Mathspace Personal Tutor

Things to Know When Using Milo Chat

At Mathspace, our mission is to be the right help at the right time for every student.

Milo Chat is our latest offering to advance that mission. It uses Generative AI technology to help answer specific questions that students have when practicing in Mathspace, providing just-in-time, custom support to every individual.

 

Here are some important things to know to make the most of Milo Chat.

Availability and Reliability

• Milo Chat is available on most problems from Grade 3 to Grade 10 in Australia and Grade 3 through Algebra 2 in the United States.

• Generative AI is still developing the ability to support some Mathspace problems that include images, tables, graphs and other interactive inputs. Where we have identified AI is not reliable for providing students with accurate help, Milo Chat will be unavailable. In such cases, you can still ask Milo for hints and video help but just won’t be able to chat.

• Despite our continued efforts to make Milo Chat as helpful and as accurate as possible, sometimes it may get things wrong or introduce biased responses. This is a limitation of Generative AI so always check with your teacher if you need more help.

Teacher Visibility and Control

Appropriate use and Chat moderation

Milo Chat is designed to be a safe and positive learning space. To protect students, we’ve introduced a Chat Moderation System that automatically detects and responds to unsafe or inappropriate messages. 

Every message sent to Milo is automatically reviewed by a moderation system that classifies it by risk level and category. The system is designed to handle most cases automatically, helping students learn how to interact appropriately over time. When something serious happens, teachers are notified straight away so they can provide support where it’s needed.

Here’s how it works:

• Low Risk - These are minor issues like rude language or light insults. When a student sends a low risk message, the Mathspace robot steps in with a gentle warning, reminding students to stay respectful, allowing Milo to remain the helpful, safe tutor students know.
  
  
• Medium Risk - These include requests for instructions that facilitate violence or illegal harm, sexual content involving minors, or other unsafe topics that don’t pose an immediate threat to the student's safety. On receiving such messages, the Mathspace Robot steps in with a warning, along with which chat access is temporarily blocked (1 hour the first time, and 12 hours the second), giving students time to reflect before continuing. If the behavior continues a third time, a permanent ban is applied automatically.
  
  
• High Risk - When a student sends a message that involves serious and immediate safety concerns (for example, credible threats to public safety or clear self-harm intent), the Mathspace Robot immediately ends the chat and Milo provides a message encouraging them to reach out to a trusted adult or a helpline. This ensures that serious situations are handled with care, not judgment, and that the right kind of help reaches the student as quickly as possible. A high risk message results in an immediate and permanent ban.

We’ve also built in safeguards to keep learning on track. Milo is trained to gently steer conversations back to the problem at hand and if a chat drifts too far off-topic, the Robot ends it automatically. This maintains focus and reinforces Milo’s purpose as a learning tool, not a social chatbot.

Privacy and Data Usage