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{203337,
        author = {Yash Sushil Zope and Vishal Natha Sukale and Yash Sandip Kakade and Khushi Arvind Tiwari and Prof. Saba Chaugule},
        title = {AI-Driven Control Mapping and Evidence Analyzer: System Implementation and Evaluation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10901-10908},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203337},
        abstract = {This paper presents the complete technical implementation of the AI-Driven Control Mapping and Evidence Analyzer introduced in our earlier work. The system was developed across four structured phases, resulting in a full-stack application with a Django backend, a React frontend, and an integrated AI pipeline. The pipeline combines semantic embeddings, vector-based similarity search over the complete ISO/IEC 27001:2022 Annex A control set, retrieval-augmented generation, and large language model inference to automate compliance assessment end to end. A single master analysis service orchestrates the entire workflow, from policy document ingestion through control mapping, evidence validation, automatic risk identification, and auditor report generation without any manual intervention. The results validate the feasibility of AI-driven ISMS compliance automation and demonstrate a measurable reduction in manual audit effort.},
        keywords = {Compliance Automation, Django REST Framework, FAISS Vector Search, Groq LLM, ISO/IEC 27001:2022, LangChain, Retrieval-Augmented Generation, React, Risk Register, SBERT, Full-Stack Implementation.},
        month = {May},
        }