How the AI works
How SafeCircle detects risk in your child's chats end to end, in plain language, and what stays on the phone.
SafeCircle uses a small AI model that runs on your child's Android phone. It reads the text of recent chat messages in a few supported apps, decides whether they show one of seven kinds of online risk, and only if the result is serious enough does it send you an alert. The message text itself is never sent to SafeCircle.
An assistant, not a verdict
The model can be wrong in both directions: it can flag harmless chats and it can miss real ones. Treat an alert as a prompt to start a conversation, not as proof. See Limitations.
What happens, step by step
The child app notices new text
The SafeCircle child app uses Android's Accessibility Service to read the text that is visible on screen in the supported messaging apps. It keeps the most recent snippets for each app in memory only.
The on-device model reads the conversation
The snippets are passed to the model stored on the phone. The model answers with a risk level, the categories it sees, and a confidence value. No network connection is needed for this step.
Only serious results become alerts
If the result is medium or high, the app builds an alert. Anything weaker is discarded on the phone. The app also waits between checks for the same app, so you do not get a flood of alerts.
You are notified
The alert (risk level, categories, confidence, a short note and the source app) is sent to SafeCircle and shown in your dashboard, with a push notification. See Understanding alerts.
What stays on the device
| Stays on the phone | Sent to SafeCircle |
|---|---|
| The text of the messages | Risk level (medium or high) |
| The model's working, including the recent-messages buffer | Risk categories |
| The model file itself, once downloaded | Confidence value |
| A short note and the app name |
Read Privacy for the full picture, including what the server stores.
Two ways the phone can analyse
Not every phone can run the full model, so the child app has three tiers. A fresh install starts on the keyword scan, which needs no download. You can switch to an AI model in the child app under Settings → Advanced → AI Model tier, which marks the tier recommended for that phone based on its memory, free storage and Android version:
| Tier | What it does |
|---|---|
| Full model | The larger on-device model (about 1.2 GB download) |
| Lite model | A smaller, quantised version (well under 1 GB) for modest phones |
| Keyword scan | A basic word-matching fallback for phones that cannot run either model. It needs no model download and is much less accurate |
Details are in On-device runtime.
What the AI looks for
Seven categories: grooming, bullying, sexual content, isolation, personal information, platform migration and threats. See Risk categories for what each one means.
Where the model comes from
The model family is called Horizon. It is trained on synthetic (AI-generated) conversations, not on real children's messages. See Horizon models for how it is trained and evaluated.
Risk categories
The seven categories, risk levels, confidence and the reasoning note.
Privacy
What is analysed, what never leaves the device, and what the server sees.
On-device runtime
Model tiers, download, supported apps, cooldown and performance.
Limitations
Accuracy caveats and known gaps, from the evidence we have.
Set up the child app
Install the child app and choose a detection tier.
Developers
Architecture and APIs.