DEV Community

Cover image for SafeReach AI
PRADEEP HEBBALLI
PRADEEP HEBBALLI

Posted on

SafeReach AI

SafeReach AI – Global Scam & Crisis Safety Assistant

Elevator Pitch

SafeReach AI helps users detect scam-risk indicators, follow crisis guidance, use safety chat, and generate family alerts in Live Safety Mode.

Project Link

https://app-bg447rmtqhhd.appmedo.com/

Category

Learning & Education

About the Project

SafeReach AI is a global no-login safety assistant built with MeDo for seniors, families, caregivers, migrants, travelers, and vulnerable users.

The project was inspired by a real and serious problem: during emergencies, people often face two risks at the same time — the crisis itself and scams that exploit fear, urgency, and confusion.

A person may receive a message about bank verification, flood relief, hospital payment, government aid, emergency donation, or a family member in danger. In stressful situations, it can be difficult to know what is real, what is risky, and what action to take next.

SafeReach AI was built to help users answer one urgent question:

Is this message risky, and what should I do safely right now?

What It Does

SafeReach AI includes:

  • Live Safety Mode for real user-entered messages and crisis guidance
  • Demo Mode for sample scam and crisis scenarios
  • Scam-risk message analyzer
  • Guided Safety Chat Assistant
  • Crisis Navigator with step-by-step emergency guidance
  • Senior Mode with large, simple action buttons
  • Emergency Wallet Card generator
  • Family Alert Generator
  • Self-Help Safety Center
  • Country Safety Packs
  • Privacy-safe local analytics

The scam analyzer uses rule-based risk scoring to identify indicators such as:

  • OTP, PIN, password, or CVV requests
  • Bank/KYC verification pressure
  • Suspicious links
  • Urgent payment requests
  • Fake relief or government aid claims
  • Fake charity or donation requests
  • Family emergency pressure
  • Instructions not to call family, police, or banks

Instead of saying a message is definitely a scam, SafeReach AI uses safer language:

This message shows scam-risk indicators.

This keeps the app responsible while still giving practical safety guidance.

Inspiration

The inspiration came from real-world scam patterns that target vulnerable people, especially during emergencies.

Scammers often send messages like:

  • “Your bank KYC is expired. Enter OTP now.”
  • “Flood relief approved. Pay a processing fee.”
  • “Your son is in hospital. Send money immediately.”
  • “Government aid available. Upload your ID and bank details.”
  • “Donate now to an official rescue team.”

These messages combine urgency, emotion, money, and confusion. SafeReach AI slows the user down, highlights red flags, and guides them toward safer action.

How I Built It

I built SafeReach AI using MeDo through prompt-driven development and iterative testing.

MeDo helped turn a complex safety concept into a working web app by allowing me to describe the product structure, user flows, safety rules, UI behavior, and demo scenarios step by step.

The build process included:

  • Designing the Live Safety Mode and Demo Mode structure
  • Creating a global country and language selector
  • Building the suspicious message analyzer
  • Adding rule-based scam-risk scoring
  • Creating crisis guidance flows
  • Designing a senior-friendly interface
  • Adding a guided safety chat assistant
  • Creating emergency wallet card and family alert tools
  • Adding privacy-safe analytics
  • Testing the app for mobile usability, safe behavior, and clear disclaimers

MeDo was especially useful for rapid iteration. I could test the app, identify weak points, and improve the experience through follow-up prompts.

One important refinement was changing the app from a demo-only concept into a usable product with Live Safety Mode as the default and Demo Mode as an optional walkthrough mode for judges and testing.

What I Learned

I learned that safety apps must be designed differently from normal productivity apps. Users may be stressed, confused, elderly, or in danger, so the interface must be calm, simple, and direct.

I also learned the importance of responsible boundaries. SafeReach AI does not contact emergency services, does not diagnose medical problems, does not give legal advice, and does not guarantee scam detection. Instead, it provides structured safety guidance and encourages users to verify through trusted people and official channels.

I also learned how powerful prompt-driven development can be for building multi-feature apps quickly. MeDo helped me focus on product thinking: what the user sees, what they click, what they understand, and how safely the app behaves.

Challenges I Faced

The biggest challenge was balancing usefulness with safety.

A scam and crisis app must be helpful, but it must not overclaim. I had to carefully design the wording so the app says “risk indicators” instead of “confirmed scam.”

Another challenge was avoiding a demo-only experience. The app originally focused heavily on sample scenarios, but I refined it so users can actually paste their own messages and use Live Safety Mode.

A third challenge was making the app senior-friendly. That required large buttons, simple text, clear warnings, and direct actions like:

  • I Am Safe
  • Do Not Share OTP/PIN
  • I Received Money Request
  • Ask Safety Assistant
  • Create Emergency Card

The goal was to reduce confusion and make safer action easier.

Built With

  • MeDo
  • Prompt-driven app development
  • Web app interface
  • Rule-based risk scoring
  • Responsive UI design
  • Local app state
  • Privacy-first no-login structure
  • Guided safety chat logic
  • Global country safety packs
  • Live Mode and Demo Mode workflows

Key Features

Live Safety Mode

Users can paste their own suspicious message, select their country and language, and receive scam-risk indicators, red flags, safe next steps, and a family alert template.

Demo Mode

Judges and users can run preloaded scam and crisis scenarios to understand how the app works.

Guided Safety Chat

A rule-based assistant helps users navigate situations like suspicious messages, money requests, crisis steps, senior support, and family alerts.

Crisis Navigator

Users can select crisis types such as flood, heatwave, earthquake, fire, medical emergency, cyber scam, evacuation, or power outage and receive structured guidance for:

  • First 10 minutes
  • First 1 hour
  • Next 24 hours

Senior Mode

A simplified interface with large buttons helps seniors take quick actions without navigating complex screens.

Emergency Wallet Card

Users can create a local emergency card with key details, emergency contacts, medical notes, and safety reminders.

Privacy-Safe Analytics

The app tracks local interaction counts for product feedback without storing raw user messages.

What’s Next

Future improvements could include:

  • Offline crisis safety packs
  • More countries and languages
  • Voice/audio mode for low-literacy users
  • Verified local safety partners
  • NGO/admin safety content dashboard
  • Official emergency alert integrations
  • Encrypted emergency card storage
  • Caregiver sharing mode
  • More advanced scam-pattern detection
  • Accessibility improvements for seniors and disabled users

Final Summary

SafeReach AI is a global no-login safety assistant that helps users detect scam-risk indicators, follow crisis guidance, use guided safety chat, generate family alerts, and create emergency wallet cards.

Using MeDo, I was able to transform a complex public-safety idea into a working web app with Live Safety Mode, optional Demo Mode, senior-friendly design, and privacy-safe local analytics.

Top comments (0)