Web App
A high-performance, full-stack ChatGPT clone designed as a specialized AI Assistant for institutional policies. It leverages modern web technologies and advanced AI orchestration to provide users with an intuitive chat interface capable of retrieving and reasoning over complex university or organizational documentation.
A policy expert that never has to guess.
Answers grounded in the actual handbook.
Every reply is retrieved from institutional policy documents in ChromaDB before generation, and LangGraph keeps conversation state in PostgreSQL so follow-up questions carry context. Where a general model would improvise, this one cites.
Purpose
Serves as an "Institutional Policy Specialist." Unlike general-purpose LLMs that may hallucinate or lack specific internal data, this clone uses Retrieval-Augmented Generation (RAG) to ensure responses are grounded in actual policy documents. It is designed to help students, faculty, and staff navigate institutional rules with precision, conciseness, and accuracy.
Key Features
AI Agent with Memory
LangGraph manages conversation state for multi-turn dialogues with context retention.
Semantic Search (RAG)
ChromaDB vector searches across policy documents for accurate, evidence-grounded responses.
Policy-Specific Tools
Specialized tools for searching, listing, retrieving, and summarizing institutional policies.
Persistent Chat History
Messages and threads saved to PostgreSQL for returning to previous conversations.
Feedback System
Built-in mechanism for rating AI responses with LangSmith monitoring for quality assurance.
Modern UX
Responsive, dark-mode-first UI with message streaming and sidebar navigation.
Tech Stack