Artificial Intelligence‐Critical Pedagogic: Design and Psychologic Validation of a Teacher‐Specific Scale for Enhancing Critical Thinking in Classrooms

ABSTRACT Background Critical thinking is essential in modern education, and artificial intelligence (AI) offers new possibilities for enhancing it. However, the lack of validated tools to assess teachers' AI‐integrated pedagogical skills remains a challenge. Objectives The current study aimed to develop and validate the Artificial Intelligence‐Critical Pedagogy Scale (AICPS) to measure teachers' ability to use AI in fostering critical thinking. Methods This study was conducted in Saudi Arabia and consisted of two phases. Phase 1 involved item development through a literature review and semi‐structured interviews with 17 secondary school teachers, leading to an initial pool of 100 items. After expert reviews and a pilot study, the scale was refined to 47 items. Phase 2 evaluated the psychometric properties of the scale through exploratory factor analysis (EFA), confirmatory factor analysis (CFA), exploratory graph analysis (EGA), reliability assessments and measurement invariance testing across gender. The final sample included 800 secondary school teachers. Results and Conclusions EFA confirmed a four‐factor structure with 39 items. The four factors were Competence in Creating Critical Thinking‐Oriented Learning Environments (CCCTOLE), Ability to Provide Dynamic and Innovative Feedback (APDIF), Understanding and Interaction with Emerging Learning Technologies (UIELT) and Creativity in Designing Transformative Learning Activities (CDTLA). CFA demonstrated a good model fit ( χ 2 /df = 3.24, RMSEA = 0.075, CFI = 0.916 and TLI = 0.909). EGA further supported the four‐factor structure. Internal consistency was excellent, with Cronbach's alpha and McDonald's omega above 0.70 for all subscales. Measurement invariance testing confirmed that the scale functions equivalently across gender groups. The AICPS is a reliable and valid tool for assessing teachers' AI‐based critical pedagogy skills. Its demonstrated gender invariance suggests its applicability across diverse educational contexts. This scale can guide future teacher training and policy decisions in AI‐driven education.