AI moderation

Kovu extraOff by default

An AI toxicity filter for automod: Llama Guard checks messages for hate, threats and worse.

Set it up

Open the dashboard and pick your server. Sign in with Discord if you haven’t.
Find AI moderation in the sidebar (or press ⌘K and type its name) and turn it on.
Go through the settings below. Simple mode shows the essentials; switch to Advanced for the rest.
Changes apply in your server within a few seconds of saving.

What you’ll find on the AI moderation page of the dashboard. Settings marked Advanced only show in Advanced mode.

Categories: ListWhat Kovu acts on. S1: Violent crimes, S2: Non-violent crimes, S3: Sex-related crimes, S4: Child sexual exploitation, S5: Defamation, S6: Specialized advice, S7: Privacy, S8: Intellectual property, S9: Indiscriminate weapons, S10: Hate, S11: Suicide and self-harm, S12: Sexual content, S13: Elections, S14: Code interpreter abuse.
Log channel: Channel

Delete flagged messages: On/off
Warn in the channel: On/offA short notice that deletes itself.
Give a formal warningAdvanced: On/offCreates a warning case, which counts toward autopunish.
Flags before punishment: NumberFlagged messages from one member within the window.
Within: Duration
Punishment: Choice
Mute lengthAdvanced: Duration0 uses the default from Moderation settings.

Ignored channels: Channels
Ignored roles: Roles
Only these channelsAdvanced: ChannelsLeave empty to check every channel.
Only members who joined withinAdvanced: DurationLeave at 0 to check everyone.

Keeps AI checks fast and within fair use.

Messages checked per day: NumberAnything past this in 24 hours goes unchecked by AI (other filters still run).
Shortest message checked: NumberIn characters, not counting links, mentions and emoji.
Check each member at most every: Duration
Share of messages checked (%): Number

Ready to try AI moderation?