What we learnedInspiration
As a B.Tech student, I noticed that creating quizzes from study materials is time-consuming for both students and teachers. Most tools only support small text files and fail to understand images or scanned notes. I wanted to build a solution that could automatically convert large documents and images into intelligent quizzes using AI.
That idea became QuizGen AI.
What It Does
QuizGen AI is an AI-powered quiz generation platform that transforms PDFs, DOCX, TXT files, and images into smart, exam-ready quizzes.
Users can:
Upload documents up to 25MB
Upload images up to 6MB
Generate 5–100 AI-based questions
Take quizzes and get instant results & analytics
It uses Gemini 2.5 Flash with Vision, allowing the system to understand both text and visual content.
How We Built It
Frontend built with React + Tailwind CSS for a clean and responsive UI
Backend logic integrated with Google Gemini 2.5 Flash Vision API
Implemented file handling for large documents and images
Designed prompt logic to generate accurate, topic-based questions
Added quiz flow, scoring system, and result analysis
Challenges We Faced
Handling large file uploads efficiently
Extracting meaningful quiz content from mixed text + image inputs
Optimizing prompts to avoid irrelevant or repetitive questions
Maintaining fast performance with AI processing
Each challenge helped improve the system’s reliability and accuracy.
What We Learned
Practical integration of multimodal AI (text + vision)
Prompt engineering for educational use cases
Building scalable EdTech solutions
Improving UX for students and educators
Log in or sign up for Devpost to join the conversation.