Inspiration
We developed Future me AI to help students who have trouble identifying areas where they need to improve. The problem with most learning platforms is that they offer a one-size-fits-all approach, which doesn't work because each student has their own unique way of learning.
Our goal was to create an AI mentor that would carefully track a student's progress, pinpoint their strengths and weaknesses, and provide them with tailored advice to keep them on track. As we worked on the project, we continually refined our ideas and developed features that would genuinely benefit students, making sure they were practical and effective. We wanted to make a real difference in their learning journey, so we designed the AI mentor to be a supportive tool that would help students navigate their academic path with confidence.
Our goal is simple: make learning more personalised, motivating, and effective for every student.
What it does
Future Me is an AI-powered academic performance and habit-tracking tool. Tracks Performance: Analyzes study logs, study habits, and grade trajectories. Predicts Outcomes: Uses smart algorithms to project potential future academic outcomes based on current trends. Actionable Recommendations: Provides personalized, step-by-step advice and study schedule adjustments to help students improve their performance before falling behind.
How we built it
Frontend: Built with an intuitive, user-friendly interface to make logging study sessions and viewing academic trends effortless. AI & Algorithm: Developed a tracking model that analyzes incoming study metrics and grade trends to output real-time progress assessments and predictions. Data Flow: Structured seamless data integration between user inputs and backend processing to deliver personalized improvement strategies instantly.
Challenges we ran into
Data Accuracy: Fine-tuning the algorithm to give realistic, encouraging, and constructive feedback based on limited initial data points. UX/UI Balancing: Designing an engaging interface that feels motivating rather than overly punishing or overwhelming. Time Constraints: Implementing core features, refining backend calculations, and polishing the final layout within the strict hackathon timeframe.
Accomplishments that we're proud of
Successfully building a working end-to-end prototype during the hackathon. Creating an AI system that provides actionable, meaningful study insights tailored to an individual student's routine. Developing a solution to a real-world problem that every student can relate to.
What we learned
How to quickly train and refine predictive models under hackathon deadlines. The importance of user experience when presenting performance data and academic feedback. How to effectively collaborate, divide tasks, and solve technical bugs on the fly.
What's next for Future me / AI
LMS Integration: Connect directly with platforms like Canvas, Google Classroom, and Blackboard to auto-sync grades and study materials in real time. Smarter Predictive Models: Train our algorithms on larger datasets to provide even more accurate career and academic trajectory forecasting. Interactive AI Tutor: Expand beyond tracking by adding an AI mentor that helps create customized study plans, practice quizzes, and daily task breakdowns. Mobile App Development: Build a dedicated iOS and Android app to send push notifications and daily study reminders straight to users' phones.
Log in or sign up for Devpost to join the conversation.