When content is moderated, students see a default response message explaining why their message was blocked. Organisation administrators can customise these messages for each moderation category to better match the tone and values of their institution.
Accessing moderation settings
Navigate to Organisation in the sidebar, then click Moderation. This page is available to organisation administrators.
Choosing a moderation policy
The top section lets you choose the overall moderation sensitivity for your organisation:
Strict - Designed for younger students. Blocks swearing and content related to violence, substance use, weapons, illegal activities, sexual content, harassment, and threats. Has particular sensitivity for mental health and self-harm topics.
Moderate - Suitable for high school students. Blocks harmful content including credible threats, illegal activities, and targeted harassment. Allows academic discussion of mature topics and mild profanity within an educational context.
Lenient - For mature audiences. Allows academic discussion of sensitive topics. Only blocks credible threats, illegal activities, targeted harassment, and non-educational sexual content.
Select your preferred policy and click Save Policy.
Adding a custom response message
Below the policy selector, the Custom Responses section lets you override the default message students see when their content is moderated.
1. Click + Add custom response.
2. Select the category you want to customise. The available categories are: Profanity, Harassment, Violence, Threats, Self Harm, Mental Health, Substance Abuse, Weapons, Illegal Activity, and Sexual Content.
3. Write your custom message in the text area. The placeholder shows the default message for reference.
4. Click Save. Your custom response now appears in the list.
Editing or removing a custom response
Click on any custom response in the list to reopen the edit dialog. From here you can update the message text and save, or click Remove to delete your override and revert to the default message.
How students experience moderation
When a student sends a message that triggers moderation, they see your custom response (or the default if you have not set one) in place of the AI reply. The moderation applies across all AI interactions in your organisation, including tutor chats and the student agent.
Educators can see moderation events in the student activity view. Moderated messages are highlighted with a warning indicator showing the category and reason.