SentriesAI
← SentriesAIROADMAP
ACT I · BUILT

Everything we've
built.

Eight chapters. Two years of iteration. From a rough first detection layer to a platform that protects millions.

SCROLL TO BEGIN
Q3 2025Foundation

First light.

The detection pipeline takes shape.

We started with a simple question: can an AI analyze a suspicious URL the way a security analyst would? The first version of our conviction engine was born — a handful of independent layers that evaluated URLs, domains, and content. It was rough, but the architecture that would define everything was already there: structural signals over content signals, evidence over points.

Layer 1activeLayer 2activeLayer 3activeLayer 4activeLayer 5activeLayer 6activeLayer 7activeLayer 8active
Q4 2025Threat Intelligence

726,000 known threats.

Three feeds. One source of truth.

We integrated URLhaus, OpenPhish, and Phishing.Database into a unified lookup layer. 726,000+ confirmed phishing URLs, 430,000+ domain-level entries, refreshed on every container restart. Combined with Tranco's top 500 trusted domains, we had both the blocklist and the safelist — the foundation for the trust engine that came next.

726K+
URLs
URLHAUS
430K+
Domains
PHISHING.DB
300+
Active
OPENPHISH
500
Trusted
TRANCO
Q4 2025Visual Brand Match

We taught it to see.

66 brands. Fingerprinted. Matched.

Phishing sites don't just use similar text — they clone the visual identity. We pre-crawled 66 major brands (banks, government, social media, couriers) and stored their fingerprints: favicon perceptual hash, dominant color palette, page structure. Now, when a page looks like BRD bank but lives on brd-secure-verify.cc, we catch it with structural confidence.

BRD
ING
BT
REV
PP
AMZ
FB
GG
AP
MS
NF
SP
DHL
FX
GOV
BNR
MATCH FOUND
brd-secure.cc → BRD 97%
Q1 2026Browser Extension

Protection where you browse.

Chrome MV3. Zero friction.

The browser extension became our reach multiplier. Real-time page scanning, popup with instant verdict, one-click deep scan. Auto-login via JWT token exchange means if you're signed into the web app, the extension just works. Safari and Firefox builds share the same codebase — one extension, three browsers.

SentriesAI
SAFE
example.com
Q1 2026Machine Learning

The model that learns.

XGBoost. 44 features. F1 0.904.

We moved beyond rules. Our XGBoost 3-class model (safe/suspicious/phishing) trained on 10,000+ real scans uses 44 features: URL structure, domain age, SPF/DMARC authentication, content signals, and TLD risk. Every Sunday at 03:00 UTC, it retrains automatically on fresh data. Each week it gets sharper — without us touching it.

FEATURE IMPORTANCE (TOP 8 / 44)
intent
0.92
hasPassword
0.78
hasLogin
0.71
hasExternalFormAction
0.64
trustedDomain
0.58
hasSPF
0.51
hasForm
0.44
domainAgeDays
0.37
Q2 2026LLM Reasoning

Claude joins the team.

Natural language understanding at scale.

Rules and ML catch patterns. But scams evolve — new variants, new lures, new emotional hooks. Claude Sonnet became our 8th layer: synchronous LLM analysis for ambiguous cases with a 3-second timeout. It can't override strong conviction rules, but it adds nuance where our other layers see only signals. The result: fewer false positives, richer reasoning.

CLAUDE ANALYSIS
This message uses urgency ("account will be suspended in 24h"), impersonates your bank's support team, and contains a link to a newly-registered domain. The combination of emotional pressure and a suspicious link is a classic phishing pattern.
urgency
impersonation
new_domain
credential_harvest
Q2 2026Gmail Integration

Always watching the inbox.

Pub/Sub webhook. Real-time scanning.

Connect your Gmail account and SentriesAI scans every incoming email through the full conviction pipeline. Phishing attempts, scam campaigns, and brand impersonation get caught before you open them. Push notifications alert you on threats. Multi-account support for users managing personal and work inboxes together.

P
PayPal Security
Action required: verify your account
THREAT
2m
A
Amazon
Your order has been shipped
14m
B
BRD <info@bnk.ru>
Suspicious login detected
THREAT
1h
G
GitHub
New pull request
3h
Q2 2026Platform

Mobile, family, and payments.

The platform matures.

React Native mobile apps for iOS and Android. Family plans with parental oversight. Organization dashboards with role-based permissions. Stripe billing with 90-day free trials on all paid plans. Image OCR for screenshot scanning. The scattered pieces became a cohesive platform that works across every way you communicate.

MOBILE
iOS + Android
FAMILY
5 members / plan
ORGS
Role-based
BILLING
Stripe + 90d trial
OCR
Screenshot scan
API
REST + webhooks
ACT II · WHAT'S NEXT

Everything
that's next.

Six chapters. Eighteen months. From collective immunity to real-time voice fraud protection.

Q3 2026Collective Immunity

When one is protected,

everyone is protected.

When a user detects a new scam, every other active user is instantly immunized against the same threat. No blocklist delay. No batch update. Real-time WebSocket push — 'a new threat was neutralized, 347 users protected in the last 5 minutes.' The more users join, the stronger everyone's protection becomes. Backend is 95% ready.

347 USERS PROTECTED · 5 MIN
Q3 2026Guardian Angel

Protect the ones you love.

Without them installing anything.

Add your parents' or grandparents' WhatsApp number and SentriesAI auto-scans every message they receive. When a threat appears, both you and they get alerted. The first security product you gift to someone else — the one they don't have to set up, configure, or remember to use. Because the people most targeted by scams are often the least equipped to defend themselves.

M
Mom
protected · online
Hi honey, your bank account is blocked. Verify here: brd-secure.cc/login
SCAM BLOCKED · You were notified
Q3 2026Mobile v2

Every feature. In your pocket.

Complete parity with the web.

Full feature parity with the web experience: URL scan, text scan, chat history, Gmail integration, recent scans sidebar with live updates, push notifications for threats. Native widgets for iOS and Android home screens. App Store and Google Play launch with zero compromises between platforms.

SCAN
example0.com
safe · 98%
example1.com
safe · 98%
example2.com
safe · 98%
example3.com
safe · 98%
HISTORY
example0.com
safe · 98%
example1.com
safe · 98%
example2.com
safe · 98%
example3.com
safe · 98%
Q4 2026Immunity Training

Train your instincts.

Three minutes a day.

Gamified training sends you simulated phishing messages across email, SMS, and chat. Can you spot the fake? Short daily sessions adjust difficulty to your real-world scan history. Enterprise vendors charge 50,000 euros a year for this. We're making it available to everyone — starting from day one of your free account.

LESSON 12 · SMISHING
Is this message legit?
DHL: Your package couldn't be delivered. Update address: dhl-redelivery.info/track
Q4 2026Waste Bot

Turn the tables.

Waste their time. Save others'.

Detect a scam, then with one click deploy an AI bot that plays a convincing target. It asks naive questions, creates technical problems, tergiversates for hours. You watch the conversation live. The best ones become viral content — and every minute the scammer spends on the bot is a minute they're not targeting a real victim.

Hi, I'm from Microsoft support. Your PC is infected.
Oh no! How do I fix it?
Download this software and I'll help you.
Is it a .exe? My screen is pink now btw.
What? Pink?
Yes, very pink. Also my mouse is upside down.
BOT ACTIVE · 4h 23min wasted
Q1 2027Vishing Shield

The final frontier.

Real-time protection against voice fraud.

68% of financial fraud happens over phone calls. On-device AI analyzes live audio for urgency patterns, authority impersonation, and social engineering tactics. A gentle vibration warns you mid-call — before the scammer gets what they want. No one in the world does this yet. We will.

INCOMING CALL · UNKNOWN
+40 755 123 456
Bank impersonation detected
urgency 92% · authority 87%
THE END. FOR NOW.

Shape what comes next.

User feedback directly influences our priorities. Tell us what you want us to build, and we'll build it.

Get started freeSend feedback