Denis Federiakin ^1* Dimitri Molerov ^1,2 Olga Zlatkin-Troitschanskaia ¹ Andreas Maur ¹

• ¹ Department of Business and Economics Education, Johannes Gutenberg University Mainz, Mainz, Germany
• ² Department of Educational Science Methodology, Humboldt University of Berlin, Berlin, Baden-Wurttemberg, Germany

Artificial Intelligence (AI) promises to revolutionize nearly every aspect of human learning. However, users have observed that the efficacy of AI assistants hinges crucially on the quality of the prompts supplied to them. A slight alteration in wording can make the difference between an assistant misinterpreting an instruction and exceeding expectations. The skill of precisely communicating the essence of a problem to an AI assistant is as crucial as the assistant itself. This paper aims to introduce Prompt Engineering (PE) as an emerging skill essential for personal and professional learning and development in the 21st century. We define PE as the skill of articulating a problem, its context, and the constraints of the desired solution to an AI assistant, ensuring a swift and accurate response. We show that no existing related frameworks on 21st skills and others cover PE to the extent that allows for its valid assessment and targeted promotion in school and university education. Thus, we propose a conceptual framework for this skill set including (1) comprehension of the basic prompt structure, (2) prompt literacy, (3) the method of prompting, and (4) critical online reasoning. We also discuss the implications and challenges for the assessment framework of this skill set and highlight current PE-related recommendations for researchers and educators.