I built CampusFind AI, an AI-powered Lost & Found platform designed to help students recover lost belongings on campus.
The idea came from a simple problem: when a student loses something on campus, finding it again can be surprisingly difficult. They may post about it in WhatsApp groups, ask friends, check with security, or simply hope someone found it. At the same time, students who find an item often have no easy way to identify its owner.
CampusFind AI brings both sides together in one platform.
Students can report lost and found items with descriptions and images, and the system uses AI to analyze item details and find potential matches. Instead of relying only on exact keywords, the matching system considers information such as:
The goal is simple: make it easier for a student to get their lost belongings back.
I built it as a project that could actually be used by students on a college campus rather than just as a prototype.
Live Application:
The application is fully deployed, with the frontend hosted on Vercel and the backend deployed separately with a cloud MySQL database.
GitHub Repository:
This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
Currently, two official plugins are available:
The React Compiler is not enabled on this template because of its impact on dev & build performances. To add it, see this documentation.
If you are developing a production application, we recommend using TypeScript with type-aware lint rules enabled. Check out the TS template for information on how to integrate TypeScript and typescript-eslint in your project.
The project contains both the frontend and backend components and includes the implementation of authentication, item management, AI-powered matching, image handling, and claim processing.
CampusFind AI is built using:
The AI is used in two important parts of the application.
When an item is reported, AI can analyze its description and image to identify useful attributes such as the object type, colors, material, features, and distinctive characteristics.
These attributes are stored as structured data and can later be used during matching.
When a lost item needs to be matched with found items, the system compares multiple factors rather than simply checking whether the item names are identical.
The matching process considers attributes such as:
Category + Name + Color + Material + Features + Location + Date + Distinctive Features
The system then generates a match score and returns the most relevant potential matches.
I also implemented authentication and authorization so that students can manage their own reports, while administrative functionality can handle claims and returned items.
Open innovation makes it possible for developers like me to experiment with AI-powered solutions without having to build every component from scratch.
For this project, the important part wasn't simply adding an AI chatbot. I wanted AI to solve a specific problem inside an application.
Using an AI model allowed me to turn unstructured information such as:
"I lost my cream and brown backpack near the library."
into useful attributes that could be compared against reported found items.
This makes the system more flexible than a basic keyword-based search.
Open innovation also makes it easier for students and independent developers to experiment, learn, modify existing ideas, and build solutions for problems in their own communities.
For a campus-specific problem like Lost & Found, that accessibility is particularly valuable. A student doesn't need a large company or expensive infrastructure to start building something useful for their own college.