> ## Documentation Index
> Fetch the complete documentation index at: https://docs.celestia.rest/llms.txt
> Use this file to discover all available pages before exploring further.

# Seraphine

> AI-powered moderation bot that automatically detects and reports rule violations in your server

## Overview

Seraphine is an AI-powered moderation bot that works alongside Celestia to automatically monitor messages in your server. It uses large language models to detect clear rule violations in real time and reports them directly to Celestia for action. Seraphine is lenient by design — it only flags obvious violations and ignores casual language, banter, and edgy humor that is normal in Discord communities.

Seraphine requires a one-time unlock purchased through Celestia and can only operate in servers where Celestia is present.

***

## Requirements

* **Celestia** must be present in your server
* The user who adds Seraphine must have the **Seraphine unlock** purchased through Celestia's store
* AI moderation must be **enabled** per server using `/seraphine enable`

<Warning>
  If Celestia is removed from your server, Seraphine will automatically leave as well.
</Warning>

***

## Commands

<AccordionGroup>
  <Accordion title="seraphine enable" icon="circle-check">
    Enables AI moderation for your server. Once enabled, Seraphine will begin scanning messages and reporting violations to Celestia.

    <CodeGroup>
      ```bash Syntax theme={null}
      /seraphine enable
      ```

      ```bash Example theme={null}
      /seraphine enable
      ```
    </CodeGroup>

    **Permissions:** Server Owner only
  </Accordion>

  <Accordion title="seraphine disable" icon="circle-xmark">
    Disables AI moderation for your server. Seraphine will stop scanning messages entirely until re-enabled.

    <CodeGroup>
      ```bash Syntax theme={null}
      /seraphine disable
      ```

      ```bash Example theme={null}
      /seraphine disable
      ```
    </CodeGroup>

    **Permissions:** Server Owner only
  </Accordion>

  <Accordion title="seraphine rules set" icon="pen-to-square">
    Opens a modal where you can write custom rules for your server. Seraphine will use these rules instead of the default ones when analyzing messages.

    <CodeGroup>
      ```bash Syntax theme={null}
      /seraphine rules set
      ```

      ```bash Example theme={null}
      /seraphine rules set
      ```
    </CodeGroup>

    **Permissions:** Server Owner only

    <Tip>
      Write rules in a numbered format for best results. Keep each rule short and specific. Vague rules like "be respectful" may produce inconsistent results.
    </Tip>
  </Accordion>

  <Accordion title="seraphine rules view" icon="eye">
    Displays the current rules Seraphine is using for your server. Shows custom rules if set, otherwise shows the default rules.

    <CodeGroup>
      ```bash Syntax theme={null}
      /seraphine rules view
      ```

      ```bash Example theme={null}
      /seraphine rules view
      ```
    </CodeGroup>

    **Permissions:** Server Owner only
  </Accordion>

  <Accordion title="seraphine rules reset" icon="arrow-rotate-left">
    Clears your custom rules and resets Seraphine back to the default rule set.

    <CodeGroup>
      ```bash Syntax theme={null}
      /seraphine rules reset
      ```

      ```bash Example theme={null}
      /seraphine rules reset
      ```
    </CodeGroup>

    **Permissions:** Server Owner only
  </Accordion>

  <Accordion title="whitelist add" icon="shield-check">
    Whitelist a user, role, or channel from AI moderation. Whitelisted targets are completely ignored by Seraphine.

    <CodeGroup>
      ```bash Syntax theme={null}
      /whitelist add [user] [role] [channel]
      ```

      ```bash Example theme={null}
      /whitelist add user:@moderator
      /whitelist add role:@Staff
      /whitelist add channel:#staff-chat
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>

  <Accordion title="whitelist remove" icon="shield-xmark">
    Remove a user, role, or channel from the whitelist.

    <CodeGroup>
      ```bash Syntax theme={null}
      /whitelist remove [user] [role] [channel]
      ```

      ```bash Example theme={null}
      /whitelist remove user:@moderator
      /whitelist remove role:@Staff
      /whitelist remove channel:#staff-chat
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>

  <Accordion title="whitelist list" icon="list">
    View all currently whitelisted users, roles, and channels for your server.

    <CodeGroup>
      ```bash Syntax theme={null}
      /whitelist list
      ```

      ```bash Example theme={null}
      /whitelist list
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>

  <Accordion title="warns list" icon="list">
    View all AI warns for a user in your server, including the rule broken, severity, date, and the message content that triggered the violation.

    <CodeGroup>
      ```bash Syntax theme={null}
      /warns list <user>
      ```

      ```bash Example theme={null}
      /warns list user:@someone
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>

  <Accordion title="warns remove" icon="minus">
    Remove a specific warn from a user by its number. Use `/warns list` first to find the warn number.

    <CodeGroup>
      ```bash Syntax theme={null}
      /warns remove <user> <index>
      ```

      ```bash Example theme={null}
      /warns remove user:@someone index:2
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>

  <Accordion title="warns clear" icon="trash">
    Clear all AI warns from a user in your server.

    <CodeGroup>
      ```bash Syntax theme={null}
      /warns clear <user>
      ```

      ```bash Example theme={null}
      /warns clear user:@someone
      ```
    </CodeGroup>

    **Permissions:** Manage Server
  </Accordion>
</AccordionGroup>

***

## Default Rules

If no custom rules are set, Seraphine uses the following default rules:

1. No racist remarks, slurs, or hate speech targeting someone's race, ethnicity, or nationality
2. No NSFW content, sexual discussions, or explicit material in non-designated channels
3. No targeted harassment or threats against members

***

## What Seraphine Flags

Seraphine is intentionally lenient. It is built for obvious, clear violations only.

<CardGroup cols={2}>
  <Card title="Flagged" icon="flag">
    * Actual racial slurs or racist remarks directed at a person or group
    * Explicitly sexual messages or graphic descriptions
    * Direct threats or serious harassment
  </Card>

  <Card title="Not Flagged" icon="check">
    * General swearing or cursing
    * Friendly trash talk or banter
    * Dark humor not targeting a race or being explicitly sexual
    * Mild insults or name calling between friends
    * Casual phrases like "i'll kill you" or "you're stupid"
    * Any ambiguous message
  </Card>
</CardGroup>

<Note>
  If Seraphine is unsure whether a message is a violation, it will always return clean. False negatives are preferred over false positives.
</Note>

***

## Violation Severity

When a violation is detected, Seraphine assigns a severity level and reports it to Celestia:

| Severity | Description                                     |
| -------- | ----------------------------------------------- |
| Low      | Borderline case, mild violation                 |
| Medium   | Clear and obvious violation                     |
| High     | Severe slur, explicit content, or direct threat |

***

## How It Works

1. A message is sent in your server
2. Seraphine checks if AI moderation is enabled for the guild — if disabled, nothing happens
3. Checks if the user, role, or channel is whitelisted — if so, skips the message
4. Sends the message to an AI model along with your server's rules
5. If a violation is detected, reports it to Celestia with the user, channel, message content, rule broken, and severity
6. Celestia handles the warning and any further action

***

## Custom Rules

You can replace the default rules with rules specific to your server using `/seraphine rules set`. This opens a text modal where you can write up to 1000 characters of rules.

<Tip>
  Number your rules and keep them specific. Example:

  ```
  1. No promoting or discussing illegal activities
  2. No hate speech of any kind
  3. No sharing personal information of other members
  ```
</Tip>

You can view them anytime with `/seraphine rules view` and reset them with `/seraphine rules reset`.

***

## Whitelist

The whitelist allows you to exclude specific users, roles, or channels from AI moderation entirely. This is useful for staff channels, trusted roles, or specific users who should not be scanned.

<Warning>
  Always whitelist your moderation staff and trusted roles to avoid false reports.
</Warning>

***

## Warns

Every violation detected by Seraphine is automatically saved as an AI warn against the user in your server. Warns are stored per user per server and include a full history of each incident.

Each warn entry contains:

* The rule that was violated
* The severity level
* The message content that triggered the violation
* The channel and message it came from
* The timestamp

You can view, remove, or clear warns at any time using the `/warns` commands. Warns are independent per server — a user warned in one server is not affected in another.

***

## Logging

When Seraphine detects a violation, it reports it to Celestia which handles the action in the same server. No separate log channel configuration is required.