How it works

Safety that thinks ahead — without surveillance.

Every message your child sends is checked for safety in real time — before a response appears. Here is exactly what we detect, and what you as a parent will see.

SafeMentor continuously observes your child's conversations for signs of distress, danger, or harmful content. When something serious is detected, you receive an alert in your parent dashboard — and for safety-critical topics such as suicide, also a summary written for you, never your child's exact words.

Our 3-stage safety

How we protect your child

Stage 1 — Always active

Normal tutoring

SafeMentor responds warmly, age-appropriately and with pedagogical care. No intervention, no notification. Your child is accompanied — you don't need to do anything.

Stage 2 — Quiet signal

Discreet heads-up

For topics like bullying, eating disorders or concerning requests, SafeMentor detects the signal. The AI responds empathetically and encourages your child to talk to you. You receive a discreet note in your parent dashboard.

Stage 3 — Immediate

Immediate notification

For serious warning signs — self-harm, sexual assault, acute danger — SafeMentor switches immediately. Your child receives a pre-written, structured response with crisis resources. This is not generated by the AI, to ensure SafeMentor cannot hallucinate in critical situations. You are notified right away with a clear summary.

How the system works

1

Your child writes a message

Every message is immediately analysed before a response is generated.

2

Safety check in real time

Our classifier pipeline checks for safety-relevant patterns in a very short time.

3

Appropriate response

The AI responds in a way that is matched to the detected situation — supportive, guiding, or de-escalating.

4

Parent dashboard updated

If a concern is detected, you receive a note and, where relevant, a paraphrased summary. Never your child's exact words.

What you see as a parent

🟡 Heads-up alert — example

🟡

Heads-up — your child may need a conversation.

📌

What: Signs of passive suicidal thoughts

📝

Context: Your child expressed feeling like a burden and that others would be better off without them

👤

Affected: Your child as the affected person

🔴 Immediate alert — example

🔴

Immediate attention — your child may need direct support.

📌

What: Possible sexual harassment by an adult

📝

Context: Your child reported inappropriate behaviour by someone close to them

👤

Affected: Your child as the affected person

Alert levels

🔴 Immediate attentionYou are notified right away. Your child may need direct support.
🟡 Heads-upSomething worth being aware of. No immediate danger, but worth a conversation.
No alertSafeMentor responds, but no parent notification is sent.
Privacy: SafeMentor never shares your child's exact words in parent alerts — all summaries are paraphrased. Your child is always informed that their parents are notified when a safety concern is detected. No conversation data is sold or shared with third parties.

Ready to give your child a safe space?

Join our pilot phase and experience SafeMentor as one of the first families — completely free.

Get started for free