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{200844,
        author = {Ashish Bhosle and Yeshas AB Naik and Bhavesh VS and Prateesh},
        title = {Developing an AI-based bot/virtual assistant for the Department of Justice},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2973-2976},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200844},
        abstract = {We present the DoJ Virtual Assistant, a safety-first, document-retrieval virtual assistant designed to provide grounded information for judicial documents. The implementation combines a deterministic keyword-retrieval index, an NLP safety layer that refuses personal legal advice, and optional integrations for cloud LLM synthesis and text-to-speech. We describe the architect ure, implementation artifacts, a small reproducible retrieval experiment on repository files, and deployment recommendations for public-sector contexts. All claims are grounded in repository inspection; no fabricated experimental claims are made.},
        keywords = {Legal NLP, Retrieval-Augmented Generation, Document Retrieval, Safety, Judicial AI},
        month = {May},
        }