Flint Moderation at a Glance
Flint’s moderation system is designed to keep students safe by automatically monitoring and flagging messages that may be inappropriate or harmful. When a student sends a message that matches one of Flint’s moderation categories, the system immediately notifies the appropriate staff and logs the event for review. This ensures that every flagged message is seen by the right people, and that no grade level or category is left unmonitored.
Key Points
There are two layers to moderation - the school level and the class level. A moderator at the school level is flagged for the whole space while moderators at the class level on see things from their particular class.
Admins can uncheck email notifications for all categories - with the exception of self-harm content. This category can never be turned off.
Moderators receive real-time email alerts and can review flagged messages in Flint’s analytics dashboard.
Moderation can be customized by grade level and content category.
📌 Tip: Every grade level in a workspace must have at least one moderator assigned. A moderator cannot be removed if doing so would leave any grade level without coverage.
Flint's moderation categories
Flint's moderation categories
Flint's categorization of flagged messages is based on OpenAI's content moderation rules. The different types of flagged messages are described in the table below.
Self-harm categories are mandatory — moderators must always receive notifications for self-harm, self-harm/intent, and self-harm/instructions. This cannot be disabled.
Category | Description |
Harassment | Content that expresses, incites, or promotes harassing language towards any target |
Harassment/Threatening | Harassment content that also includes violence or serious harm towards any target. |
Hate | Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment. |
Hate/Threatening | Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. |
Illicit | Content that gives advice or instruction on how to commit illicit acts. A phrase like "how to shoplift" would fit this category. |
Illicit/Violent | The same types of content flagged by the "illicit" category, but also includes references to violence or procuring a weapon. |
Self-harm | Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. |
Self-harm/Intent | Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders. |
Self-harm/Instructions | Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts. |
Sexual | Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness). |
Sexual/Minors | Sexual content that includes an individual who is under 18 years old. |
Violence | Content that depicts death, violence, or physical injury. |
Violence/Graphic | Content that depicts death, violence, or physical injury in graphic detail. |
Relationship Building | sonal problems, seeking life advice, or expressing emotional attachment unrelated to academics. |
How Flint’s Moderation System Works
Flint uses AI to automatically scan student messages for content that matches specific moderation categories, such as harassment, hate speech, self-harm, and more. When a message is flagged:
An email notification is sent to the assigned moderator(s)
An email is sent to the school moderator. If the message takes place in a class, the owner of the class will also receive a message.
The flagged message appears in the analytics dashboard at both the school and class level.
Moderators can review the flagged message and take appropriate action.
This process ensures that concerning messages are quickly brought to the attention of the right staff members, helping schools respond promptly and appropriately.
Who can be a moderator
Moderators are designated faculty/staff members who are responsible for reviewing flagged content and receive notifications. There are two types of Moderators in Flint:
School Moderators:
These can be administrators, teachers, guidance counselors, or other student support staff. School moderators can be assigned to all categories and grade levels, or can be assigned to particular categories/grades to ensure the notifications are going to the correct individual.
Class moderators:
Must be the owner or have access to edit a class. Class moderators only receive notifications for flagged messages within their own workspace.
By default, the creator of a school is automatically set as the school moderator, and the creator of a class is automatically the class moderator. You can add as many moderators as needed, but you cannot remove all moderators from any grade level.
How to set up a moderator
School level
School level
Click "School Settings" from the left sidebar
Click "Moderation" from the left sidebar
Click on one of the moderators in your workspace
Click on the dropdown menu under "Moderation categories for email notifications", check or uncheck the categories you want to enable or disable for this class.
Click "Save" to save your changes
Class Level - adjusting email notifications
Class Level - adjusting email notifications
Click the class you want to configure
Click "Settings"
Under "Moderation categories for email notifications", check or uncheck the categories you want to enable or disable for this class
Click "Save" to save your changes
Class Level - adding moderator
Class Level - adding moderator
Click the class you want to configure
Click "People"
Under the access column, click the drop-down for "Can participate" and change to "Can edit"
If the person is not ther, click "Add people" and add their email.
Click the empty shield on the right to make it filled in.
What are moderation guidelines
Moderation guidelines are custom instructions that tell Flint’s AI assistant (Sparky) how to respond when a student sends an inappropriate or concerning message. These guidelines help ensure that students receive a supportive and appropriate response in real time.
Setting moderation guidelines
Setting moderation guidelines
Click "School Settings" from the left sidebar
Click "Moderation" from the left sidebar
Click the Moderation guidelines text box and enter instructions for how Sparky should respond to inappropriate messages
Click "Save" to save your changes
Best practices
Best practices
When writing moderation guidelines, consider:
Provide clear escalation procedures: Tell students who to contact if they need help.
Include contact information for support resources: Add links to counseling services, helplines, or school support staff.
Specify tone and approach for different scenarios: Guide Sparky on how to respond compassionately while redirecting the conversation.
Reference your student handbook: Direct students to specific sections of your school's policies when appropriate
Example guideline: "When a student uses inappropriate language, respond with empathy and redirect them to Section II Article III of our student handbook. If a student expresses distress, provide the school counseling office contact ([email protected]) and encourage them to reach out for support."
Viewing flagged messages
School level
School level
Navigate to the workspace homepage
Click on "Analytics"
Select "Alignment"
Scroll down to the section titled "Inappropriate messages"
Click on a flagged message to access the chat where the message was flagged.
Class Level
Class Level
Click the class you want to view
Click on "View analytics"
Scroll down to the section titled "Inappropriate messages"
Click on a flagged message to access the chat where the message was flagged.
📌 Tip: Both schooland class moderators receive notifications based on the moderation categories that are selected for them.
See the Setting moderation categories section to adjust what categories moderators are notified about.
Email notifications
Email notifications
When a flagged message is detected, Flint immediately sends an email notification to the appropriate moderators:
The email comes from [email protected] with the subject line: "Review Required: Message Flagged for [moderation category]"
The email includes:
The student's name
The moderation category triggered
A link to view the full chat session
Moderators can access any chat for students within their assigned grade-level coverage directly from the email link. This allows moderators to review the full context and determine appropriate follow-up.