Skip to content

Jev directory

Jev Content Moderation

Content moderation with asymmetric thresholds built on Jev: three bands, approve, shadow and remove, where the README's rule is that removing good content is worse than leaving bad content up, so the removal bar sits higher than the approval bar.
Stars
0
Language
Python
License
MIT
Reading time
2 min
Published by
Community
Author
kallurayaankit
Last verified
Oct 2026

Highlights

  • Three moderation bands instead of binary approve or remove: Approve, Shadow (hidden but reversible, the author is not notified) and Remove (permanent).
  • Asymmetric thresholds: the removal bar is deliberately higher than the approval bar because removing good content is treated as the worse error.
  • The README lists the costs of false removals as user rage, bad press and lost trust, as the excerpt puts it before cutting off mid-sentence.
  • Built with Jev (TypeSafe AI), carrying a powered-by-Jev badge, with Python 3.12, MIT license and a CI workflow.
  • 0 stars, 0 forks; created and pushed 2026-10-14, found via a 'built with jev' README search.

Watch out

README reviewed 2026-10-17; the captured excerpt cuts off mid-sentence right after the rule summary, so the Jev question definitions, threshold values, setup and API key needs are not visible, and the repo has 0 stars.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

YouTube: Building a contextual brand-safety scorer on Jev from scratch.

X: A website slop detector that checks 35 tells in 243 ms

X: Breaking, golden nugget, or slop

X: A filter for reply-guy comments

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai