmark: snifftest
Keep this in your collection.
Leave a noteWhat would you try with this?
: snifftest
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
You can use this approach to catch robotic or unnatural writing in project documentation, marketing drafts, or blog posts. A developer can install the tool to scan your text locally for countable issues, such as repetitive dashes, paragraphs packed with colons, or sentences that all share the exact same length.
To review subtle phrasing like circular endings or over-cautious wording, you will need a separate service access key from TypeSafe. Keep in mind that the tool never rewrites your sentences for you, and it will skip making online requests unless you specifically provide the key and confirm permission.