Prompt Engineering in Generative AI: A Comparative Study and Industry Analysis

Author Details

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

[1]      X. Amatriain, “Prompt Design and Engineering: Introduction and Advanced Methods,” May 2024, [Online]. Available: http://arxiv.org/abs/2401.14423

[2]      S. Bubeck et al., “Sparks of Artificial General Intelligence: Early experiments with GPT-4,” Apr. 2023, [Online]. Available: http://arxiv.org/abs/2303.12712

[3]      L. Reynolds and K. McDonell, “Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm,” Feb. 2021, [Online]. Available: http://arxiv.org/abs/2102.07350

[4]      M. Desmond and M. Brachman, “Exploring Prompt Engineering Practices in the Enterprise,” Mar. 2024, [Online]. Available: http://arxiv.org/abs/2403.08950

[5]      T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa, “Large Language Models are Zero-Shot Reasoners,” Jan. 2023, [Online]. Available: http://arxiv.org/abs/2205.11916

[6]      J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” Jan. 2023, [Online]. Available: http://arxiv.org/abs/2201.11903

[7]      P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, “Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing,” ACM ComputSurv, vol. 55, no. 9, Sep. 2023, doi: 10.1145/3560815.

[8]      P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha, “A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications,” Mar. 2025, [Online]. Available: http://arxiv.org/abs/2402.07927

[9]      K. Singhal et al., “Large language models encode clinical knowledge,” Nature, vol. 620, no. 7972, pp. 172–180, Aug. 2023, doi: 10.1038/s41586-023-06291-2.

[10]     T. B. Brown et al., “Language Models are Few-Shot Learners,” Jul. 2020, [Online]. Available: http://arxiv.org/abs/2005.14165

[11]     H. Touvronet al., “Llama 2: Open Foundation and Fine-Tuned Chat Models,” Jul. 2023, [Online]. Available: http://arxiv.org/abs/2307.09288

[12]     P. Liang et al., “Holistic Evaluation of Language Models,” Oct. 2023, [Online]. Available: http://arxiv.org/abs/2211.09110

[13]     Y. Zhou et al., “Large Language Models Are Human-Level Prompt Engineers,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2211.01910

[14]     Q. Lyu et al., “Faithful Chain-of-Thought Reasoning,” Sep. 2023, [Online]. Available: http://arxiv.org/abs/2301.13379

[15]     J. Kang, W. Xu, and A. Ritter, “Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models,” Jul. 2023, [Online]. Available: http://arxiv.org/abs/2305.01645

[16]     C. Raffel et al., “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” Sep. 2023, [Online]. Available: http://arxiv.org/abs/1910.10683

[17]     Y. Bai et al., “Constitutional AI: Harmlessness from AI Feedback,” Dec. 2022, [Online]. Available: http://arxiv.org/abs/2212.08073

[18]     K. Cobbe et al., “Training Verifiers to Solve Math Word Problems,” Nov. 2021, [Online]. Available: http://arxiv.org/abs/2110.14168

[19]     M. Chen et al., “Evaluating Large Language Models Trained on Code,” Jul. 2021, [Online]. Available: http://arxiv.org/abs/2107.03374

[20]     J. W. Rae et al., “Scaling Language Models: Methods, Analysis & Insights from Training Gopher,” Jan. 2022, [Online]. Available: http://arxiv.org/abs/2112.11446

[21]     OpenAI et al., “GPT-4 Technical Report,” Mar. 2024, [Online]. Available: http://arxiv.org/abs/2303.08774

[22]     C. Qin, A. Zhang, Z. Zhang, J. Chen, M. Yasunaga, and D. Yang, “Is ChatGPT a General-Purpose Natural Language Processing Task Solver?” Nov. 2023, [Online]. Available: http://arxiv.org/abs/2302.06476

[23]     A. Bolotin, “The paradox of classical reasoning,” Jul. 2022, doi: 10.1007/s10701-022-00604-7.

[24]     V. Sanh et al., “Multitask Prompted Training Enables Zero-Shot Task Generalization,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2110.08207

[25]     D. Zhou et al., “Least-to-Most Prompting Enables Complex Reasoning in Large Language Models,” Apr. 2023, [Online]. Available: http://arxiv.org/abs/2205.10625

[26]     A. Tamkin, M. Brundage, J. Clark, and D. Ganguli, “Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models,” Feb. 2021, [Online]. Available: http://arxiv.org/abs/2102.02503

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.