DEVELOPMENT OF AI-BASED LEARNING MEDIA ON NETWORK CONFIGURATION MATERIAL IN COMPUTER AND NETWORK ENGINEERING DEPARTMENT OF VOCATIONAL HIGH SCHOOL This study aims to develop, and to test the feasibility, practicality, and effectiveness of AI-based learning media using Canva AI on network configuration material in the Computer and Network Engineering (TKJ) department of Vocational High School. The background of this research is the limitation of learning media used at SMKN 1 Braja Selebah, which still relies on printed modules and simple slides, making it difficult for students to deeply understand network configuration procedures. The research used the Research and Development (R&D) method with the ADDIE development model, covering Analysis, Design, Development, Implementation, and Evaluation stages. Research subjects were 66 grade X TKJ students divided into experimental and control classes. Instruments used included expert validation questionnaires for media and content, teacher and student response questionnaires, and pretest and posttest questions. Results showed that Canva AI-based learning media received a feasibility percentage of 89.6% from media experts and 83.3% from material experts, both categorized as very feasible. The practicality level based on teacher responses reached 87.3% and student responses 83%, both categorized as very practical. The effectiveness test showed that the posttest scores of the experimental class (81.2) were higher than the control class (72.3), with an independent sample T-test significance of 0.003 and an effect size of 0.773. It was concluded that Canva AI-based learning media is feasible, practical, and effective in improving student learning outcomes in network configuration material.