Answers are grounded in this paper and cite their sources.
Students commonly rely on separate services for course browsing, question answering, quizzes, research drafting, textbook discovery, note sharing and scholarship search, which fragments the study workflow and leaves the reliability of each source for the learner to judge. This paper presents Dronacharya Hub, an AI-assisted modular web application that brings these workflows behind one interface. The system comprises eight modules: a learning tutor, a research studio, a location-aware book marketplace, a notes repository, a scholarship finder, a classroom and live-session hub, educational games, and AI summary and roadmap tools. They are implemented as feature-oriented Flask blueprints over a shared SQLAlchemy model layer with PostgreSQL and Supabase. Generative features call the Google Gemini API through a service boundary that validates input on the server before each call and checks the structure of returned content before display. Nearby books are ranked by the haversine great-circle distance computed from latitude and longitude. The paper documents the requirements, architecture, AI request pipeline, geospatial algorithm, security design and implementation, and presents interface captures of the running application with a worked distance example. Because the project artefacts contain no executed test log, no accuracy, latency or user-study figures are reported; a repeatable plan of 26 test cases and a measurement plan are specified instead. The contribution is a documented integration architecture for AI-assisted student services, and future work on automated testing, moderation, multilingual and offline support is outlined.
No takes yet. Share an insight, caveat, or question.
M et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: