Inspiration We wanted to build a learning tool that actually feels natural to use. Most study platforms are overwhelming or too formal, but texting is something everyone understands. We asked ourselves: what if learning felt like chatting with a friend? That idea became SAGA a simple, conversation-first way to understand any topic without stress.
What it does SAGA is an AI-powered chat that explains any topic in clear, human language. Users just type a question, and SAGA replies with simple breakdowns, examples, analogies, or step-by-step explanations. The interface looks and feels like iMessage, so learning happens through conversation instead of long articles or complicated dashboards.
How we built it We designed a lightweight React frontend using a custom chat interface to mimic a texting experience. On the backend, we used Node.js and Express to handle requests and connect to the OpenAI API for generating explanations. We structured the app so messages flow from the UI → backend → AI model → formatted response back to the chat. We coordinated through GitHub and split the work between frontend styling and backend logic.
Challenges we ran into We had a very short timeline, so coordinating tasks while learning parts of the tech stack was a challenge. We also ran into API authentication issues, environment variable setup problems, and a few broken connections between the frontend and backend. Making sure both sides communicated smoothly took a lot of debugging.
Accomplishments that we're proud of We’re proud that we built a clean, working conversational learning tool in such a tight timeframe. We designed an intuitive UI, learned how to connect a full AI-powered backend, and created something that genuinely feels helpful. Seeing SAGA respond with clear explanations was a big moment for us.
What technologies did we use? The frontend was built with React and Vite to create a fast, responsive chat-style interface. The backend uses Node.js and Express to handle API requests and connect to the OpenAI API. We also used JavaScript throughout the project for both client-side and server-side logic. Together, these technologies allowed us to build a smooth, real-time conversational experience.
Which track are we submitting to? We are submitting SAGA to the “Automate Learning: Build Smarter Study Tools” track. SAGA fits this category because it automates explanations, feedback, and guided learning in a way that makes studying both faster and more personalized. It’s designed to meet students where they are, help them grasp difficult material, and make the learning process more efficient and supportive.
What we learned We learned how to build a full-stack AI application from scratch, including handling API keys, routing, state management, and deployment issues. We also learned how to collaborate efficiently, divide tasks, and troubleshoot under time pressure.
What's next for SAGA We’d love to add features like visual explanations, voice note input, better personalization, conversation memory, and study-mode summaries. In the future, SAGA could support group chats, classroom tools, and even guided learning paths.
Built With
- api
- chatgpt
- express.js
- javascript
- node.js
- react
- vite
Log in or sign up for Devpost to join the conversation.