Calcyon: Design and Validation of an AI-Based Chatbot Framework Integrating Computational Thinking and Self-Regulated Learning in University Calculus Learning

Background The integration of artificial intelligence (AI) into mathematics education has advanced rapidly; however, systematic AI-based chatbot frameworks that integrate computational thinking (CT) and self-regulated learning (SRL) scaffolding within university calculus remain limited. This study developed and formatively evaluated Calcyon, an AI-based chatbot framework designed to integrate CT processes and SRL scaffolding within university differential calculus learning. Methods A Design and Development Research (DDR) approach guided by the ADDIE model was employed, focusing on the design, development, and formative evaluation stages. Expert evaluation (n = 3) was conducted across five design dimensions using Aiken’s V to examine content and design validity. A formative student pilot study (n = 11) was conducted to evaluate prototype readability and feasibility across six dimensions. Results Expert evaluation indicated strong expert-rated design and content validity across content, instructional, technical, linguistic, and media design dimensions (Aiken’s V = 0.92). Most items met the predefined criterion, while several revisions were incorporated based on expert feedback. The student pilot indicated good readability and feasibility of the prototype. Conclusions Calcyon provides an empirically evaluated AI-based chatbot framework that integrates AI-mediated interaction, CT-oriented scaffolding, and multidimensional SRL design principles within university calculus learning. The findings provide evidence of framework quality and feasibility; however, they do not establish the effectiveness of Calcyon in improving CT, SRL, or calculus learning outcomes. Further empirical studies are required to examine its instructional effectiveness.