Prompt Engineering in English Language Teaching: Theory and Practice

The article presents the concept of “prompt engineering” as an important component of modern practice of interaction with artificial intelligence (AI) models, especially in educational and teaching and learning environments . A brief historical overview into the development of AI technologies and the gradual formation of the art of Prompt Engineering, the main goal of which is to obtain the most relevant and accurate response of an AI model through correctly written instructions, is proposed . Key concepts related to Prompt Engineering are formulated and its features are highlighted as a new interdisciplinary tool located at the intersection of linguistics, pedagogy, cognitive psychology and information technology . Special attention is paid to the process of creating effective prompts (queries), rules of their construction, common mistakes and techniques of their writing taking into account the goals of learners (users) and the nature of the task . The theoretical part is accompanied by detailed practical examples of using these techniques and their combinations in teaching a foreign language at non-language universities . The article describes a step-by-step algorithm that allows to adapt a large amount of educational material for the purposes of interim or final certification in the discipline “English for professional purposes”, including the generation of texts of different levels of lexical and grammatical complexity, mental maps and means of self-control . The article contains practical recommendations for organising independent work with AI models for students with different levels of language proficiency, motivation, chosen learning strategy and intellectual readiness for learning . It concludes with the results of the application of the described prompt-engineering techniques and analyses their potential impact on the quality of learning, achievement, engagement and development of learners’ linguistic independence.

1. Ursula K. Le Guin. The Left Hand of Darkness. NY: Ace, 2000. 367 p.

2. John W. Tukey. The future of data analysis. The Annals of Mathematical Statistics. 1962;33(1):1–67. URL: http://www.mat.ufrgs.br/~viali/estatistica/mat2274/material/textos/2237638.pdf

3. Harma R. C., Bozkurt A. Transforming education with generative AI: Prompt engineering and synthetic content creation. IGI Global; 2024. URL: https://www.researchgate.net/publication/378066821_Transforming_Education_With_Generative_AI_Prompt_Engineering_and_Synthetic_Content_Creation

4. Stuart Russell, Peter Norvig. Artificial intelligence: A modern approach. Pearson; 2009:11152 p. URL: https://api.pageplace.de/preview/DT0400.9781292401171_A41586057/preview-9781292401171_A41586057.pdf

5. Fengchun Miao, Wayne Holmes. Guidance for generative AI in education and research. UNESCO. 2023: 44 p. URL: https://www.downes.ca/files/docs/UNESCO_Gen_AI_Guidelines_2023.pdf

6. Bernstein David Scott. Prompt engineering for everyone: A comprehensive guide to unlock the potential of ChatGPT and AI-language models. Passionate Programmer; 2023. p. 314.

7. Lukinsky I.S., Gorsheneva I.A. Promt engineering in the educational process and scientific activity or to the question of the necessity of training to work with artificial intelligence. Psychology and pedagogy of service activity. 2024;(4):148–154. (In Russ.). DOI: 10.24412/2658–638Х-2024–4–148–154

8. Osmolovskaya I.M. Differentiated learning: some issues of theory and practice. Bulletin of TSPU. 1999;5(14):6–12. URL: https://vestnik.tspu.ru/files/vestnik/PDF/articles/Osmolovskaya_I._M._6_12_5_14_1999.pdf (In Russ.).

9. Savchenko Yu.Y. Higher professional education services as a commodity and a public good. Modern problems of science and education. 2014;(3). URL: https://www.elibrary.ru/syzodp (In Russ.).

10. D. Hume. A Treatise of human nature. Dover publications; 2003. p. 480.