<![CDATA[The purpose of this study is to describe the challenges faced by junior high school English teachers in formulating learning theory-based prompts in ChatGPT. This study employed a qualitative approach with a descriptive research design. The informants were English teachers who teach at SMP Negeri 2 Rote Barat Laut. The subjects of the research were selected using purposive sampling technique, in which they were deliberately selected based on specific criteria considered relevant by the researcher. The supporting instruments used in this study were an interview guide and a documentation sheet. The findings showed that English teachers had regularly integrated ChatGPT to support instructional planning and administrative tasks, such as developing lesson plans/teaching modules, learning materials, activities, questions, test blueprints, and assessment rubrics. However, the teachers’ understanding of prompt engineering, particularly in relation to learning theory, remained limited to the basic functions of prompts. The teachers experienced difficulties in specifically integrating learning theories, instructional objectives, context, and learner characteristics into prompts. In addition, the teachers were familiar with several prompt components, such as role, context, and output format, but their use of these components was not yet consistent or systematic. These findings indicate that although teachers’ practical ability to use ChatGPT has developed, their ability to formulate learning theory-based prompts still needs to be strengthened comprehensively, particularly in integrating pedagogical knowledge with prompt structures and strategies.]]>
