Skip to main content
AutoMod scans member messages and acts on what it finds. Staff and exempt roles are never scanned. Message content is never stored — only a hash, used to correlate repeat offenders. Configure it in Settings → AutoMod. The master switch is Enable AutoMod. Until that is on, the other cards on the page have no effect.

​
Detection layers

Layers run cheapest-first. Turn each one on independently. The first layers run on every plan at no extra cost. AI classification uses your monthly AI AutoMod scans (2,000 on Pro, 20,000 on Business, none on Free).
Edits are scanned again. Forwarded messages, embeds, and stickers are included. See Scam defense for the dedicated scam view.

​
Rules for the AI

Settings → AutoMod → Rules for the AI is plain language: what counts as solicitation, off-topic, or a scam pitch here. On save, Thea compiles that into phrases members would actually type. A match is what sends the message to the AI. You can add per-channel rules on top. Where they disagree, the channel rules win — that is where “self-promo is fine here” goes. This card only matters if the AI layer is on.

​
Actions by severity

Each finding is Low, Medium, High, or Critical. You choose an action per severity, and you can override by category. Deleting and timing out need Manage Messages and Timeout Members. Without a log channel, quarantine falls back to log-only. Kick and ban are not per-severity message actions. They show up on repeat-offender escalation and in moderator commands.

​
Exemptions, domains, and the community list

  • Exemptions — roles and channels AutoMod never scans. Bots and webhooks are always exempt. Put staff roles here so quoting a scam to warn about it is not itself actioned.
  • Blocked domains — extra hosts treated as scam links. Subdomains of a blocked domain are blocked too. You can pre-fill a set of known scam domains.
  • Community scam list — Discord-AntiScam phishing domains, checked weekly. Modes: ask before each update, update automatically, or do not use. Well-known domains such as discord.com are never blocked. Needs the Heuristics layer. See Scam defense.

​
Log channel

Pick a private staff channel. Quarantined content can be exactly what you did not want members to see. Review buttons and global blacklist Allow / Ban decisions land here.

​
Channel focus

Declare what a channel is for (for example, #help is for support). Messages that clearly do not fit get a friendly warning pointing at the focus. Nothing is deleted for being off-topic. Uses the AI layer and counts against its monthly allowance.

​
Repeat offenders

After enough findings in a window, AutoMod responds more strongly than the per-severity action. The count uses AutoMod’s event log. Also available as /automod escalation. Members can check their own record with /standing.

​
Auto-slowmode

When a channel’s rate spikes far above normal, Thea can apply a short slowmode and lift it when things calm down. Needs Manage Channels. It never touches a channel a moderator already put in slowmode.

​
Appeals

Members who receive a punishment can press Request review on the DM Thea sent — including after a kick or ban. Your moderators review the appeal in the existing AutoMod queue, not Thea trust and safety (unless someone flags it). Caps: 3 appeals per member per week, 50 per server per day.

​
Test before you ship a rule

The reply is a layer-by-layer breakdown of what the live ruleset would do. Same path as enforcement.