Keywords
AI
Prompt engineering
How to Cite
Abstract
The article presents prompt engineering as a key element of effective communication between the user and artificial intelligence models based on large language models. Current artificial intelligence is already able to create and deliver material tailored to real needs, but the user does not always have the right skills to obtain this material. The article presents the main techniques of prompt engineering. The article aims to identify the mechanisms by which the structure and precision of prompts affect the quality, accuracy, and coherence of generated responses. As a result, knowledge of the principles of designing effective instructions is just as important as understanding how the expected result functions as feedback.
References
Anam, R.K. (2025) ‘Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity’. OSF Preprints. Available at: https://doi.org/10.31219/osf.io/ad9y5_v1 2025
Chen, B., Zhang, Z., Langrené, N. and Zhu, S. (2025) ‘Unleashing the potential of prompt engineering for large language models’, Patterns, 6(6), 101260. Available at: https://doi.org/10.1016/j.patter.2025.101260
Fagadau, I.D., Mariani, L., Micucci, D. and Riganelli, O. (2024) ‘Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot’, arXiv preprint arXiv:2402.08430. Available at: https://doi.org/10.48550/arXiv.2402.08430
Hickerson, D. and Perkins, M. (2025) ‘A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models’. arXiv preprint. Available at: https://doi.org/10.48550/arXiv.2503.15205
Lee, D. and Palmer, E. (2025) ‘Prompt engineering in higher education: A systematic review to help inform curricula’, International Journal of Educational Technology in Higher Education, 22, 7. Available at: https://doi.org/10.1186/s41239-025-00503-7
OpenAI (no date) ChatGPT. Available at: https://chatgpt.com
OpenAI (no date) Tokenizer. Available at: https://platform.openai.com/tokenizer
Pastor-Merino, A., Martínez-Barbero, X., Vicente, M.R. and Domenech, J. (2025) ‘Does AI boost firm productivity? A web scraping and LLMs approach’, Telecommunications Policy, 50(2), 103138. Available at: https://doi.org/10.1016/j.telpol.2025.103138
Pawar, S., Apte, M.M., Jadhav, K., Palshikar, G.K. and Ramrakhiyani, N. (2025) ‘Broken Words, Broken Performance: Effect of Tokenization on Performance of LLMs’. arXiv preprint. Available at: https://arxiv.org/abs/2512.21933 (
Vallverdú, J., Rzepka, R. and Sans Pinillos, A. (2025) ‘Editorial: Prompts: the double-edged sword using AI’, Frontiers in Artificial Intelligence, 8, 1756343. Available at: https://doi.org/10.3389/frai.2025.1756343 (
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Konrad Hoza