ChatGPT-Mediated Materials and Assessment Design in an Omani EFL Foundation Programme: An Intelligent-TPACK Case Study

Generative artificial intelligence can accelerate English-as-a-foreign-language (EFL) materials and assessment design, yet its pedagogical value depends on teachers’ capacity to evaluate linguistic quality, contextual appropriateness, and ethical risk. This interpretive case study examined how five General Foundation Programme EFL teachers at Sohar University, Oman, used ChatGPT to prepare instructional materials and design assessments. Semi-structured interview data were analysed deductively in NVivo through the Intelligent-TPACK framework and Braun and Clarke’s six-phase thematic procedure. The teachers used ChatGPT to develop speaking and writing tasks, reading passages, vocabulary and grammar exercises, lesson ideas, and formative assessments. Effective use was described as an iterative process involving explicit prompts, proficiency-level specifications, learning outcomes, templates or tables of specifications, output checking, and prompt refinement. Participants valued efficiency, ideation, and adaptability, but reported concerns about inaccurate or unreliable content, weak coherence and authenticity, cultural inappropriateness, data privacy, academic integrity, overreliance, and the possible erosion of teacher and learner creativity. The study shows that productive teacher–AI interaction is not one-step automation but a cycle of pedagogical specification, linguistic validation, contextual adaptation, and ethical judgement. It recommends targeted professional development and institution-level guidance for responsible generative-AI use in language teaching and assessment.