M.

PAH - Graduate Policy AI

A Full-Stack RAG-based chatbot platform designed to help graduate students navigate complex university policies using OpenAI and real-time document management.

Source Live Demo

Overview

PAH is a specialized AI-powered platform designed to revolutionize how graduate students interact with institutional data. By leveraging Retrieval-Augmented Generation (RAG), the system transforms static university policy documents into a dynamic, conversational interface, ensuring students get accurate, context-aware answers in real-time.

My Role: Full-Stack AI Engineer

As the lead engineer, I was responsible for the end-to-end development of the AI architecture and the web infrastructure. This included building the RAG pipeline, designing the smart query classification system, and developing both the user-facing chat interface and the administrative control panel.

Key Features

  • 🤖 AI-Based FAQ System — Instant answers to common student inquiries using fine-tuned logic.
  • 📚 RAG Integration — Seamlessly retrieves information from uploaded policy documents to provide grounded AI responses.
  • 📂 Smart Document Management — An admin portal for real-time uploading and indexing of institutional PDFs and handbooks.
  • 🧠 Query Classification — Automatically categorizes user intent to route queries to the correct knowledge base or department.
  • 🛡️ Admin & User Portals — Distinct interfaces for students to chat and administrators to manage data and monitor system performance.

Tech Stack

  • AI/LLM: OpenAI API (GPT-4), LangChain / LlamaIndex
  • Frontend: React.js, Tailwind CSS
  • Backend: Node.js, Express.js / Python (FastAPI/Flask)
  • Database: MongoDB (User data) & Vector Database (Pinecone/Milvus for RAG)
  • Deliverables: Retrieval Augmented Generation, Full-Stack Development, Smart Query Classification

Why I Built This

Navigating university bureaucracy is notoriously difficult for graduate students. This project was built to replace dense, 100-page handbooks with a “smart assistant” that is adaptable to any institution. The automated RAG pipeline allows administrators to update policies on the fly without needing to retrain the underlying AI model.

Bridging the gap between students and policy with AI.