Elgindy, R., Sedek, S., Abd Alhakam, R. (2025). Prompt engineering considerations of artificial intelligence applications and its role in formulating advertising messages. International Design Journal, 15(1), 411-417. doi: 10.21608/idj.2025.395729
Reham Mohamed Elgindy; Shimaa Salah Sadek Sedek; Reem Yasser Abd Almawjoud Abd Alhakam. "Prompt engineering considerations of artificial intelligence applications and its role in formulating advertising messages". International Design Journal, 15, 1, 2025, 411-417. doi: 10.21608/idj.2025.395729
Elgindy, R., Sedek, S., Abd Alhakam, R. (2025). 'Prompt engineering considerations of artificial intelligence applications and its role in formulating advertising messages', International Design Journal, 15(1), pp. 411-417. doi: 10.21608/idj.2025.395729
Elgindy, R., Sedek, S., Abd Alhakam, R. Prompt engineering considerations of artificial intelligence applications and its role in formulating advertising messages. International Design Journal, 2025; 15(1): 411-417. doi: 10.21608/idj.2025.395729
Prompt engineering considerations of artificial intelligence applications and its role in formulating advertising messages
2Associate professor, Advertising department, faculty of applied arts, Benha University, Qalyubia, Egypt
3Master's Researcher, Advertising Department, Faculty of Applied Arts, Benha University
Abstract
The rapid pace of technological advancements in artificial intelligence (AI) is accelerating significantly, with major companies in the AI field competing to release AI applications that keep up with this progress. The use of AI applications in social media and multimedia advertising has become widespread, necessitating advertisers to study the architectural frameworks required for large language models to effectively interact with AI applications. This will enable designers to make optimal use of these applications and achieve the best outcomes in crafting advertising messages a process known as prompt engineering. The research aims to establish the foundational principles of prompt engineering for AI applications in the formulation of advertising messages. The importance of this research lies in the necessity of developing prompt engineering skills among advertising designers to enhance their sensory imagination when using AI applications. The research problem is summarized in the following question: What are the key considerations in studying prompt engineering for AI applications, and what role does it play in crafting advertising messages? The researcher adopted a descriptive methodology to gather facts and information about prompt engineering and employed an applied approach to produce designs using AI applications while taking prompt engineering considerations into account. Large Language Models (LLMs) have garnered significant attention across numerous fields, including advertising, where these models have become increasingly intertwined. LLMs are supervised machine learning algorithms designed for regression analysis of datasets using a method known as Ensemble Learning. This approach combines different learning algorithms, with each algorithm supporting the others to enhance predictive capabilities. These models have been fed with extensive information available on the internet, focusing on the field of natural language processing (NLP), specifically human language. This development has led to the emergence of what is now called prompt engineering, a method through which the user—specifically, the advertiser—interacts with AI to shape its behavior in ways that yield more efficient crafting of advertising messages. Recently, the term "command engineering" has become popular, but it is a misnomer. Command engineering is more relevant to programmers, whereas prompt engineering is aimed at AI application users, guiding them in how to communicate effectively with these systems to achieve more impactful results. Research Problem: The research problem revolves around answering the following question: What are the key considerations in studying prompt engineering for AI applications, and what is its role in crafting advertising messages? Research Objectives: The research aims to establish the foundational principles of prompt engineering for AI applications in the formulation of advertising messages. Research Significance: The significance of the research lies in developing prompt engineering skills among advertising designers to enhance their sensory imagination when using AI applications. Research Hypothesis: Developing prompt engineering skills among advertising designers enhances the formulation of advertising messages through AI applications in a manner consistent with the digital world. Research Methodology: The study follows: The descriptive method to collect facts and information about prompt engineering. The applied method to produce designs using AI applications while considering the principles of prompt engineering. Results: Developing prompt engineering skills among advertising designers enhances the formulation of advertising messages through AI applications in a manner consistent with the digital world. Generative AI provides remarkable results in crafting advertising messages when used correctly, following a thorough study of all aspects of the advertising message. Prompts that incorporate proper prompt engineering considerations help in shaping the sensory imagination of advertising designers. The outputs of AI applications vary depending on the formulation of the prompts. AI-generated outputs may require the designer's technical intervention to add text using design software like Photoshop, as AI applications may struggle to correctly interpret text directions in prompts or may need to rely on other specialized applications for text.
Xavier Amatriain (2024), "Prompt Design and Engineering: Introduction and Advanced Methods",arXiv:2401.14423v4 [cs.SE], Cornell University.
Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C. Schmidt (2023), "A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT", arXiv:2302.11382v1[cs.SE], Vanderbilt University
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, Denny Zhou (2023), "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models", arXiv:2201.11903v6 [cs.CL], Google Research, Brain Team
View on SCiNiTO
Top