Degree

Master of Science in Computer Science

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Fall 2025

Supervisor

Dr. Tariq Mahmood, Professor, School of Mathematics and Computer Science (SMCS)

Keywords

Gamification, Education Technology, AI Question Generation, Card Combat Game

Abstract

Educational platforms typically force a choice between engaging games or flexible content management. Teachers either get rigid quiz formats (like Kahoot) or content- heavy platforms without real gamification. This project presents a platform that combines both. We built a system where teachers can create questions manually through a rich text editor supporting code syntax highlighting, LaTeX math, and image support, or generate them through AI templates using OpenAI’s GPT. Students then interact with this content in two ways: traditional timed quizzes, or a turn-based card combat game where answering questions becomes the battle mechanic. The technical stack uses FastAPI on the backend with PostgreSQL and SQLModel as the ORM. The frontend runs React with TypeScript, using Three.js for 3D card graphics and TanStack Router for file-based routing. AI generation follows a template- based approach with multi-layer validation: format checks run first to catch structural issues, and optional content quality checks use a secondary LLM call for scoring. The game includes health and shield systems, special abilities with 4-turn cooldowns, and real-time WebSocket communication. Future work includes polishing the game mechanics, adding more “fun” features, and writing automated test suites.

Document Type

Restricted Access

Submission Type

Research Project

Download

The full text of this document is only accessible to authorized users.

Access content accompanying this publication

Share

COinS