Skip to Main Content

an Electron-based desktop overlay that acts as a "digital friend" for non-technical users navigating complex government websites. By using Gemini Multimodal Live, the app "sees" the user's screen through continuous captures and "hears" their voice to provide real-time guidance. Instead of just talking, it draws visual arrows and highlights directly on the screen to show exactly where to click and can even perform actions (like clicking or typing) once the user gives a voice "yes" to confirm. This combines AI vision with human-in-the-loop automation to turn a confusing tax or ID portal into a simple, guided conversation.

Team

januaryfeb

Placement

Participant

More from Gemini 3 Bengaluru Hackathon

TryOnAI is a universal virtual try-on shopping assistant that lets you chat in any language, browse any e-commerce website in the world, and instantly see…

anoniket project preview

Voice calling agent that will make a call on our behalf and inquire about details in any language.

drive.google.com/…

This is an AI-powered educational tool that automatically generates animated math/physics solution videos from simple text prompts. It combines Google Gemini…

x.com/…

Diffcast automatically converts code changes into demo videos that are easily understandable for non-technical teams. When a commit occurs, our system…

Psyduck project preview

Our application is built upon Vision Claw(open source repo), which allows users to interact with AI using the Google Gemini Live API and Gemini 3 Pro via Open…

Taheer project preview

My grandfather recently walked 2km to a hospital because he couldn't book a cab—the ads and clutter on the Ola app made him feel helpless. This "digital…

drive.google.com/…