Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203272,
        author = {Sanket Shewalkar and Sahil Kulkarni and Pratham Kokardekar and Kunal Pawar and Jitendra Chavan},
        title = {EaseOS: An AI-Powered Workplace Assistant for Hybrid Enterprises Using Retrieval-Augmented Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10863-10868},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203272},
        abstract = {Modern enterprises apply a variety of tools for policies, communication support, scheduling, employee services. Each tool addresses a specific problem, but fragmented work-flows hinder response time and productivity. In this paper, we describe the design, implementation, and performance evaluation of EaseOS, a unified enterprise assistant that integrates Retrieval-Augmented Generation (RAG), role-aware access control, document intelligence, analytics, and voice-ready interaction. The implemented platform is based on MERN architecture with a React frontend, Node.js and Express backend services, MongoDB for operational data, and a vector index for semantic retrieval. Our proposed pipeline converts uploaded enterprise documents into searchable embeddings, and then generates grounded responses by combining the context of the query with the retrieved evidence. We evaluate EaseOS on simulated enterprise workloads, and against a keyword-search baseline. Results show improved response relevance, decreased mean latency, improved context continuity and improved voice-query success rates. The results show that a modular RAG-first assistant can enhance enterprise knowledge access with scalability and operational simplicity.},
        keywords = {Retrieval-Augmented Generation, Enterprise Assistant, MERN Stack, Semantic Search, Workplace Automation, Conversational AI.},
        month = {May},
        }