SharkScholar

home page
choose academic path mdc
choose academic path mdc
timeline
relevant scholarships
generated proposal/essay for scholarship

Inspiration

We were inspired to create SharkScholar after seeing how many students struggle to understand which classes, programs, or scholarships best align with their career goals. We wanted to build an AI-powered tool that turns transcripts and resumes into clear, personalized pathways — helping students make smarter academic and career decisions with confidence.

What it does

SharkScholar is a full-stack AI app that helps students turn their transcripts and resumes into personalized career and education pathways. It uses Gemini AI to read PDFs, match scholarships, and build structured program maps, while a React + Vite frontend and Cloudflare Workers backend make everything fast and serverless. The app can analyze college programs (like MDC pathways), suggest next courses or transfer options, and even draft scholarship proposals — all through an interactive, user-friendly interface.

How we built it

We built SharkScholar as a full-stack app using React + Vite for the frontend and Cloudflare Workers (Hono) for the backend. Our backend integrates Gemini AI for natural language processing to analyze transcripts, resumes, and program PDFs, returning structured JSON data. We created a custom MDC program scraper and a pathway generator to map programs to careers. The frontend connects these features through an interactive flow — from career search to program analysis to pathway and scholarship generation — with a clean, responsive UI and optional wallet integration for on-chain student proofs.

Challenges we ran into

One of the biggest challenges we faced was creating a personalized roadmap that truly aligns with each student’s background and goals. It was difficult to ensure that the AI-generated pathways accurately reflected individual transcripts, transfer credits, and career interests. Balancing data accuracy with flexibility — while keeping the experience smooth and intuitive — took a lot of iteration and fine-tuning between our frontend flow, backend logic, and Gemini AI prompts.

Accomplishments that we're proud of

We’re proud of building a fully functional full-stack app that connects AI, education, and blockchain in one platform. Our biggest wins include creating accurate Gemini-powered PDF parsing for transcripts and resumes, designing a clean and intuitive React + Vite UI, and deploying a serverless backend on Cloudflare Workers for low-latency AI calls. Most of all, we’re proud of being given the chance to help others, empowering students to better understand their academic options and confidently plan their future.

What we learned

We learned a lot about making AI work smoothly with real-world data. Getting Gemini to consistently parse PDFs and return clean, structured results took serious prompt tuning and testing. On the backend, we figured out how to use Cloudflare Workers to handle fast, serverless AI calls, and on the frontend, we built a responsive React + Vite flow that ties everything together in real time.

What's next for SharkScholar

Expand to more colleges, improve AI-driven course recommendations, and add on-chain verification so students can securely prove achievements and receive scholarships.