> ## Documentation Index > Fetch the complete documentation index at: https://docs.theabot.com/llms.txt > Use this file to discover all available pages before exploring further. # AutoMod > Layered detection — Discord rules, heuristics, moderation screen, images, names, and optional AI — with per-severity actions, quarantine, and appeals. 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. | Layer | What it catches | Plan | | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | | **Discord's built-in AutoMod** | The rules you already set in Discord. Needs **Manage Server**. | All | | **Heuristics** | Floods, mention spam, invites, scam links (including bare hostnames and lookalike Unicode). Decodes QR codes on up to two Discord CDN images per message. | All | | **Moderation screen** | Harassment, hate, sexual content, violence | All | | **Image scanning** | NSFW, gore, self-harm in attachments. Needs the moderation screen on. | All | | **Name screening** | Suspicious usernames and nicknames at join or rename, including staff impersonation | All | | **AI classification** | Borderline messages judged against the rules you write | Pro and Business (metered) | 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](/moderation/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. | Action | What it does | | ------------------------------------- | ------------------------------------------------------------------------------- | | **Log only** | Record in the log channel | | **Warn in channel, keep the message** | Public warn, message stays | | **Quarantine for review** | Remove the message and repost it in the log channel with **Approve** / **Undo** | | **Delete and DM the member** | Delete plus a DM | | **Delete and warn in channel** | Delete plus a public warn | | **Delete and time out** | 10 minutes, 1 hour, 24 hours, 7 days, or a duration that scales with severity | 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](#repeat-offenders) and in [moderator commands](/moderation/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](/moderation/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](/moderation/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`](/moderation/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 ``` /automod test message:free nitro click this ``` The reply is a layer-by-layer breakdown of what the live ruleset would do. Same path as enforcement. ## Related * [Scam defense](/moderation/scam-defense) * [Global blacklist](/moderation/global-blacklist) * [Raid protection](/moderation/raid-protection) * [Moderator commands](/moderation/moderator-commands)