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{196404,
        author = {kushal Sanjay Khune and Aditya Akankar and Shruti Mundhe and Sakshi kasurkar and Anjali Shegokar and Amit Patil},
        title = {LegalReach: A Multi-Tier AI-Augmented Platform for Democratizing Legal Consultation Access in India},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2889-2893},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196404},
        abstract = {Access to legal counsel in India is severely constrained by geographic barriers, opaque pricing, and the absence of a unified digital intermediary between citizens and legal professionals. Existing platforms address access and discovery but provide no integrated consultation workflow, document security, or AI-assisted guidance. This paper presents Legal Reach, a multi-tier web platform that unifies domain-constrained Retrieval-Augmented Generation (RAG) legal guidance, freemium-gated real-time chat, WebRTC peer-to-peer video consultation, and presigned cloud document storage within a single role-differentiated system. The RAG pipeline, built on FAISS vector search and a domain-limited system prompt, achieves 85% top-3 retrieval accuracy across four Indian statutes. All REST API operations except the RAG inference step satisfy a 300 ms P95 latency target. Security controls correctly reject 100% of tampered payment signatures and expire presigned URLs at the 15-minute boundary.},
        keywords = {FAISS vector search, Legal Tech, RAG, real-time consultation, Retrieval-Augmented Generation, Socket.io, WebRTC, legal access, AI-assisted legal guidance.},
        month = {April},
        }