Acadbot: AI-Driven Automation of Academic Services

Abstract

Accessing timely and accurate information in academic institutions is often challenging, as students, faculty, and administrators struggle to locate dynamic data such as event schedules, meeting details, and academic notifications, which are typically scattered across multiple systems. Traditional university portals lack intuitive, centralized, and fast query mechanisms, leading to inefficiency, delays, and user dissatisfaction. To address this issue, we present Acadbot, a full-stack web application built using the MERN (MongoDB, Express, React, Node.js) stack, offering a unified and user-friendly dashboard for managing academic information, supported by a secure Role-Based Access Control (RBAC) system that ensures proper authorization for different user groups. The core innovation of this project is its lightweight, database-driven AI chat assistant, which deviates from conventional systems that depend on large vector embeddings, FAISS indexes, and separate retrieval pipelines. Instead, Acadbot employs a practical heuristic-based retrieval engine that performs case-insensitive, token-based, and typo-tolerant regex searches directly on the live MongoDB database. By querying real-time operational data rather than relying on preprocessed vector stores, the system reduces complexity and avoids issues related to outdated or unsynchronized information. This approach enables Acadbot to deliver fast, accurate, and context-aware responses tailored to academic environments. The paper further discusses the system architecture, the implementation of the heuristic retrieval algorithm, and the benefits of adopting this efficient approach for domain-specific academic chatbots. Keywords: MERN Stack, AI Chatbot, Academic Portal, Heuristic Retrieval, Information Retrieval, Role-Based Access Control (RBAC).