What I've built, and what I learned
Every project here started with a genuine question, involved at least one major failure, and taught me something I couldn't have learned any other way.
RAG Based Search Tool — Internship Project
An AI-driven Retrieval-Augmented Generation (RAG) system built during my time at Bharati Innovative to organize and unlock scattered historical CAD/CAM design knowledge, reducing lookup time and improving workflow efficiency by an estimated 65–75%.
Technology for Parents of Autistic Children
A platform designed to make useful information and resources more accessible to parents navigating autism-related challenges. Built after observing how fragmented existing resources were.
Autonomous Vehicle
Teaching a small vehicle to perceive its environment, make navigation decisions, and move without human control. The core question: how does a machine understand space?
Fall Detection System
An embedded system designed to detect potentially dangerous falls using low-cost sensors. Exploring whether affordable hardware can provide meaningful safety benefits.
Heart Disease Risk Prediction Using Machine Learning
Developed a machine learning application to predict heart disease risk using clinical data, achieving over 87% accuracy. Built an interactive user interface for instant preliminary risk predictions using real-world Kaggle datasets. Deployed the application on Vercel, gaining hands-on experience in end-to-end AI product development.
KissanConnection — Empowering Farmers
A smart agriculture web platform connecting Indian farmers directly with B2B buyers, D2C consumers, farmer's markets, financial assistance, and wellness support — cutting middlemen and maximising farmer profit.
These projects are ongoing explorations of ideas, problems, and possibilities. Rather than focusing solely on polished demos, I aim to showcase how I approach challenges, experiment with solutions, and learn along the way. If you’re curious about the thinking behind each build—the failures, pivots, and unexpected discoveries—you’ll find the real story here.