A taxonomy of Prompt-Driven Development (PDD): Paradigms, Classification, and Implications for Software Engineering


EOI: 10.11242/viva-tech.01.09.16

Download Full Text here



Citation

Vaishnavi Pisal, Amitkumar Vishwakarma, Tejas Sankpal, Reema Gupta, "A taxonomy of Prompt-Driven Development (PDD): Paradigms, Classification, and Implications for Software Engineering", VIVA-IJRI Volume 1, Issue 9, Article 1, pp. 1-6, 2026. Published by Electrical & Computer Engineering Department, VIVA Institute of Technology, Virar, India.

Abstract

The emergence of Large Language Models (LLMs) has catalyzed a fundamental transformation in software engineering, precipitating the rise of Prompt-Driven Development (PDD). This paradigm shifts the primary mechanism of system specification and implementation from rigid syntactic construction to intent-based natural language description. While industry adoption of AI-assisted tools-ranging from intelligent autocomplete systems to fully autonomous software agents-has been rapid, the theoretical framework characterizing these diverse workflows remains under-defined. This paper conducts a comprehensive review of existing literature and technical documentation to establish a rigorous Taxonomy of Prompt-Driven Development. We define PDD as a distinct methodology where the natural language prompt serves as the authoritative source of truth, effectively rendering executable code a disposable, regenerable artifact. The proposed taxonomy classifies PDD across six critical dimensions: Intent Layer, Granularity Level, Human-AI Interaction Mode, Development Phase, Control & Autonomy, and Risk & Reliability Profile. Through detailed case studies of systems such as GitHub Copilot, Replit Agent, Devin, and Autospec, we validate the utility of this taxonomy in distinguishing between assistive, conversational, and agentic workflows. Furthermore, we analyze the profound implications of PDD on software metrics, introducing concepts such as Prompt Stability and Prompt Debt, and examine the critical challenges of security, maintainability, and education. We conclude that PDD represents not merely an acceleration of traditional practices but a divergence into probabilistic engineering, necessitating new frameworks for version control, verification, and human oversight.

Keywords

Agentic Workflows, Generative AI, Large Language Models, Prompt Debt, Prompt Engineering, Prompt-Driven Development, Software Engineering Taxonomy.

References

  1. H. Bai, J. G. Voelkel, S. Muldowney, J. C. Eichstaedt, and R. Willer, “LLM-generated messages can persuade humans on policy issues,” Nature Commun., vol. 16, no. 1, p. 6037, Jul. 2025.
  2. B. Slavych and G. Williams, “Crafting effective prompts for chatgpt: A tutorial,” Internet J. Allied Health Sci. Pract., vol. 23, no. 2, p. 4, 2025.
  3. D. Zhu, J. Chen, X. Shen, X. Li, and M. Elhoseiny, “MiniGPT-4: Enhancing vision-language understanding with advanced large language models,” 25th Int. Conf. Learn. Representations, 2024. [Online]. Available: https://openreview.net/forum?id=1tZbq88f27"How Developers Interact with AI: A Taxonomy," arXiv preprint arXiv:2501.08774v1.
  4. B. Min, H. Ross, E. Sulem, A. P. B. Veyseh, T. H. Nguyen, O. Sainz, E. Agirre, I. Heintz, and D. Roth, “Recent advances in natural language processing via large pre-trained language models: A survey,” ACM Comput. Surveys, vol. 56, no. 2, pp. 1–40, Feb. 2024.
  5. F. Liu, “Remoteclip: A vision language foundation model for remote sensing,” IEEE Trans. Geosci. Remote Sens., vol. 62, 2024, Art. no. 5622216.
  6. G. Yenduri, M. Ramalingam, G. C. Selvi, Y. Supriya, G. Srivastava, P. K. R. Maddikunta, G. D. Raj, R. H. Jhaveri, B. Prabadevi, W. Wang, A. V. Vasilakos, and T. R. Gadekallu, “GPT (generative pre-trained transformer)—A comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions,” IEEE Access, vol. 12, pp. 54608–54649, 2024.
  7. M. H. Munro, R. J. Gore, C. J. Lynch, Y. D. Hastings, and A. M. Reinhold, “Enhancing risk and crisis communication with computational methods: A systematic literature review,” Risk Anal., pp. 1–15, Dec. 2024.
  8. M. A. K. Raiaan, M. S. H. Mukta, K. Fatema, N. M. Fahad, S. Sakib, M. M. J. Mim, J. Ahmad, M. E. Ali, and S. Azam, “A review on large language models: Architectures, applications, taxonomies, open issues and challenges,” IEEE Access, vol. 12, pp. 26839–26874, 2024.
  10. Zhao, Wayne Xin, et al. “A survey of large language models.” arXiv preprint arXiv:2303.18223 (2023).
  11. E. A. M. van Dis, J. Bollen, W. Zuidema, R. van Rooij, and C. L. Bockting, “ChatGPT: Five priorities for research,” Nature, vol. 614, no. 7947, pp. 224–226, Feb. 2023.
  12. M. Sallam, “ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns,” Healthcare, vol. 11, no. 6, p. 887, Mar. 2023.
  13. C. J. Lynch, E. J. Jensen, V. Zamponi, K. O’Brien, E. Frydenlund, and R. Gore, “A structured narrative prompt for prompting narratives from large language models: Sentiment assessment of ChatGPT-generated narratives and real tweets,” Future Internet, vol. 15, no. 12, p. 375, Nov. 2023.
  14. Y. Wang, S. Joty, and S. C. Hoi, “CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2021, pp. 8696–8708.
  15. J. Wei et al., “Chain-of-thought prompting elicits reasoning in large language models,” Proc. 36th Int. Conf. Neural Information Processing Systems (NeurIPS), 2022.
  16. P. Vaithilingam, T. Zhang, and E. L. Glassman, “Expectations, outcomes, and challenges of using AI-assisted coding tools,” Proc. ACM CHI Conf. Human Factors in Computing Systems, pp. 1–17, 2022.
  17. E. Kochmar, T. Briscoe, and A. G. Liakata, “Human-in-the-loop learning for NLP,” Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), pp. 1–12, 2022.
  18. T. Brown et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 1877–1901, 2020.
  19. W. Holmes, M. Bialik, and C. Fadel, Artificial Intelligence in Education: Promises and Implications for Teaching and Learning. Boston, MA, USA: Center for Curriculum Redesign, 2019.
  20. B. Selic, “The pragmatics of model-driven development,” IEEE Software, vol. 20, no. 5, pp. 19–25, Sep.–Oct. 2003.