StudyMapper

admin portal
AI-agent matching tool
landing page

Every year, more than 80,000 Vietnamese students search for a path to study abroad — yet no tool truly understands what they need. ChatGPT offers generic advice, traditional consulting is expensive and out of reach for most families, and students end up spending weeks, even months, browsing websites and comparing options manually, still unsure if they're heading in the right direction. That gap between ambition and clarity is what inspired us to build StudyMapper AI. What it does StudyMapper AI is a personalized university matching platform. Students enter their profile — GPA, IELTS score, budget, intended major, and target country. Within 30 seconds, powered by a large language model, the platform returns a curated list of best-matched universities, complete with compatibility scores, specific reasoning, an action roadmap, and scholarship analysis. No guesswork, no generic answers — just the right student, matched to the right school. How we built it We built StudyMapper AI using the Anthropic Claude API with web search capabilities, allowing the system to scrape and verify real-time university data. The frontend is a responsive web interface with scroll-based animations, and the matching engine applies multi-factor weighted scoring across GPA, language requirements, tuition budget, and scholarship availability. Challenges we ran into The biggest challenge was making the AI truly personalized rather than just a smarter search filter. Normalizing GPA across different grading systems, handling incomplete user profiles gracefully, and ensuring the model explains its reasoning in a way that feels human and trustworthy — these required significant prompt engineering and iteration. Accomplishments that we're proud of We're proud of building a working end-to-end prototype — from profile input to matched results with explanations — in a single hackathon session. The gap analysis feature, which automatically identifies what a student needs to improve to unlock more options, felt like a meaningful breakthrough. What we learned We learned that personalization is not just about filtering data — it's about understanding context. The difference between a useful recommendation and a generic one often comes down to one or two pieces of information the user never thought to mention. Designing the input flow to surface those details naturally was the most valuable lesson. What's next for StudyMapper We plan to expand the university database to 500+ institutions across 15 countries, integrate a parent-facing dashboard for family decision-making, and add a PDF export feature so students can share their personalized roadmap with advisors and family members. Longer term, we want to partner with ETEST and similar education centers to connect students with the right preparation programs based on their gap analysis.