Moderation

ChatBotKit includes built-in content moderation that helps you maintain the safety of your bot-user interactions. When enabled, all incoming and outgoing messages are automatically scanned for abusive or harmful content.

Content moderation is available on the Pro plan.

Features

1. Content Scanning: All incoming and outgoing messages are checked for abusive and harmful content.
2. Automatic Refusal: If a message is flagged, the bot will not process it and will send a refusal response instead, preventing harmful content from propagating.

Enabling Content Moderation

To enable content moderation for a bot:

1. Open the bot's settings page and scroll to Advanced Settings.
2. Toggle the Moderation switch to ON.
3. Save your changes.

Once enabled, every message - both from users and from the bot - will be checked before being processed.

How it Works

• When a user sends a message, ChatBotKit checks the content before the bot processes it.
• If the message is flagged as abusive or harmful, the bot will not respond to it and will send a default refusal message instead.
• Flagged conversations appear in your Conversations dashboard, where you can filter by flagged status to review them.
• You will receive an email notification when content abuse is detected in one of your conversations.