---
title: AI filter
description: A bypass-aware filter that catches what a wordlist can't - built to stop doxxing on stream.
---

The AI filter is the [word filter's](/moderation/word-filter) big sibling, built specifically to stop streamers getting doxxed on their own stream. It's a [TipPage+](/tippage-plus) feature.

## What it catches

Ban "Alex Adams" once, and the AI catches "Alicks Aderms", "Eye Licks Add Dams", and every phonetic bypass in between - plus the leetspeak, unicode lookalikes, split words, and creative spacing that a wordlist can't see. It uses a model trained by TipPage to detect doxxing attempts, so it understands *intent*, not just spelling.

It runs alongside your normal word list, not instead of it - regex catches the cheap stuff, the AI catches the clever stuff.

## Turning it on

**Filter** page, **Filter settings** panel, flip the **AI filter** toggle. Without TipPage+ you'll see an **Unlock with TipPage+** button there instead.

{/* SCREENSHOT /images/moderation/ai-filter-test.png : The "Test the filter" panel with the AI filter enabled, showing a caught bypass attempt with the "TipPage AI reasoning" line visible in the result. Uncomment the Frame below once taken. */}
{/* <Frame caption="The test panel shows the AI's reasoning for every catch.">
![The AI filter catching a bypass attempt](/images/moderation/ai-filter-test.png)
</Frame> */}

## Seeing why something was caught

- The **Test the filter** panel shows the AI's reasoning for anything it flags.
- If you've set up a [Discord webhook](/moderation/bans-and-refunds#discord-notifications), blocked-message notifications include the AI reasoning too - so you can sanity-check its calls from Discord.