Inspiration

While working on this idea, we realized that access to laboratory equipment is not the same for every researcher. Some institutions have expensive instruments that are not being used all the time, while smaller laboratories and students may struggle to access the equipment they need.

We wanted to find a practical way to connect these two sides. That's how LabShare AI started. Our idea was to create a platform where researchers could find suitable laboratory equipment, book it when needed, and make payments through a simple process.

What it does

LabShare AI helps researchers find and book laboratory equipment without having to search through multiple sources.

One of its main features is the AI Equipment Matcher. Instead of knowing the exact name of an instrument, researchers can simply describe their experiment or requirements. The system uses Gemini AI to suggest equipment that could be suitable for their work.

Users can also explore equipment listings, compare options, choose booking slots, and complete a test payment through PayPal Sandbox. They can then manage their bookings through the application.

For this hackathon, we used sample laboratory listings to demonstrate how the platform would work.

How we built it

We built the frontend using React, TypeScript, Vite, and Tailwind CSS, focusing on making the application simple to navigate.

For the backend, we used Python and Flask to handle requests, bookings, and payment-related functions. We integrated Google Gemini AI for equipment recommendations and PayPal Sandbox to demonstrate the payment process without using real money.

We also used GitHub to manage our code and Vercel to deploy the frontend.

Challenges we ran into

One challenge was making the AI understand different research requirements and suggest equipment that actually matched them. Researchers may describe the same requirement in different ways, so we had to think about how the system should handle those inputs.

We also faced difficulties connecting the frontend with the backend and integrating the PayPal payment process into the booking workflow.

Testing these features and fixing errors took time, but it helped us understand how the different parts of the application work together.

Accomplishments that we're proud of

We're proud that we were able to bring several features into one working application.

The AI Equipment Matcher is one of our favorite parts because it makes equipment discovery easier, especially for someone who knows what experiment they want to perform but isn't sure which instrument to use.

We're also happy that we could connect equipment booking with PayPal Sandbox payments and build an interface that's easy to understand.

What we learned

This project helped us understand what it takes to build an application beyond just designing its interface.

We gained hands-on experience with React, Flask, API integration, AI recommendations, and PayPal Sandbox payments. We also learned more about debugging, testing, and preparing an application for deployment.

Most importantly, we learned how combining different technologies can help solve a practical problem in scientific research.

What's next for LabShare AI

Right now, LabShare AI is a working demonstration using sample equipment data. Our next step would be to connect real laboratories and research institutions so researchers can access actual equipment availability.

We would also like to add live scheduling, laboratory verification, equipment maintenance information, and dashboards for institutions to manage their resources.

In the long run, we hope LabShare AI can help researchers make better use of existing laboratory facilities instead of being limited by the equipment available at their own institution.

Built With

React, TypeScript, Vite, Tailwind CSS, Python, Flask, Google Gemini AI, PayPal Sandbox, GitHub, and Vercel.