Soojal Kumar
Back to Projects

2026

CampusStudy AI

University-focused AI study platform with RAG, web, mobile, backend, workers, and study workflows.

CampusStudy AI is a university-focused AI study platform designed to help students organize learning, generate study support, and interact with AI-powered academic workflows. The project combines a modern frontend, FastAPI backend, worker-based processing, and retrieval-augmented generation concepts to support scalable study experiences.

TypeScriptFastAPIRAGAIWebMobileWorkers

Generated from project structure

AI Study Platform Concept

CampusStudy AI study dashboard visual

Study Planner

AI Assistant

RAG Search

Mobile App

Highlight

AI Study Workflows

Highlight

RAG Architecture

Highlight

Web + Mobile Platform

Highlight

FastAPI Backend

Executive Summary

CampusStudy AI is a university-focused AI study platform designed to help students organize learning, generate study support, and interact with AI-powered academic workflows. The project combines a modern frontend, FastAPI backend, worker-based processing, and retrieval-augmented generation concepts to support scalable study experiences.

Problem Statement

Students often use disconnected tools for notes, assignments, study planning, and AI assistance. CampusStudy AI aims to bring these workflows into a unified academic platform with structured study support and intelligent retrieval.

What I Built

AI study workflows

RAG-style learning assistance

Backend workers

Web and mobile platform planning

How It Works

A conceptual workflow showing how the project moves from input to processing and output.

Step 1

Student Uploads / Study Input

Step 2

RAG Retrieval

Step 3

AI Study Assistant

Step 4

Generated Study Output

Step 5

Saved Workflow

Architecture / System Design

A simplified system view of the major project components and how responsibilities connect.

Step 1

Web App / Mobile App

Step 2

FastAPI Backend

Step 3

RAG Layer

Step 4

Worker Queue

Step 5

Study Data / Documents

Technical Implementation

Frontend

  • TypeScript interface planning
  • Web and mobile study flows
  • Minimal academic dashboard patterns

Backend

  • FastAPI service layer
  • Study workflow endpoints
  • Structured backend responsibilities

AI Layer

  • RAG-style retrieval
  • Context-aware study assistance
  • Academic content grounding

Workers

  • Background processing
  • Async study tasks
  • Pipeline-ready architecture

Screenshots & Visuals

Real project screenshots and outputs appear first. Where a project has no existing screenshots, the visuals are grounded diagrams or output previews based on the actual project structure.

CampusStudy AI study dashboard visual
DiagramGenerated from project structure

Study Dashboard Preview

Grounded dashboard visual based on the real CampusStudy AI web/mobile routes for study planning, materials, AI assistance, and course context.

CampusStudy AI retrieval augmented generation workflow
WorkflowGenerated from project structure

RAG Retrieval Flow

Workflow diagram based on the implemented retrieval, chunking, citation, and generation service structure in the CampusStudy AI backend.

CampusStudy AI FastAPI and worker pipeline
ArchitectureGenerated from project structure

Background Worker Pipeline

Architecture visual grounded in the FastAPI services and Celery worker tasks used for extraction, processing, and study output generation.

Challenges & Solutions

Challenge

Students often use disconnected tools for study planning, notes, and AI help.

Solution

Designed a unified academic platform concept with AI workflows and retrieval-based assistance.

Challenge

AI output needs context from course material to be useful in an academic workflow.

Solution

Structured the system around a RAG-style retrieval layer that connects responses with study content.

Results / Impact

Demonstrates practical software engineering through modular structure, readable workflows, and clear technical documentation.

Shows ability to convert course and research concepts into working systems with real implementation constraints.