Abstract
In this research, we examine prompt engineering in generative AI from two primary perspectives. First, we examine the performance of several prompting techniques, such as Zero-shot, Few-shot, and Chain-of-Thought. We then explore the practical applications of these strategies in real-world settings. To determine the best tools and timing, we evaluate models such as GPT-4, Deep Seek, and Gemini on tasks including coding, problem-solving, and content summarization. We rely on metrics such as accuracy, token efficiency, and output consistency to measure their effectiveness.We also look at how companies in industries like customer service and education use prompt engineering to improve chatbots and AI tutoring. The results show where each method works well and falls short, pointing to the most useful ways they can be applied.
Keywords
- Gen AI
- Prompting Techniques
- Open AI
- chatbot
Author affiliations
- Ankur Narwal,, Uttaranchal School of Computing Sciences, Uttaranchal University, Dehradun -248007, India
- Alka Kumari, Uttaranchal School of Computing Sciences, Uttaranchal University, Dehradun -248007, India
How to cite
A. Narwal and A. Kumari, “Prompt engineering in generative AI: A comparative study and industry analysis,” IPEM Journal of Computer Application & Research, vol. 10, pp. 93–101, Dec. 2025.