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{204040,
        author = {Saanika Wani and Spoorthi Gumgol and Shreeya Rajurikar and Piyush Kale and Prof. Mrs. Priyanka Deshpande},
        title = {PyAI: An LLM-Driven AI Mentor for Personalized and Optimized Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1844-1856},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204040},
        abstract = {This paper presents the design and implementation of PyAI, an AI-driven, gamified programming education platform built for beginner-to-intermediate learners, with a primary focus on students aged 8–16. PyAI combines a React-based single-page application, a Supa base-hosted backend for authentication and persistent content storage, an interactive coding environment for hands-on Python practice, and an in-application AI Mentor character that delivers contextual feedback and motivational guidance during the learning process. The platform delivers structured Python courses through a hierarchical content model (courses, units, topics, lessons, and tests) stored in Supa base and retrieved dynamically at runtime. A skill-assessment evaluation module places students into ap-propriate learning tiers before enrollment. An adaptive progress system implemented in React Context tracks per-lesson accuracy using a rolling average and adjusts the difficulty label assigned to each student’s next attempt. A separate Mentor Dashboard, powered by the Recharts library, gives instructors a real-time view of class-level XP accumulation, topic mastery, and individual student progress. Preliminary evaluation with a student cohort shows improvements in task completion rate and self-assessed comprehension over a static learning alternative. This work demonstrates the feasibility of building a functional, deployable AI-assisted coding education platform using a modern frontend stack with a managed backend-as-a-service provider.},
        keywords = {AI Mentor, Coding Education, Supa base, Adaptive Learning, Gamification, React, Intelligent Tutoring, Python Education, PyAI.},
        month = {June},
        }