Skip to main content

Overview

AI Moderation in the CometChat SDK helps ensure that your chat application remains safe and compliant by automatically reviewing messages for inappropriate content. This feature leverages AI to moderate messages in real-time, reducing manual intervention and improving user experience.
For a broader understanding of moderation features, configuring rules, and managing flagged messages, see the Moderation Overview.

Prerequisites

Before using AI Moderation, ensure the following:
  1. Moderation is enabled for your app in the CometChat Dashboard
  2. Moderation rules are configured under Moderation > Rules
  3. You’re using CometChat SDK version that supports moderation

How It Works

StepDescription
1. Send MessageApp sends a text, image, or video message
2. Pending StatusMessage is sent with PENDING moderation status
3. AI ProcessingModeration service analyzes the content
4. Result EventonMessageModerated event fires with final status

Supported Message Types

Moderation is triggered only for the following message types:
Message TypeModeratedNotes
Text MessagesContent analyzed for inappropriate text
Image MessagesImages scanned for unsafe content
Video MessagesVideos analyzed for prohibited content
Custom MessagesNot subject to AI moderation
Action MessagesNot subject to AI moderation

Moderation Status

The moderationStatus property returns one of the following enum values:
StatusEnum ValueDescription
PendingModerationStatusEnum.PENDINGMessage is being processed by moderation
ApprovedModerationStatusEnum.APPROVEDMessage passed moderation and is visible
DisapprovedModerationStatusEnum.DISAPPROVEDMessage violated rules and was blocked

Implementation

Step 1: Send a Message and Check Initial Status

When you send a text, image, or video message, check the initial moderation status:

Step 2: Listen for Moderation Results

Implement the MessageListener to receive moderation results in real-time:

Step 3: Handle Disapproved Messages

When a message is disapproved, handle it appropriately in your UI:

Next Steps

After implementing AI Moderation, consider adding a reporting feature to allow users to flag messages they find inappropriate. For more details, see the Flag Message documentation.