Character conversation moderation

ChatFAI conversations happen between a user and an AI-voiced character built to speak in that character's style. A Beam agent reads conversation logs against the content rules a platform has approved, checking for messages that violate guidelines around harassment, self-harm, or other restricted content. It updates a moderation record once a conversation is checked and clear. Where a message matches a restricted category or sits close to a boundary the rules do not clearly cover, the agent does not remove content itself, it routes the conversation to a human moderator for a final decision.

Character profile record updates

Each ChatFAI character is defined by a profile describing their personality, background, and speaking style, which can be edited by a creator over time. A Beam agent reads profile records to check they still match the platform's content guidelines, such as required disclaimers or age ratings, and updates a compliance field once a profile passes the check. It applies only the checklist a platform has approved. Where a profile description raises a question the checklist does not cover, such as an ambiguous reference to a real person, the agent flags it for a person to review before publishing.

User report handling

Users can report a conversation or character on ChatFAI that they find inappropriate or against platform rules. A Beam agent reads incoming reports, checks the flagged conversation against the platform's stated content rules, and updates the report status once it can confirm whether the content matches an approved violation category. It does not take action against a user account itself. Reports that involve a safety concern, a request from the user for a refund, or content the rules do not clearly address are routed directly to a person on the moderation team to decide.