Sahayak AI: Adaptive Intelligence for Teaching and Learning

Abstract

Education in India often faces challenges such as limited resources, overcrowded classrooms, and unequal access to quality learning. Sahayak AI is an intelligent teaching and learning assistant designed to support both teachers and students in such low-resource, multi-grade environments. The system integrates artificial intelligence, natural language processing (NLP), and immersive technologies to create an adaptive micro-learning experience. Teachers can generate lesson plans, assessments, and interactive content using an AI-powered assistant, while students receive personalized learning paths based on their progress and understanding. The platform uses React.js and Node.js for its scalable architecture, Firebase for efficient data handling, and LangChain.js with Gemini API for generative AI capabilities. In addition, WebXR modules enable VR and AR-based educational content, enhancing engagement and conceptual understanding. Preliminary evaluations indicate improved student motivation and teacher productivity. This paper discusses the system’s architecture, key modules, implementation strategy, and its potential impact on accessible and adaptive digital education.

Introduction

Summary

The Indian education system faces major challenges, including large student populations, linguistic diversity, multi-grade classrooms, limited teacher availability, and unequal access to digital resources—especially in rural and government schools. Existing AI-based educational platforms often focus on high-resource, urban settings and lack contextual adaptability, multilingual support, teacher assistance, and immersive learning integration.

To address these gaps, Sahayak AI is proposed as an intelligent teaching assistant and adaptive learning platform tailored for the Indian education ecosystem. Designed for low-resource and multi-grade classrooms, it combines AI-driven personalization, natural language processing (NLP), and immersive VR/AR technologies to enhance both teaching and learning experiences.

The system follows a modular three-tier architecture:

• Frontend Layer (React.js): Provides separate dashboards for teachers and students.

• Backend Layer (Node.js, Express.js, Firebase): Manages authentication, data storage, analytics, and cloud hosting.

• AI Integration Layer (LangChain.js + Gemini API): Generates personalized lesson plans, quizzes, summaries, and adaptive learning pathways.

WebXR integration enables immersive VR/AR learning experiences accessible through affordable devices. Firebase ensures secure, scalable, and real-time data synchronization, even in low-bandwidth environments.

Key features include AI-powered lesson planning, multilingual content generation, adaptive learning paths, immersive simulations, performance analytics, and cloud-based accessibility with offline support.

Pilot simulations showed promising results:

• Students achieved 15–20% higher assessment scores using adaptive AI content.

• Teachers reduced lesson planning time by 30–40%.

• Engagement increased significantly through VR/AR modules.

Overall, Sahayak AI presents an innovative, scalable, and inclusive EdTech solution that integrates adaptive learning, teacher support, and immersive technologies to address the unique challenges of multi-grade, resource-constrained classrooms in India.

Conclusion

Sahayak AI presents an innovative approach to addressing the challenges of multi-grade and resource-constrained classrooms in India. By integrating artificial intelligence, adaptive learning algorithms, and immersive technologies, the platform delivers personalized learning experiences while simultaneously supporting teachers through AI-assisted content generation and real-time analytics. Pilot evaluations indicate improvements in student engagement, comprehension, and assessment performance, as well as significant reductions in teacher workload. The system’s cloud-based architecture, powered by Firebase, ensures secure, scalable, and accessible deployment, even in low-connectivity environments.

References

[1] S. M. Metev and V. P. Veiko, Laser Assisted Microtechnology, 2nd ed., R. M. Osgood, Jr., Ed. Berlin, Germany: Springer-Verlag, 1998. [2] J. Breckling, Ed., The Analysis of Directional Time Series: Applications to Wind Speed and Direction, ser. Lecture Notes in Statistics. Berlin, Germany: Springer, 1989, vol. 61. [3] S. Zhang, C. Zhu, J. K. O. Sin, and P. K. T. Mok, “A novel ultrathin elevated channel low-temperature poly-Si TFT,” IEEE Electron Device Lett., vol. 20, pp. 569–571, Nov. 1999. [4] M. Wegmuller, J. P. von der Weid, P. Oberson, and N. Gisin, “High resolution fiber distributed measurements with coherent OFDR,” in Proc. ECOC’00, 2000, paper 11.3.4, p. 109. [5] R. E. Sorace, V. S. Reinhardt, and S. A. Vaughn, “High-speed digital-to-RF converter,” U.S. Patent 5 668 842, Sept. 16, 1997. [6] (2002) The IEEE website. [Online]. Available: http://www.ieee.org/ [7] M. Shell. (2002) IEEEtran homepage on CTAN. [Online]. Available: http://www.ctan.org/tex-archive/macros/latex/contrib/supported/IEEEtran/ [8] FLEXChip Signal Processor (MC68175/D), Motorola, 1996. [9] “PDCA12-70 data sheet,” Opto Speed SA, Mezzovico, Switzerland. [10] A. Karnik, “Performance of TCP congestion control with rate feedback: TCP/ABR and rate adaptive TCP/IP,” M. Eng. thesis, Indian Institute of Science, Bangalore, India, Jan. 1999. [11] J. Padhye, V. Firoiu, and D. Towsley, “A stochastic model of TCP Reno congestion avoidance and control,” Univ. of Massachusetts, Amherst, MA, CMPSCI Tech. Rep. 99-02, 1999. [12] Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specification, IEEE Std. 802.11, 1997.

Copyright

Copyright © 2026 Ganesh Rodge, Harsh Gawali, Shravani Velse, Madhura Shirsath. This 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.