Skip to content

jev-comment-triage

WordPress plugin that triages comments in the background with Jev questions on relevance, spam and abuse.

Projectbeta

Overview

Jev Comment Triage is a WordPress plugin that moderates comments using Jev through the AI Provider for Jev plugin. For every comment, Jev answers three independent questions in the context of its post: how the comment relates to the post, whether it is spam, and whether it is abusive. Plain PHP turns those answers into a decision, and only confident answers cause an automatic action.

The Jev call is asynchronous so commenting stays fast: untrusted comments are held as pending on submit with no API call, then a per-minute background drain sends each post once with up to 20 comments per request. Trusted users, pingbacks and comments WordPress already blocked keep the native decision. It never publishes beyond the site's own moderation policy, retries malformed answers up to three times, and splits rejected batches to isolate oversized comments. Answers are stored as comment meta and shown in an admin column.

What the decision model decides

TypeQuestionAnswers
ChoiceHow does this comment relate to the post?(inferred)—
Yes / noIs this comment spam?(inferred)—
Yes / noIs this comment abusive?(inferred)—

How it works

  1. Hold untrusted comments as pending on submit without an API call
  2. Background drain groups pending comments by post and sends up to 20 per Jev request
  3. PHP decision logic acts only on confident answers and never exceeds the site's moderation policy
  4. Retry malformed answers; after 3 attempts leave the comment for a human

Strengths

  • Comment submission stays fast because triage runs off the request
  • Confidence-gated actions with human fallback
  • Self-healing batching that isolates problem comments

Caveats

  • Depends on the separate AI Provider for Jev plugin and an API key
  • Requires WordPress 6.8+ and PHP 8.3+
  • No licence stated in the excerpt

Getting started

Download jev-comment-triage.zip from the latest release, upload it under Plugins > Add New Plugin, and activate it with AI Provider for Jev configured.

At a glance

Type
Project
Status
beta
Language
PHP
Runtime
WordPress plugin
Has code
yes

Use cases and integrations

How curated lists describe it

  • Async Jev-powered WordPress comment triage: background spam, scam/phishing, and toxicity moderation that keeps comment submission fast.

    hellogumbo/awesome-jev

Frequently asked questions

What does Jev decide?

How each comment relates to its post, whether it is spam and whether it is abusive.

Does it slow down commenting?

No. Comments are held as pending and judged by a background job.

Can it publish a comment WordPress would hold?

No. It never publishes past the site's own moderation policy.

Related projects

  • Chrome extension that uses your Jev key to hide high-confidence sexual and solicitation replies on X behind reversible placeholders.

    Browser extensionproductionTypeScript
  • Discord bot where Jev flags spam and scam links in real time, drives an escalating timeout ladder and profiles members.

    ProjectbetaPython
  • Message moderation that asks Jev for probabilities of spam, scam, harassment and other harms plus your own plain-English rules.

    ProjectbetaPython
  • Chrome extension and Workers API that score X posts and replies for AI writing, solicitation and paraphrase bots using Jev.

    Browser extensionbetaTypeScript
  • Chrome extension that labels every X post you scroll past with six typed Jev questions and shows a live cost counter.

    Browser extensionbetaTypeScript
  • Minimal grammY Telegram bot that asks Jev whether each group message is spam and deletes only high-confidence matches.

    ModelbetaTypeScript