All projects

Project 05, AI and education

StudySetu.

A prototype that finds what each student missed after a lecture, and builds a short revision session around it.

StudySetu review screen after a diagnostic quiz, showing chosen and correct answers with reasoning
The review screen after a five-question diagnostic.
Event
TetraTHON 2026, Indo-French AI Innovation Sprint
Stage
Selection-round project
Status
Working prototype
Users
Students, teachers, admins

01, The idea

The teacher teaches. StudySetu checks that it stuck.

StudySetu is a revision companion, not a replacement for the teacher. Teachers build the curriculum, and their own material grounds everything the system produces.

AI writes the questions and lessons, and no AI-generated item reaches a student until a teacher approves it.

02, How it works

Diagnose first, then revise.

  1. Diagnose

    The first time a student opens a topic, a five-question probe checks what they already know.

  2. Track mastery

    Bayesian Knowledge Tracing, a simple statistical model of whether a skill is learned, updates after every answer.

  3. Revise

    A short session is built from what the probe found, with a doubt chat grounded in the lesson itself.

  4. Review

    Teachers approve AI content and see which misconceptions are common across the class.

03, Screens

Built for three kinds of users.

Teacher analytics showing average mastery, completion and misconceptions per topic
Teacher analytics, with mastery and misconceptions per topic.
  • A personalised lesson card with a doubt chat box below it

    A personalised lesson, with the doubt chat underneath.

04, Engineering

How it is built.

  • One AI gateway. Every AI call goes through one gateway with automatic failover across four providers.
  • Safe deployments. Docker Compose and a GitHub Actions pipeline that rolls back a failed deployment.
  • Prototype stage. It was built for a hackathon round and is not a finished product.

Built with

  • React 18
  • TypeScript
  • Vite
  • FastAPI
  • PostgreSQL
  • pgvector
  • Docker
  • GitHub Actions