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{187255,
        author = {Ishan Srivastav and Priyanshu Kumar Singh and Aditya Jaswal},
        title = {BrillX: An Architecture for Dynamic Learning Paths},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4229-4239},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187255},
        abstract = {BrillX is a comprehensive Software-as-a-Service (SaaS) learning platform designed to revolutionize digital education through modern web technologies and artificial intelligence integration.[1] The platform integrates secure authentication, responsive frontend interfaces (HTML5, CSS3, JavaScript), and a robust backend powered by Node.js, Express.js, and MongoDB.[2][3] The system incorporates an AI-driven mentor powered by large language models, a PDF chatbot utilizing semantic embeddings and cosine similarity, and a dynamic quiz generation system leveraging prompt engineering.[4][5] The platform implements twelve key machine learning algorithms including Q-learning for content sequencing, Sentence Transformer embeddings for semantic matching, gradient boosting for performance prediction, and token-based streaming for real-time response delivery.[6][7] The architecture follows cloud-native SaaS principles with comprehensive security measures including AES-256 encryption, role-based access control, and WCAG 2.1 Level AA accessibility compliance.[1][2] Performance metrics demonstrate responsive user interfaces with sub-2-second page loads, AI mentor response latency of 1.2 seconds with 92% contextual accuracy, and PDF chatbot retrieval accuracy of 87%.[8] This research demonstrates the feasibility of integrating modern web technologies with AI capabilities to create production-grade adaptive learning systems addressing contemporary educational challenges.[1]},
        keywords = {Adaptive Learning, Item Response Theory, Machine Learning, Educational Technology, SaaS Platform, Personalized Education, Artificial Intelligence, Accessibility, Intelligent Tutoring Systems},
        month = {November},
        }