K. M. Ravi Kumar1, M. Satyanarayana2, T. Avinash3, G. Rama Devi4, N. Swaroop5, V. Balaji Varma6 03 3(1) Academic institutions face a persistent challenge in delivering timely accurate and personalised academic support to large and growing student populations Conventional Learning Management System LMS platforms store considerable volumes of course materials yet lack conversational contextaware assistance Existing AI chatbots that rely exclusively on pretrained Large Language Models LLMs frequently produce hallucinated or curriculummisaligned responses eroding student trust This paper presents Student Ease an Androidbased AI powered college helpdesk chatbot that integrates RetrievalAugmented Generation RAG with an LMS backend The system ingests institutional documentslecture notes assignment sheets and discussion archivesconverts them into semantic vector embeddings stored in a FAISS index and retrieves the most relevant chunks before passing them to an LLM for grounded answer synthesis A personalization engine tracks each students query history and learning gaps to provide targeted study recommendations and deadline reminders System evaluation achieved a Grounded Accuracy of 946 a Citation Precision of 918 a Retrieval Relevance Score of 894 and reduced the hallucination rate from 27 pure LLM to 6 RAGenhanced The FlutterFirebase mobile frontend offers rolebased access for students and administrators Results confirm that combining semantic retrieval with LLM generation substantially outperforms pure LLM baselines in academic helpdesk scenarios Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026