RecallAI

Inspiration

Students often spend hours studying but struggle to remember concepts later. We wanted to build a tool that makes revision more interactive and helps students identify gaps in their understanding. This inspired us to create RecallAI, an AI-powered personal learning and revision agent.

What it does

RecallAI helps students revise topics using active recall. Students enter a topic and their study notes, and the application generates questions using AI. Students answer those questions and receive AI-powered evaluation and feedback to understand what they got right and which concepts need more revision.

RecallAI also saves learning sessions in a database, allowing students to revisit their learning history even after refreshing the application.

How I built it

I built RecallAI as a full-stack web application using React and Vite for the frontend, Node.js and Express for the backend, and MongoDB Atlas for persistent storage. I integrated Backboard AI to power question generation and answer evaluation.

I deployed the frontend on Vercel and the backend on Render, connecting them through API endpoints so users can access the application online.

Challenges I ran into

One of the main challenges was connecting the frontend, backend, AI integration, and database into a working application. Configuring environment variables and API URLs for deployment also required debugging. Another challenge was ensuring that learning sessions were stored persistently and remained available after refreshing the page.

Accomplishments that I'm proud of

I am proud of building a working AI-powered learning application that brings question generation, answer evaluation, and learning history together. I successfully connected the frontend and backend, integrated the AI workflow, and implemented persistent session storage so that learning history remains available after refresh.

What I learned

Through this project, I gained practical experience in full-stack development, REST API integration, database persistence, AI integration, and cloud deployment. I also learned how different components of a web application work together to deliver a complete user experience.

What's next for RecallAI

I plan to improve RecallAI with detailed quiz reviews, progress tracking, topic management, and the ability to retry previous quizzes. Future improvements could also include personalized revision recommendations based on previous performance and concepts that students find difficult.

Built With

• ai
• backboard
• css
• express.js
• html
• javascript
• mongodb
• node.js
• react
• render
• vercel
• vite