Projects

Designed Google Drive Companion, an AI-powered productivity assistant that transforms Google Drive from passive storage into a proactive intelligence platform. Built intelligent features including automated Syllabus-to-Schedule parsing (converts course outlines to Google Calendar), Smart Reading Packs (condenses PDFs into summaries and flashcards), and AI Meeting Chief of Staff (auto-captures decisions and action items). Conducted user research with 100+ students and professionals, revealing that emotional benefits (reduced anxiety, increased confidence) drive 70% more adoption than time-saving alone. Created dual-persona design system serving both academic and workplace users, addressing the $65.94B AI productivity market gap where competitors require manual file uploads while Companion seamlessly integrates within the Drive ecosystem.

Built an interactive data visualization project analyzing 129 horror film screenplays to discover the "power law of horror" using AI and statistical analysis. Developed a hybrid GPT-4o-mini/GPT-4o parsing pipeline that processed 10,000 scenes to extract 11,204 horror signals, achieving 99.97% success rate while reducing costs by 96.5%. Created 8 custom D3.js visualizations including a real-time Fear Monitor with BPM animation, Sankey flow diagrams for signal analysis, Markov chain transition matrices for pacing patterns, and interactive bubble charts revealing that elite signals like "scream" and "blood" drive 68% of fear responses despite representing only 5% of detected elements. Demonstrated advanced skills in AI prompt engineering, parallel processing with Python, data pipeline architecture, and responsive visualization design.

Led a team to develop The Night Shift, an interactive three-chapter data story challenging the assumption that job titles primarily drive sleep quality. Analyzed a dataset of 374 individuals exploring how personal lifestyle choices and physiological markers often outweigh professional roles. Using D3.js, built a series of multivariate visualizations including a Bubble Landscape examining stress variance within professions and a Sankey Diagram revealing pathways between physical activity levels and sleep outcomes. Engineered The Dream Lab, a physiological mapping tool where data points pulse in sync with resting heart rates.

Led the product design and UI/UX for Food ResQ, an AI-powered fridge management app developed during Hack The Valley 8 to combat household food waste. Designed complete user experience for tracking fridge inventory via MongoDB database and generating flexible recipe recommendations using ChatGPT. Created intuitive interface for quickly adding ingredients (even unmeasured or unknown foods), built using React.js and Bootstrap frontend with Flask backend. Managed API integration with OpenAI for consistent recipe generation and wrote detailed prompts to retrieve formatted cooking instructions. Secured 6th place overall and won Best Use of MongoDB Atlas, demonstrating ability to deliver polished demo under 36-hour hackathon constraints.

Redesigned The Music Pathways Project to transform how music students discover career pathways beyond traditional performance and teaching. Created Tempo, a character mascot designed as a friendly metronome that serves as the face of an AI-powered chatbot, making career exploration feel personal and approachable. Built an Interactive Pathways Explorer that replaced static PDF documents with an animated career map, integrating natural language queries with real-time visual highlighting to reduce cognitive load and support different learning styles. Developed brand strategy using CBBE framework and positioning principles, including dual brand mantras ("Illuminate Pathways. Redefine Music. Empower Futures.") and the tagline "Discover where music can take you." Completely redesigned homepage from static text-heavy layout to dynamic interactive entry point, applying consumer behavior principles to reduce search costs and build brand salience, resulting in stronger engagement and emotional resonance with students exploring diverse music careers.

Led the UX design for Tutorly, a peer tutoring platform built to bridge the gap between students through personalized academic support. Directed end-to-end design process starting with comprehensive user research and detailed persona creation. Designed core functional suite including personalized recommendation system for finding matches, integrated messaging interface, and data-driven progress tracking dashboard. Conducted iterative usability testing using student feedback to refine navigation and feature set. Project achieved final evaluation score above 85% and was selected for showcase at University of Toronto Scarborough Undergraduate Research Symposium 2024.

Designed the UI for Matchify, a music-driven social application that connects users through their listening habits. Developed an intuitive navigation system and customizable user profiles prioritizing visual identity and musical taste. Created streamlined onboarding process leveraging Spotify API integration to instantly personalize user journey. Designed comprehensive settings suite with granular privacy options. High-fidelity prototype was selected to be showcased at ARIA 2024, University of Toronto's premier research and innovation event.