-
-
Karthik
Inspiration Scams and phishing messages are becoming increasingly common. We wanted to create a simple AI-powered tool that helps people identify suspicious messages and stay safer online. What it does Kavach AI analyzes a message using an AI API and provides: 🛡️ Scam probability ⚠️ Risk verdict 🔍 Explanation of suspicious signs 💡 Safety recommendations 🔊 Text-to-speech for the result How we built it We built Kavach AI using HTML, CSS, and JavaScript. Instead of embedding our API key directly into the project, the user can enter their own API key when using the application. This avoids exposing a developer's personal API key in the source code. Challenges we ran into We faced challenges with connecting the API, handling JSON responses, displaying AI-generated results correctly, and debugging the frontend. We also had to make sure the API key was not permanently exposed in the project. Accomplishments that we're proud of We are proud of creating a functional AI-powered scam detection tool with a clean interface and a user-provided API system that gives users more control over their API credentials. What we learned We learned how to work with JavaScript, APIs, JSON, asynchronous requests, and AI model responses. We also learned why API keys should not simply be hard-coded into publicly shared projects. What's next for Kavach AI We want to add URL scanning, screenshot analysis, voice input, multilingual support, and improved phishing detection. We also want to improve how API credentials are handled so they can be used securely in a production-ready version.
Built With
- api
- browser
- css3
- gemini
- html
- html5
- javascript
