# Moderation

> Built-in and AI spam detection close junk automatically. Pattern rules catch the rest. Your rulebook decides what’s rejected, what’s escalated, and what’s left to AI judgment.

Canonical: https://www.getsift.ai/platform/moderation/

## Spam closed on arrival. Policy calls escalated to people.

Built-in and AI spam detection close junk automatically. Pattern rules catch the rest. Your rulebook decides what’s rejected, what’s escalated, and what’s left to AI judgment.

[Read the docs](https://docs.getsift.ai/docs/configure/content-management)

Spam layers **Stock, AI, pattern**

Rulebook modes **3**

Confidence **Adjustable threshold**

## What it does

### AI spam detection

Set spam and safe indicators, keywords, and a confidence threshold. Test it with the built-in spam tester.

### Pattern rules

Catch known spam with substring or regex patterns.

### Rulebook (on request)

Write policies as Hard reject, Always escalate, or AI judgment. We turn it on for your organization.

### Blocked users

Blocked users can’t open new conversations.

### Impersonator detection

A built-in user rule flags likely impersonators, on by default.

### Moderation analytics

Spam caught, average confidence, top spammers, and top channels.

## Layers of spam defense

Built-in detection catches the obvious. AI spam detection reads intent with your indicators and threshold. Pattern rules catch known strings. Test any message before you save.

## Policy with a person in the loop

Write your rulebook as Hard reject, Always escalate, or AI judgment. Blocked users can’t open new conversations, and impersonator detection runs by default.

## Where it moderates

[All integrations →](https://www.getsift.ai/integrations/)

[Discord](https://www.getsift.ai/integrations/discord/) [YouTube](https://www.getsift.ai/integrations/youtube/) [Discourse](https://www.getsift.ai/integrations/discourse/) [Telegram](https://www.getsift.ai/integrations/telegram/) [Instagram](https://www.getsift.ai/integrations/instagram/) [Facebook](https://www.getsift.ai/integrations/facebook/)

## Questions

### Is the rulebook on for everyone?

The rulebook is available when moderation policy is enabled for your organization. Talk to us to turn it on.

### Can I test spam rules first?

Yes. The spam tester shows how a message would be scored before you save.

## More of the platform

[**AI triage** Score, summarize, tag, and filter every message.](https://www.getsift.ai/platform/triage/) [**AI replies** Drafts in your voice, grounded in your knowledge.](https://www.getsift.ai/platform/ai-replies/) [**Knowledge base** The facts your agents answer from.](https://www.getsift.ai/platform/knowledge-base/) [**SiftGPT** Ask your data, get answers with sources.](https://www.getsift.ai/platform/siftgpt/) [**Inbox** Every channel in one keyboard-first inbox.](https://www.getsift.ai/platform/inbox/) [**Workflows** Rules and goals that route work for you.](https://www.getsift.ai/platform/workflows/) [**Analytics** Topics, sentiment, SLAs, and custom dashboards.](https://www.getsift.ai/platform/analytics/) [**Listening** Brand mentions you weren’t tagged in.](https://www.getsift.ai/platform/listening/) [**People** Advocates, detractors, and who’s going quiet.](https://www.getsift.ai/platform/people/) [**Quality & CSAT** QA agents, reviews, and customer scores.](https://www.getsift.ai/platform/quality/) [**Security & admin** Roles, audit log, and agent access controls.](https://www.getsift.ai/platform/security/)

## Close spam before your team sees it.

We’ll test your rules against real messages from your community.