An AI-supported E-mentoring model to develop EFL pre-service teachers' self-efficacy and emotional intelligence.

INTRODUCTION: This study investigated the effectiveness of an AI-supported e-mentoring model in enhancing self-efficacy and emotional intelligence among EFL pre-service teachers within the Egyptian practicum context. METHODS: Using a mixed-methods quasi-experimental design, 50 participants were assigned to an experimental group, which received structured mentoring, collaborative digital platform support (Facebook, Padlet, Nearpod, Google Classroom), and AI-driven feedback via Gemini, and a control group, which followed conventional practicum procedures. RESULTS: Quantitative results revealed substantial improvements in the experimental group's self-efficacy and emotional intelligence compared to the control group, while qualitative data indicated that participants shifted toward more student-centered, reflective, and adaptive teaching practices. DISCUSSION: The findings highlight the potential of integrating AI tools with structured mentoring and collaborative digital environments to create a continuous cycle of practice, feedback, and reflection. Implications for teacher education emphasize scalable, context-sensitive professional development that addresses both pedagogical and emotional competencies, particularly in under-resourced settings. Study limitations and directions for future research are also discussed.