Student Moderations monitors student conversations with MagicSchool tools and surfaces alerts when content may warrant a closer look. It is designed to help teachers and administrators stay aware of student wellbeing and policy concerns without creating so much noise that important signals get missed.
Moderations surfaces two types of alerts: Urgent and Flagged.
🏠 The Moderations Home Page
When you navigate to My Organization → Moderation, you'll land on a home page designed to give you context before you dive into configuration.
The home page:
Explains how moderation works in plain language — click "How moderation works" for a modal that walks through each configuration option.
Surfaces at-a-glance information for your organization — active alert recipients, active categories, and flagged keywords, so you land with context rather than a blank slate.
Links directly to each configuration section: Categories, Keywords, Alerting, and Denied Topics.
📝 Note: Admins can manage all moderation settings — alert routing, category configuration, and custom keyword lists — directly in MagicSchool without contacting support.
⚙️ How Moderations Works
Two Alert Types
Two Alert Types
🔴 Urgent — content that may signal risk of serious harm to a student or others. These warrant prompt attention from a school counselor or administrator.
🟡 Flagged — content a teacher should review when they have the opportunity. These cover policy concerns or other things worth knowing but are not emergencies.
How Moderations Reduces False Alerts
How Moderations Reduces False Alerts
Personal expression vs. academic analysis — before surfacing an alert, the system considers whether a student is expressing something personal or analyzing content for an assignment.
Full conversation context — the system considers what tool the student is using, what the assignment is about, and what the conversation looked like leading up to the message.
🔴 Urgent Alerts
🔴 Urgent Alerts
Urgent alerts capture content that may indicate risk of serious harm to the student or to others.
Self-Harm: Imminent risk — a student personally expressing thoughts of self-harm, with or without a specific method. Academic discussion of self-harm in literature is not flagged unless a student shifts to expressing personal feelings.
Self-Harm: Past disclosure — a student referencing their own prior self-harm, including recovery language.
Violence: Specific threat — a student personally expressing a threat that includes a named target, method, or timeline.
Violence: Violent ideation — anger-driven expressions of violence without specific planning.
Mental and Emotional Distress — content where a student expresses hopelessness, persistent sadness, or withdrawal.
🟡 Flagged Alerts
🟡 Flagged Alerts
Flagged alerts indicate content a teacher should review when they can. These are not emergencies.
Category | What it captures |
Hate speech | Slurs or dehumanizing language targeting protected groups |
Sexual content | Explicit sexual language or attempts to use the AI to produce sexual content |
Abusive or derogatory language | Sustained derogatory language directed at a named individual |
Academic misconduct | Explicit requests for the AI to complete an assignment |
Illicit or illegal content | References to weapons (without threat context) or substance use (without accompanying distress signals) |
Platform manipulation | Attempts to override AI instructions or manipulate the system technically |
PII exposure | A student sharing personal information such as phone numbers or addresses |
Spam or nonsense | Gibberish, repeated characters, or button-mashing |
Off-topic misuse | Non-educational use of the AI without harmful content |
✅ What Moderations Does Not Flag
The system is designed to stay quiet during normal, healthy student interactions. The following are examples of content that will not generate alerts:
Routine academic use — questions for explanations, working through problems, requesting feedback.
Sensitive topics in an academic context — discussion in the context of analyzing literature, history, or current events.
Strong emotions that aren't distress — frustration about an assignment, excitement about an accomplishment.
Hyperbolic language — common expressions like "this homework is killing me."
❓ Frequently Asked Questions
What's the difference between a yellow flag and a red flag?
Yellow flags indicate content that may need attention but might not necessitate immediate action. Red flags indicate content that suggests more severe messages — such as those relating to imminent risk of harm to self or others. You are able to configure email alerts around these categories.
The AI evaluates the full context of a student's message, not just individual keywords. A student saying "I'm so tired" would not necessarily flag. A student expressing hopelessness and describing a plan would elevate to red.
When does the flag trigger — before or after the AI responds?
Every student message is reviewed for moderation. When student-provided content meets a moderation category, MagicSchool responds per your district policy — Flag or Block — and sends an alert if configured.
What does "Block Student Message" actually do?
A custom message will be shown to the student, and the thread can continue.
Can we flag AND block a student message at the same time?
No — you must select one option per category:
Flag Only: the message will only be flagged for review.
Block Student Message: a custom message drafted by your district will be shown to the student whenever this moderation category is triggered.
Can we decide which categories always trigger a red flag, regardless of severity?
No, the color of the flags are not under district control. What you can control today is which of the most severe categories trigger an alert email.
📝 Note: Start with all relevant categories checked, collect a few weeks of data, then dial back where you're seeing over-notification.
What should happen after a red flag is received?
MagicSchool surfaces the alert. Your district's established procedures for self-harm, harm to others, or other critical incidents govern what happens next.
What should we tell teachers when they receive a yellow flag notification?
Yellow flags are informational. Suggested guidance is to review the flagged conversation, use your professional judgment about whether a follow-up conversation with the student is warranted, and document if needed per your existing classroom discipline process. Yellow flags do not require escalation to administration.
How are site-level admin notifications different from org-wide notifications?
Org-wide settings send alerts to district-level recipients for all flagged content across all schools. Site-level notifications let you assign specific recipients at each school building, so the right administrator gets the right alert. Both can run simultaneously. Site-level does not replace or disable org-wide.
Can we use a distribution list email address instead of individual addresses?
Yes. You can enter a Google Group or distribution list address in the recipient field. This is the recommended approach if you want notifications managed the same way as your other safety tools and don't want to update recipient lists in multiple places.
Can rooms stay open 24/7 for student access?
Yes. If a teacher leaves a student room open, students can access it outside of school hours. Moderation monitoring is active regardless of time of day. Flagged content will generate notifications per your alert settings, including outside business hours.
Who can see Moderations alerts?
Reach out to your MagicSchool account team to confirm how alert visibility is configured for your organization.
Will every concerning message be caught?
No automated system is a substitute for human judgment, school counselor support, or established student safety protocols.
What should I do when I receive an Urgent alert?
Follow your school or district's existing protocols for student safety concerns.