Playable demos & bots
jev-content-mod uses Jev's harm, category and clarity judgments to feed code rules that approve a post, hide it for review or remove it.
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Jev scores harm, picks a category and answers clarity questions. Code then applies the approve, shadow or remove policy. The example needs 0.85 clarity for removal but 0.5 for approval. The author set those values by hand and reports no evaluation; they are not universal moderation defaults.
Unclear posts that look harmful stay hidden in the review band rather than being deleted automatically. That distinction matters when a mistaken deletion is costly. Choose cutoffs for your community and test cases with known outcomes. The sample numbers express the author's tradeoff, not a measured policy that fits everyone.