Guilt trips. Gaslighting. Scams disguised as texts from people you trust. Sentinel's AI catches manipulation in your messages before you fall for it.
Free during beta.
The Problem
The most dangerous texts aren't obvious scams. They're from people you trust - guilt trips disguised as concern, threats wrapped in "lol," lies that sound just plausible enough.
A second pair of eyes that can't be gaslit.
If someone in your life makes you constantly question yourself, Sentinel can help you trust your instincts.
If you or someone you know is in crisis: National DV Hotline - 1-800-799-7233
Built for Security
Sentinel isn't a generic chatbot. It's a specialist - built from the ground up to catch deception in your messages.
Custom model trained specifically for deception detection
8-step behavioral rubric from academic deception research
No sign-up, no login. Just install and go
Runs silently in your menu bar, alerts you when it matters
How It Works
Sentinel sits in your menu bar and works silently in the background. No windows to manage, no workflows to learn.
Download the app and drop it in your Applications folder. Grant Full Disk Access in System Settings. Takes about 2 minutes.
Sentinel silently evaluates every incoming message using AI built specifically for detecting manipulation.
When a threat is detected, you get an immediate notification with context on what was flagged, the specific category, and why it was suspicious.
What It Detects
Built from deception research at UC Berkeley and Oxford to catch what you'd miss.
Fake identity claims, credential theft attempts, impersonation, and social engineering tactics designed to steal information.
Guilt-tripping, gaslighting, love bombing, and other tactics used to control through exploiting emotions and attachment.
Investment scams, romance scams, advance-fee fraud, and deceptive financial requests disguised as opportunities.
False urgency, fake scarcity, ultimatums, peer pressure, and coercive language meant to force quick decisions.
False alibis, selective withholding of information, blame-shifting, and strategic distortion of facts.
Threats and intimidation hidden behind humor, sarcasm markers like "lol" and "jk," or plausible deniability.
Built on Research
Sentinel's detection engine is built on deception research from UC Berkeley and Oxford. It uses a behavioral framework that maps to how manipulation actually works in real conversations.
This isn't a toy. It's a research-backed detection engine built by Jonathan Bodea, designed to catch what humans miss in the messages they trust most.
The Numbers
Most people don't realize they're being manipulated until it's too late. Sentinel catches it in seconds.
FAQ
Sentinel scans iMessage and SMS texts only - the messages that come through Apple Messages on your Mac. It does not access WhatsApp, Instagram, Signal, or any other app. It only analyzes incoming messages from other people - it never reads messages you send.
Apple requires "Full Disk Access" for any app that reads the Messages database. It's the only way to access your texts on macOS. Sentinel only reads your messages - it does not access your files, passwords, photos, or any other data on your Mac.
Sentinel requires an internet connection to analyze messages. We're actively working on a fully offline version that runs entirely on-device.
Sentinel runs on any Mac with Apple Silicon (M1, M2, M3, M4, or later) running macOS 13 or newer.
No. Sentinel was specifically trained to distinguish sarcasm, jokes, and genuine emotional expression from actual manipulation. “You’re literally the worst lmao” won’t trigger an alert. “You’re the worst, and if you don’t do what I say, I’ll make sure everyone knows it” will.
Spam filters catch mass-sent junk. Sentinel catches targeted, personal manipulation - guilt trips from people you know, threats disguised as jokes, scams that use your name and context. These are the messages spam filters are designed to ignore.
No. Your messages are never used for training and are not stored beyond the analysis moment.
Sentinel achieves high precision with a low false positive rate. It's built on an 8-step behavioral framework developed from academic deception research.
Sentinel is free during the beta period. We’ll announce pricing before any changes.
Get Protected
Get Sentinel before everyone else. Drop your email and we'll send you the download link.