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{196447,
        author = {vedika devang parikh and Karina Pandav and Parineeta Rao and Pankaj Deshmukh},
        title = {SuvidhaAI: A Dual-Mode Intelligent Welfare Navigation Platform for Indian Citizens},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4885-4894},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196447},
        abstract = {India hosts over 500 active central and state-level welfare programmes; however, a significant proportion of eligible citizens fail to access these benefits due to awareness deficits, eligibility confusion, and application complexity. Existing platforms such as UMANG and MyScheme.gov.in provide scheme catalogues but lack personalised eligibility assessment and guided application support, especially for users with low literacy and limited English proficiency. This paper presents SuvidhaAI, a voice-first, multilingual, dual-mode intelligent web application designed to address these challenges. The system introduces two interfaces: Simple Mode, a conversational WhatsApp-style interface for low-literacy users, and Full Mode, a professional dashboard for CSC operators and assistants. Key features include multilingual scheme matching, visual document verification, application letter generation, progress tracking, and geolocation-based service centre access. Comparative evaluation shows that SuvidhaAI delivers capabilities absent in existing platforms. The paper also outlines a scalable architecture incorporating semantic search, FastAPI, PostgreSQL, Redis, and speech recognition technologies.},
        keywords = {e-governance, welfare scheme recommendation, voice-first interface, multilingual NLP, citizen-centric AI, digital inclusion.},
        month = {April},
        }