CensorX is an AI-powered moderation bot designed to automatically detect and handle explicit content.
CensorX is a robust, AI-driven moderation and content filtering solution designed to ensure your community remains safe.
Key Features & Functionality Real-Time Content Filtering CensorX automatically processes message content against a sophisticated classification model to assign a confidence score for explicit material. This happens instantly, minimizing user exposure to harmful text.
Dual-Level Moderation Action The bot handles flagged content using two distinct tiers based on the confidence score:
High-Confidence Deletion: Messages exceeding a high threshold are automatically deleted from the channel immediately, and the author is notified with an explanatory, ephemeral warning.
Low-Confidence Flagging: Messages falling within a lower threshold are flagged for administrator review. The original message is preserved, and a detailed alert (with content and score) is sent to a private admin channel with actionable buttons for review.
CensorX ensures efficient, consistent moderation, allowing your human moderators to focus on complex conflicts rather than fighting spam and explicit content.
