AI Moderation System

Texts and Images AI Auto Moderation System for your servers

Experience whole new texts and images Auto Moderation power by AI

---

📄 General Settings

🖊️ Log Channel

Select a channel where moderation actions (timeouts, bans, etc.) will be logged. This is helpful for transparency and recordkeeping.

• Example: #server-log

🛡️ Message Handling Options

• DM User: Notifies the user via direct message when moderation action is taken.

• Same Channel Notification: Shows moderation results in the same channel where the violation occurred.

• Delete Flagged Messages: Automatically removes messages that violate moderation rules.

🔍 Ignored Elements

• Channels: Add channels to be excluded from moderation.

• Users: List user IDs that should be excluded (Developer Mode needed to get IDs).

• Roles: Define roles that will bypass moderation.

---

🔎 Content Filters

🔗 URL Filtering

• Mode: You can choose to enable or disable URL filtering.

• Web Risk Detection: Uses Google Web Risk API to identify harmful URLs (e.g., phishing, malware).

🔒 Content Moderation Thresholds

Each category can be toggled ON/OFF and configured with sensitivity:

• Sexual Content

• Sexual Content (Minors)

• Harassment

• Threatening Harassment

• Hate Speech

• Threatening Hate Speech

Sensitivity range: 0% (Less Sensitive) to 100% (More Sensitive).

---

🔨 Actions

Enable automated disciplinary actions based on user warnings:

Placeholders Available

• {username}: User’s name

• {user_id}: User’s ID

• {moderator}: Moderator’s name

• {duration}: Timeout/ban length

• {reason}: Reason for action

• {now}: Current time/date

⏱ Timeout

• Warnings Before: 2

• Duration: 30 minutes

• Enabled: ✅

🚫 Temporary Ban

• Warnings Before: 3

• Duration: 1 day

• Enabled: ✅

❌ Permanent Ban

• Warnings Before: 4

• Warning: Cannot be reversed automatically.

• Enabled: ✅

---

🔔 Events

Each moderation action is logged with:

• ID: Unique event ID

• Action: (e.g., Warning, Timeout)

• User: Targeted user

• Moderator: Who triggered the action (e.g., AI Moderation)

• Timestamp: When the action occurred

• Details: View breakdown of moderation reasoning

---

🔧 Saving & Enabling

• Use the Save Settings button to apply all configurations.

• Toggle the Enabled switch to activate or deactivate moderation enforcement.

---

🛡️ Required Permissions

The bot needs specific permissions to operate the moderation system. If any are missing, the module may not function.

• Administration (Optional but Recommended): Granting this overrides the need to manually assign the individual permissions below.

If Administration is not enabled, you must enable the following server-wide permissions:

• Kick Members (Required)

• Ban Members (Required)

• Moderate Members (Required)

• Manage Messages (Required)

You can use command /diagnose to check which feature/module is eligible to use in your server

NYX cannot moderate members who have a higher or equal role position. Make sure the bot’s highest role is placed above the roles of any members you want it to moderate.

---

Defaulted Ignored Moderation

this follow list are defaulted ignored moderation, they are not able to modified by server admin

• Users with administration permission

• Bot doesn't have required permission

---

Self-Harm Build-In Detector

We priorities user mental state and maintain safety to all user make sure everyone is safe! When we detect self-harm messages even texts or images we will send you this embed to the user DMs