Jev in production › Writing and content scoring

riff

riff prose linter uses Jev for semantic rule checks, returning calibrated probabilities per finding; an example run costs about $0.0004 (Scale Venture Partners).

Open on GitHub ↗

$0.0004measured, as published by the source
Use
Writing and content scoring
Industry
Productivity
Form
Open-source tool
Stage
Beta
Listed
2026-09-30
Found via
github
Repository
scale-venture-partners/riff
Stars
8
Forks
2
Last push
2026-11-11
Language
Python
License
MIT

The README opens with

A small, fast prose linter. It reads a document, flags the writing tells and clarity problems it finds, and reports them with ruff-style rule codes you can select, ignore, and configure. Static rules are pure Python and run in milliseconds. The semantic rules are yes/no questions for TypeSafe's Jev, a decision model that returns a calibrated probability per judgment instead of generated text; every rule asked about the same paragraph (or section, or document) shares one call.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for writing and content scoring