PROMPT-ENGINEERING AS AN INTELLECTUAL EDUCATIONAL TECHNOLOGY
TL;DR
The findings indicate that the effectiveness ofAI-assisted teaching largely depends on educators’ digital competence, their ability to critically evaluate AI-generated content, verify the reliability of information, verify the reliability of information, and comply with the principles of academic integrity.
Abstract
The article explores prompt engineering as an emerging intelligent educational technology shaped by the rapid advancement of generative artificial intelligence and the digital transformation of higher education. The relevance of the study is determined by the need to reconsider the role of university teachers in the context of the active integration of artificial intelligence into the educational process, the necessity to develop new professional competencies, enhance digital literacy, foster critical thinking, and ensure academic integrity when using generative AI systems. The study is based on the methods of theoretical analysis, synthesis, comparison, systematization, and generalization of contemporary scientific literature, international research findings, and national and international policy documents addressing artificial intelligence in education, digital pedagogy, and prompt engineering. Particular attention is devoted to the advantages and potential risks associated with the educational use of generative artificial intelligence. The findings indicate that the effectiveness ofAI-assisted teaching largely depends on educators’ digital competence, their ability to critically evaluate AI-generated content, verify the reliability of information, and comply with the principles of academic integrity. The study emphasizes that prompt engineering should not be regarded as a replacement for the teacher’s professional expertise but rather as an effective instrument for enhancing teaching quality when applied responsibly and pedagogically. The article proposes a comprehensive algorithm for designing high-quality educational prompts consisting of nine interconnected stages: defining the professional role, identifying the target audience, setting educational objectives, specifying the instructional context, formulating the task, designing the response structure, establishing output requirements, selecting the response format, and defining evaluation criteria. Practical pedagogical recommendations for implementing each stage in higher education teaching are provided. The practical significance of the study lies in the possibility of integrating the proposed algorithm and educational prompt models into university teaching practice, professional development programs for academic staff, and the preparation of future educators. The proposed approaches may contribute to improving teaching methodology, developing contemporary educational resources, and strengthening the digital competence of higher education teachers in the context of the widespread implementation of artificial intelligence technologies.