# Zero Trust moderation ### What is "Zero Trust moderation" “Zero Trust Moderation” is a modern and reliable solution designed to protect your chats from spam. It leverages the latest AI models along with internal triggers to detect and instantly remove spam messages and ban offending users. ### How it works “Zero Trust Moderation” continuously monitors messages from new users. If someone sends a message that the AI model classifies into one or more of the following categories, the message will be removed, and the sender will be banned within seconds. #### Tracking categories * Violence * Self-harm * Scams * Spam * Harassment * Hate speech These categories are currently fixed, but we plan to make them customizable in a future release. ### Limitations and known problems Due to the possibility of false positives, we recommend turning off “Zero Trust Moderation” for the following types of chats: * Buying and selling goods or services * Chats where one or more of the above topics are considered acceptable ### Why "Zero Trust moderation" 1. No manual setup required — works out of the box and is enabled by default for the eligible chats registered in Fullyst after 2024-04-07 2. Fast and reliable response to spam messages with the reason of the actions 3. Reduced spam by 96% in most chats 4. Safe-by-default approach --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.fullyst.com/features/zero-trust-moderation.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.