🎓 Data Science Capstone Project

Learn Python &
Data Science,
one lesson at a time

DataLingo is an AI-powered learning platform that generates structured, beginner-friendly data science lessons with interactive MCQ quizzes and a built-in tutor chatbot.

🚀 Launch App Learn More

50+

Lessons

100+

Practice MCQs

Free

Forever

🔥 7 Day Streak!

https://datalingo-ucsd.vercel.app

Level 1: Fundamentals

Seeing the World Through Data

✓

Computational Tools

Completed

Statistical Techniques

In Progress ⭐

🔒

Why Data Science?

Locked

Lesson Progress 3/5 questions

🎯 About the Project

What is DataLingo?

⚡

The Problem

Creating quality data science learning content is labor-intensive and hard to scale. Beginners often lack structured, interactive, and affordable resources to get started.

💡

Our Solution

We built a full-stack pipeline that uses LLMs to generate structured lesson and quiz datasets, serves them through a FastAPI backend, and delivers them via a beautiful Next.js frontend with an AI tutor.

🎯

Who It's For

Absolute beginners who want to learn Python and Data Science through bite-sized, gamified lessons. Free, forever.

"Our goal is to reduce the manual effort of content creation while still giving learners a guided experience with quizzes and tutor-style explanations."

Intended Impact

A reproducible AI pipeline for generating lesson content, and a platform that makes that content usable for real learners. DataLingo demonstrates how generative AI can accelerate educational content creation without sacrificing quality.

⚙️ System Architecture

How DataLingo Works

A three-layer system that takes raw data science content and turns it into interactive lessons.

Data Collection

Raw data science content is collected and cleaned using Python scripts and Jupyter notebooks.

Python · Notebooks

AI Generation

n8n workflows apply LLM-based generation to transform content into structured lessons and MCQ datasets.

n8n · OpenAI · Supabase

Backend API

FastAPI loads the lesson JSON and exposes endpoints for lessons, questions, and a context-scoped tutor chat.

FastAPI · Python

Frontend App

Next.js renders lesson content, quizzes, and the embedded AI tutor widget for learners.

Next.js · React · Tailwind

✨ Key Features

Everything a beginner needs

DataLingo combines gamification, AI tutoring, and structured curriculum to make learning stick.

📚

Structured Lessons

Bite-sized, beginner-friendly lessons covering Python basics, statistics, and data science fundamentals, organized by topic and level.

🧩

Interactive MCQ Quizzes

Multiple-choice quizzes with difficulty ratings test your understanding after each lesson. Progress is saved automatically.

🤖

AI Tutor Chat

Stuck on a question? Ask the built-in tutor for hints, explanations, or breakdowns of each answer choice, without spoiling the answer.

🏆

Gamification

Streaks, XP points, locked levels, and daily goals keep learners motivated and coming back.

🔄

Reproducible Pipeline

Lesson content is generated via an automated n8n + LLM workflow inspired by academic research papers, making it easy to scale to new topics and difficulty levels.

🆓

Free Forever

DataLingo is completely free to use. No paywalls, no subscriptions, just learning.

🛠️ Tech Stack