Prompt engineering as a tool for improving the learning process of foreign languages
DOI: 10.23951/2307-6127-2026-1-46-55
Prompt engineering is increasingly recognized as a pivotal tool for optimizing the foreign language learning process in the context of digital transformation in education. As artificial intelligence (AI) becomes deeply integrated into educational environments, large language models (LLMs) such as GPT, Claude, and Gemini offer unprecedented opportunities for personalized, interactive, and adaptive language instruction. However, the effectiveness of these technologies is not inherent in the models themselves, but critically depends on the user’s ability to formulate clear, structured, and contextually appropriate prompts. This article explores prompt engineering as a metacognitive and pedagogical skill essential for maximizing the educational potential of AI. It analyzes key prompting strategies – zero-shot, oneshot, and few-shot prompting – and demonstrates their differential effectiveness across proficiency levels (A2–C1), with few-shot prompting proving particularly valuable for complex tasks such as grammatical explanations and academic writing. The study identifies five core applications of AI in language education: the generation of authentic texts and dialogues, individualized grammar instruction, creation of tailored exercises, oral practice through AI-driven text and voice interactions, and immediate, detailed feedback on written assignments. Drawing on pilot teaching sessions and original methodological developments, the article presents a comparative analysis of basic versus optimized prompts, revealing a substantial improvement in the relevance, accuracy, and pedagogical value of AI-generated responses when prompt engineering principles are applied. Practical recommendations are proposed for integrating prompt engineering into the curriculum through a four-stage framework: introduction, modeling, practice, and reflection. Furthermore, the article addresses critical ethical considerations, including issues of authorship, academic integrity, technological dependency, and data privacy, advocating for the development of students’ critical digital literacy. It concludes that prompt engineering should be embedded into language curricula as a core component of 21st-century digital competence, empowering learners to become autonomous, reflective, and strategic users of AI in their educational journey..
Keywords: prompt engineering, artificial intelligence technologies, neural network, foreign language teaching, LLM (Large Language Models), digital technologies in education, personalized learning
References:
1. Ostapenko S.V., Khalina N.V. Lingvisticheskaya optimizatsiya prompta v aspekte problematiki prompt-inzhiniringa [Linguistic prompt optimization in the context of prompt engineering issues]. Vestnik Tyumenskogo gosudarstvennogo universiteta. Gumanitarnye issledovaniya. Humanitates – Tyumen State University Herald. Humanities Research. Humanitates, 2025, no. 1 (41), pp. 36–50 (in Russian).
2. Bansal P. Prompt Engineering Importance and Applicability with Generative AI. Journal of Computer and Communications, 2024, no. 12, pp. 14–23.
3. Soldatkina Ya.V., Chernavskiy A.S. Generativnye yazykovye modeli kak aktual’nyy fenomen mediakul’tury v nachale XXI veka [Generative language models as a current phenomenon of media culture at the beginning of the 21st century]. Nauka i shkola, 2023, no. 4, pp. 44–56 (in Russian).
4. Alfer’yeva-Termsikos V.B. Prompt-inzhiniring kak strategiya formirovaniya informatsionnoy kul’tury obuchayushchikhsya [Prompt engineering as a strategy for forming the information culture of learners]. Mezhdunarodnyy zhurnal gumanitarnykh i yestestvennykh nauk, 2024, no. 9-1 (96) (in Russian). URL: https://cyberleninka.ru/article/n/promt-inzhiniring-kak-strategiya-formirovaniya-informatsionnoy-kultury-obuchayuschihsya (accessed 06 August 2025).
5. Sokolova M.E. ChatGPT i prompt-inzhiniring: o perspektivakh vnedreniya generativnykh neyrosetey v nauke [ChatGPT and prompt engineering: on the prospects of implementing generative neural networks in science]. Naukovedcheskiye issledovaniya, 2024, no. 1, pp. 92–109 (in Russian).
6. Rashid F., Ranaweera N., Doyle B., Seneviratne S. LLMs are one-shot URL classifiers and explainers. Computer Networks, 2025, no. 258, 111004.
7. Mayer V.S., Rybenets D.A. Sravneniye obyashchayushchikh prilozheniy na osnove iskusstvennogo intellekta v protsesse obucheniya angliyskomu yazyku [Comparison of AI-based explanatory applications in the process of teaching English]. Vestnik NGPU, 2025, no. 2 (55), pp. 329–331 (in Russian).
8. Zhu M., Wang C. A systematic review of artificial intelligence in language education: Current status and future implications. Language Learning & Technology, 2025, no. 29(1), pp. 1–29.
9. Wang X., Pang H., Wallace M. P., Wang Q., Chen W. Learners’ perceived AI presences in AI-supported language learning: A study of AI as a humanized agent from community of inquiry. Computer Assisted Language Learning, 2024, no. 37(4), pp. 814–840.
10. Godwin-Jones R. Partnering with AI: Intelligent writing assistance and instructed language learning. Language Learning & Technology, 2022, no. 26(2), pp 5–24.
11. Li B., Bonk C., Wang C., Kou X. Reconceptualizing self-directed learning in the era of generative AI: An exploratory analysis of language learning. IEEE Transactions on Learning Technologies, 2024, no. 17, pp. 1515-1529.
12. Hockly N. Artificial intelligence in English language teaching: The good, the bad and the ugly. RELC Journal, 2023, no. 45(2), pp. 445–451.
13. Lukinskiy I.A., Gorsheneva I.A. Prompt-inzhiniring v obrazovatel’nom protsesse i nauchnoy deyatel’nosti ili k voprosu o neobkhodimosti obucheniya rabote s iskusstvennym intellektom [Prompt engineering in the educational and research activities or on the necessity of training in working with artificial intelligence]. Psikhologiya i pedagogika sluzhebnoy deyatel’nosti, 2024, no. 4, pp. 148–154 (in Russian).
14. Mantsulich V.V. Teoreticheskaya model’ razvitiya metakognitivnykh sposobnostey budushchikh pedagogov [Theoretical model of developing metacognitive abilities of future teachers]. Psikhologiya. Istoriko-kriticheskiye obozreniya i sovremennye issledovaniya, 2024, no. 4A, pp. 140–147 (in Russian).
15. Cherkasova M.N., Taktarova A.V. Iskusstvenno sgenerirovannyy akademicheskiy tekst (lingvopragmaticheskiy aspekt) [Artificially generated academic text (linguopragmatic aspect)]. Filologicheskiye nauki. Voprosy teorii i praktiki – Philology. Theory and Practice, 2024, vol. 17, no. 7, pp. 2551–2557 (in Russian).
16. Mayer V.S. Feedback Sandwich kak tekhnologiya obratnoy svyazi na zanyatiyakh po inostrannomu yazyku [Feedback Sandwich as a feedback technology in foreign language classes]. Teoretiko-prakticheskiye aspekty obucheniya inostrannym yazykam v neyazykovykh vuzakh (g. Perm’, Rossiya, 31 yanvarya 2024 g.) [Theoretical and practical aspects of teaching foreign languages in non-linguistic universities (Perm, Russia, January 31, 2024)]. 2024. Pp. 166–170 (in Russian).
17. Shamsutdinova T.M. Problemy i perspektivy primeneniya neyronnykh setey v sfere obrazovaniya [Problems and prospects of applying neural networks in the field of education]. Otkrytoye obrazovaniye – Open Education, 2022, no. 26 (6), pp. 4–10 (in Russian).
18. Vezetiu E.V. Formirovaniye fasilitativnoy kompetentnosti budushchikh pedagogov kak usloviye gumanisticheskoy paradigmy obrazovaniya [Developing facilitative competence of future teachers as a condition of the humanistic educational paradigm]. Problemy sovremennogo pedagogicheskogo obrazovaniya – Problems of modern pedagogical education, 2019, no. 62 (1), pp. 80–82 (in Russian).
19. Emel’yantsev A.E. Perspektivnoye ispol’zovaniye neyronnykh setey v zakonotvorchestve i ikh vliyaniye na obespecheniye prav i svobod cheloveka [Prospective use of neural networks in lawmaking and their impact on ensuring human rights and freedoms]. Gumanitarnye, sotsial’no-ekonomicheskiye i obshchestvennye nauki – Humanities, Socio-Economic and Spcial Sciences, 2023, no. 9, pp. 134–137 (in Russian).
20. Filipova I.A. Neyroseti: primeneniye, voprosy etiki i prava [Neural networks: application, ethical and legal issues]. Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Seriya: Pravo – Bulletin of South Ural State University. Law, 2023, no. 23 (4), pp. 76–81 (in Russian).
( 362.12 kB ) 
( 350.86 kB )
Issue: 1, 2026
Series of issue: Issue 1
Rubric: THEORY AND METHODOLOGY OF TEACHING AND EDUCATION
Pages: 46 — 55
Downloads: 337