SavedAdd your journal

Journals / Journal of Business Innovation and Governance / 2026 / Cilt: 9

INTEGRATING GENERATIVE ARTIFICIAL INTELLIGENCE INTO AGILE SOFTWARE DEVELOPMENT AND DEVOPS PROCESSES: EFFECT MECHANISMS, APPLICATION PATTERNS, AND MEASUREMENT METRICS

ÇEVİK YAZILIM GELİŞTİRME VE DEVOPS SÜREÇLERİNDE ÜRETKEN YAPAY ZEKÂ ENTEGRASYONU: ETKİ MEKANİZMALARI, UYGULAMA DESENLERİ VE ÖLÇÜM METRİKLERİ

Hamid Yeşilyayla(PAMUKKALE ÜNİVERSİTESİ, ÇİVRİL MESLEK YÜKSEKOKULU)0000-0002-7309-615X
Pages
—
Publication Date
2026-06-22
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The review concludes by proposing a multidimensional measurement frame that jointly monitors delivery speed, quality, security, technical debt, and user acceptance.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The influence of generative artificial intelligence on software engineering has evolved from isolated task-level performance into a process-level research question of considerable scope.
📊
Key Findings & Data:This study synthesizes literature from Scopus, Web of Science, ScienceDirect, ACM Digital Library, IEEE Xplore, and the TR Dizin index for the period 2016–2026, applying a structured review and thematic coding methodology.
💡
Conclusion & Impact:The review concludes by proposing a multidimensional measurement frame that jointly monitors delivery speed, quality, security, technical debt, and user acceptance.
🔬Design:Review & Systematic Survey
📍Scope:2016–2026 Verileri
⚙️Variables:Üretken Yapay Zekâ · Çevik Yazılım Geliştirme · DevOps

Abstract

The influence of generative artificial intelligence on software engineering has evolved from isolated task-level performance into a process-level research question of considerable scope. This study synthesizes literature from Scopus, Web of Science, ScienceDirect, ACM Digital Library, IEEE Xplore, and the TR Dizin index for the period 2016–2026, applying a structured review and thematic coding methodology. Fifty-one studies with verified DOIs and direct relevance to agile development or DevOps processes were retained. The findings converge on three themes: consistent productivity gains in low-uncertainty tasks such as code drafting, unit test generation, and backlog expansion; mixed evidence on correctness, security, and technical debt; and governance gaps in which individual tool adoption does not transfer to organizational process integration. Evidence from randomised user studies demonstrates that developers with AI assistant access produce code containing more security vulnerabilities and hold stronger beliefs that their code is secure, establishing that speed gains cannot be represented by a single productivity indicator. The review concludes by proposing a multidimensional measurement frame that jointly monitors delivery speed, quality, security, technical debt, and user acceptance.

Özet

Üretken yapay zekânın yazılım mühendisliğine etkisi, tekil görev başarısından öte süreç düzeyinde incelenmesi gereken bir araştırma alanına dönüşmüştür. Bu çalışma, 2016-2026 dönemine ait Scopus, Web of Science, ScienceDirect, ACM Digital Library, IEEE Xplore ve Türkiye Atıf Dizini (TR Dizin) kaynaklı literatürü yapılandırılmış inceleme ve tematik sentez yöntemiyle ele almaktadır. DOI doğrulaması yapılan ve çevik geliştirme ya da DevOps süreçleriyle doğrudan ilişkili elli bir çalışma örnekleme alınmıştır. Bulgular üç eksen üzerinde yoğunlaşmaktadır: düşük belirsizlikli görevlerde —kod taslağı, birim test üretimi ve backlog genişletme— tutarlı verimlilik kazanımları; güvenlik, doğruluk ve teknik borç boyutunda karışık kanıtlar; geliştirici benimsemesinin kurumsal düzeyde aynı hızla ilerlemediği yönetişim açıkları. Kodlama yardımcısına erişimli geliştiricilerin daha yüksek oranda güvenlik açığı ürettiğine ilişkin deney bulguları, hız-kalite dengesinin tek boyutlu üretkenlik göstergesiyle temsil edilemeyeceğini göstermektedir. İnceleme sonunda teslim hızı, kalite, güvenlik, teknik borç ve kullanıcı kabulünü birlikte izleyen çok boyutlu bir ölçüm çerçevesi önerilmektedir.

🔖

Cite This Article

Yeşilyayla, H. (2026). INTEGRATING GENERATIVE ARTIFICIAL INTELLIGENCE INTO AGILE SOFTWARE DEVELOPMENT AND DEVOPS PROCESSES: EFFECT MECHANISMS, APPLICATION PATTERNS, AND MEASUREMENT METRICS. Journal of Business Innovation and Governance, Cilt: 9. https://doi.org/10.54472/jobig.1921341

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (52)

  1. Amaro, R., Pereira, R. ve Da Silva, M. M. (2023). Capabilities and metrics in DevOps: A design science study. Information & Management, 60(5), 103809. doi:10.1016/j.im.2023.103809
  2. Amaro, R., Pereira, R. ve Mira Da Silva, M. (2024). DevOps Metrics and KPIs: A Multivocal Literature Review. ACM Computing Surveys, 56(9), 1-41. doi:10.1145/3652508
  3. Asare, O., Nagappan, M. ve Asokan, N. (2023). Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code? Empirical Software Engineering, 28(6), 129. doi:10.1007/s10664-023-10380-1
  4. Aydiner, A. S., Esen, M. F. ve Özlü, E. (2020). Türkiye’de Çevik Yazılım Geliştirme Süreçlerinde Scrum Yöntemini Uygulayan İşletmelerin Başarı Faktörleri. Bilişim Teknolojileri Dergisi, 13(4), 463-477. doi:10.17671/gazibtd.598346
  5. Bahi, A., Gharib, J. ve Gahi, Y. (2024). Integrating Generative AI for Advancing Agile Software Development and Mitigating Project Management Challenges. International Journal of Advanced Computer Science and Applications, 15(3). doi:10.14569/IJACSA.2024.0150306
  6. Banh, L., Holldack, F. ve Strobel, G. (2025). Copiloting the future: How generative AI transforms Software Engineering. Information and Software Technology, 183, 107751. doi:10.1016/j.infsof.2025.107751
  7. Barke, S., James, M. B. ve Polikarpova, N. (2023). Grounded Copilot: How Programmers Interact with Code-Generating Models. Proceedings of the ACM on Programming Languages, 7(OOPSLA1), 85-111. doi:10.1145/3586030
  8. Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. de O., Kaplan, J., … Zaremba, W. (2021). Evaluating Large Language Models Trained on Code. arXiv. doi:10.48550/ARXIV.2107.03374
  9. Cheng, H., Husen, J. H., Lu, Y., Racharak, T., Yoshioka, N., Ubayashi, N. ve Washizaki, H. (2026). Generative AI for Requirements Engineering: A Systematic Literature Review. Software: Practice and Experience, 56(2), 141-170. doi:10.1002/spe.70029
  10. Cornide-Reyes, H., Monsalves, D., Durán, E., Silva-Aravena, F. ve Morales, J. (2025). Generative Artificial Intelligence in Agile Software Development Processes: A Literature Review Focused on User eXperience. A. Coman ve S. Vasilache (Ed.), Social Computing and Social Media içinde, Lecture Notes in Computer Science (C. 15787, ss. 228-246). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-93536-7_16
  11. Dakhel, A. M., Nikanjam, A., Majdinasab, V., Khomh, F. ve Desmarais, M. C. (2024). Effective test generation using pre-trained Large Language Models and mutation testing. Information and Software Technology, 171, 107468. doi:10.1016/j.infsof.2024.107468
  12. Eramo, R., Said, B., Oriol, M., Bruneliere, H. ve Morales, S. (2024). An architecture for model-based and intelligent automation in DevOps. Journal of Systems and Software, 217, 112180. doi:10.1016/j.jss.2024.112180
  13. Esposito, M., Li, X., Moreschini, S., Ahmad, N., Cerny, T., Vaidhyanathan, K., … Taibi, D. (2026). Generative AI for software architecture. Applications, challenges, and future directions. Journal of Systems and Software, 231, 112607. doi:10.1016/j.jss.2025.112607
  14. Gao, C., Hu, X., Gao, S., Xia, X. ve Jin, Z. (2025). The Current Challenges of Software Engineering in the Era of Large Language Models. ACM Transactions on Software Engineering and Methodology, 34(5), 1-30. doi:10.1145/3712005
  15. Hanci, A. K. ve Gülseçen, S. (2023). DevOps Test Süreç Geliştirmede Yeni Bir Model Önerisi. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11(4), 1829-1846. doi:10.29130/dubited.1132368
  16. He, J., Treude, C. ve Lo, D. (2025). LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision, and the Road Ahead. ACM Transactions on Software Engineering and Methodology, 34(5), 1-30. doi:10.1145/3712003
  17. Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., … Wang, H. (2024). Large Language Models for Software Engineering: A Systematic Literature Review. ACM Transactions on Software Engineering and Methodology, 33(8), 1-79. doi:10.1145/3695988
  18. Jensen, V. V., Alami, A., Bruun, A. R. ve Persson, J. S. (2025). Managing expectations towards AI tools for software development: A multiple-case study. Information Systems and e-Business Management, 23(4), 869-901. doi:10.1007/s10257-025-00704-7
  19. Jiang, J., Wang, F., Shen, J., Kim, S. ve Kim, S. (2026). A Survey on Large Language Models for Code Generation. ACM Transactions on Software Engineering and Methodology, 35(2), 1-72. doi:10.1145/3747588
  20. Kemell, K.-K., Saarikallio, M., Nguyen-Duc, A. ve Abrahamsson, P. (2025). Still just personal assistants? – A multiple case study of generative AI adoption in software organizations. Information and Software Technology, 186, 107805. doi:10.1016/j.infsof.2025.107805
  21. Kumar, A., Nadeem, M. ve Shameem, M. (2025). A Systematic Literature Review for Investigating DevOps Metrics to Implement in Software Development Organizations. Journal of Software: Evolution and Process, 37(1), e2733. doi:10.1002/smr.2733
  22. Li, S., Cheng, Y., Chen, J., Xuan, J., He, S. ve Shang, W. (2026). Performance analysis of AI-generated code: A case study of Copilot, Copilot Chat, CodeLlaMa, and DeepSeek-Coder models. Empirical Software Engineering, 31(3), 62. doi:10.1007/s10664-025-10776-1
  23. Liang, J. T., Yang, C. ve Myers, B. A. (2024). A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges. Proceedings of the IEEE/ACM 46th International Conference on Software Engineering içinde (ss. 1-13). ICSE ’24: IEEE/ACM 46th International Conference on Software Engineering, sunulmuş bildiri, Lisbon Portugal: ACM. doi:10.1145/3597503.3608128
  24. Liu, Y., Le-Cong, T., Widyasari, R., Tantithamthavorn, C., Li, L., Le, X.-B. D. ve Lo, D. (2024). Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues. ACM Transactions on Software Engineering and Methodology, 33(5), 1-26. doi:10.1145/3643674
  25. Mastropaolo, A., Pascarella, L., Guglielmi, E., Ciniselli, M., Scalabrino, S., Oliveto, R. ve Bavota, G. (2023). On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot. 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) içinde (ss. 2149-2160). 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), sunulmuş bildiri, Melbourne, Australia: IEEE. doi:10.1109/ICSE48619.2023.00181
  26. Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C. ve Jiang, Z. M. (Jack). (2023). GitHub Copilot AI pair programmer: Asset or Liability? Journal of Systems and Software, 203, 111734. doi:10.1016/j.jss.2023.111734
  27. Moreschini, S., Arvanitou, E.-M., Kanidou, E.-P., Nikolaidis, N., Su, R., Ampatzoglou, A., … Lenarduzzi, V. (2026). The Evolution of Technical Debt from DevOps to Generative AI: A multivocal literature review. Journal of Systems and Software, 231, 112599. doi:10.1016/j.jss.2025.112599
  28. Nguyen‐Duc, A., Cabrero‐Daniel, B., Przybylek, A., Arora, C., Khanna, D., Herda, T., … Abrahamsson, P. (2025). Generative Artificial Intelligence for Software Engineering—A Research Agenda. Software: Practice and Experience, 55(11), 1806-1843. doi:10.1002/spe.70005
  29. Ozkaya, I. (2023). Can Architecture Knowledge Guide Software Development With Generative AI? IEEE Software, 40(5), 4-8. doi:10.1109/MS.2023.3306641
  30. Pearce, H., Ahmad, B., Tan, B., Dolan-Gavitt, B. ve Karri, R. (2022). Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions. 2022 IEEE Symposium on Security and Privacy (SP) içinde (ss. 754-768). 2022 IEEE Symposium on Security and Privacy (SP), sunulmuş bildiri, San Francisco, CA, USA: IEEE. doi:10.1109/SP46214.2022.9833571
  31. Perry, N., Srivastava, M., Kumar, D. ve Boneh, D. (2023). Do Users Write More Insecure Code with AI Assistants? Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security içinde (ss. 2785-2799). CCS ’23: ACM SIGSAC Conference on Computer and Communications Security, sunulmuş bildiri, Copenhagen Denmark: ACM. doi:10.1145/3576915.3623157
  32. Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., … Sun, M. (2024). ChatDev: Communicative Agents for Software Development. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) içinde (ss. 15174-15186). Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), sunulmuş bildiri, Bangkok, Thailand: Association for Computational Linguistics. doi:10.18653/v1/2024.acl-long.810
  33. Recupito, G., Pecorelli, F., Catolino, G., Lenarduzzi, V., Taibi, D., Di Nucci, D. ve Palomba, F. (2024). Technical debt in AI-enabled systems: On the prevalence, severity, impact, and management strategies for code and architecture. Journal of Systems and Software, 216, 112151. doi:10.1016/j.jss.2024.112151
  34. Russo, D. (2024). Navigating the Complexity of Generative AI Adoption in Software Engineering. ACM Transactions on Software Engineering and Methodology, 33(5), 1-50. doi:10.1145/3652154
  35. Sainio, K., Abrahamsson, P. ve Ahtee, T. (2024). Prompt Patterns for Agile Software Project Managers: First Results. S. Hyrynsalmi, J. Münch, K. Smolander ve J. Melegati (Ed.), Software Business içinde, Lecture Notes in Business Information Processing (C. 500, ss. 190-204). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-53227-6_14
  36. Sauvola, J., Tarkoma, S., Klemettinen, M., Riekki, J. ve Doermann, D. (2024). Future of software development with generative AI. Automated Software Engineering, 31(1), 26. doi:10.1007/s10515-024-00426-z Sergeyuk, A., Golubev, Y., Bryksin, T. ve Ahmed, I. (2025). Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forward. Information and Software Technology, 178, 107610. doi:10.1016/j.infsof.2024.107610
  37. Sharma, A. ve Kumar Tripathi, A. (2025). Evaluating user story quality with LLMs: A comparative study. Journal of Intelligent Information Systems, 63(4), 1423-1451. doi:10.1007/s10844-025-00939-3
  38. Svyatkovskiy, A., Zhao, Y., Fu, S. ve Sundaresan, N. (2019). Pythia: AI-assisted Code Completion System. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining içinde (ss. 2727-2735). KDD ’19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, sunulmuş bildiri, Anchorage AK USA: ACM. doi:10.1145/3292500.3330699
  39. Tony, C., Díaz Ferreyra, N. E., Mutas, M., Dhif, S. ve Scandariato, R. (2025). Prompting Techniques for Secure Code Generation: A Systematic Investigation. ACM Transactions on Software Engineering and Methodology, 34(8), 1-53. doi:10.1145/3722108
  40. Tufano, R., Masiero, S., Mastropaolo, A., Pascarella, L., Poshyvanyk, D. ve Bavota, G. (2022). Using pre-trained models to boost code review automation. Proceedings of the 44th International Conference on Software Engineering içinde (ss. 2291-2302). ICSE ’22: 44th International Conference on Software Engineering, sunulmuş bildiri, Pittsburgh Pennsylvania: ACM. doi:10.1145/3510003.3510621
  41. Umre, J., Parihar, A. S. ve Gupta, A. (2026). CSLLM: Code-Specific Large Language Models—A Survey. Expert Systems with Applications, 308, 130991. doi:10.1016/j.eswa.2025.130991
  42. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin, I. (2017). Attention Is All You Need. arXiv. doi:10.48550/ARXIV.1706.03762
  43. Yang, L., Yang, C., Gao, S., Wang, W., Wang, B., Zhu, Q., … Chen, J. (2024). On the Evaluation of Large Language Models in Unit Test Generation. Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering içinde (ss. 1607-1619). ASE ’24: 39th IEEE/ACM International Conference on Automated Software Engineering, sunulmuş bildiri, Sacramento CA USA: ACM. doi:10.1145/3691620.3695529
  44. Yetistiren, B., Ozsoy, I. ve Tuzun, E. (2022). Assessing the quality of GitHub copilot’s code generation. Proceedings of the 18th International Conference on Predictive Models and Data Analytics in Software Engineering içinde (ss. 62-71). PROMISE ’22: 18th International Conference on Predictive Models and Data Analytics in Software Engineering, sunulmuş bildiri, Singapore Singapore: ACM. doi:10.1145/3558489.3559072
  45. Yu, L., Alégroth, E., Chatzipetrou, P. ve Gorschek, T. (2025). Measuring the quality of generative AI systems: Mapping metrics to quality characteristics — Snowballing literature review. Information and Software Technology, 186, 107802. doi:10.1016/j.infsof.2025.107802
  46. Yu, L., Alégroth, E., Chatzipetrou, P. ve Gorschek, T. (2026). Evaluating the quality of GenAI applications in software engineering: A multi-case study. Empirical Software Engineering, 31(2), 29. doi:10.1007/s10664-025-10759-2
  47. Zhang, B., Liang, P., Zhou, X., Ahmad, A. ve Waseem, M. (2023). Practices and Challenges of Using GitHub Copilot: An Empirical Study (ss. 124-129). The 35th International Conference on Software Engineering and Knowledge Engineering, sunulmuş bildiri. doi:10.18293/SEKE2023-077
  48. Zhang, Q., Fang, C., Xie, Y., Zhang, Y., Yu, S., Sun, W., … Chen, Z. (2026). A survey on large language models for software engineering. Science China Information Sciences, 69(4), 141102. doi:10.1007/s11432-025-4670-0
  49. Zhou, X., Liang, P., Zhang, B., Li, Z., Ahmad, A., Shahin, M. ve Waseem, M. (2025). Exploring the problems, their causes and solutions of AI pair programming: A study on GitHub and Stack Overflow. Journal of Systems and Software, 219, 112204. doi:10.1016/j.jss.2024.112204
  50. Ziegler, A., Kalliamvakou, E., Li, X. A., Rice, A., Rifkin, D., Simister, S., … Aftandilian, E. (2024). Measuring GitHub Copilot’s Impact on Productivity. Communications of the ACM, 67(3), 54-63. doi:10.1145/3633453
  51. Cornide-Reyes, H., Monsalves, D., Durán, E., Silva-Aravena, F. ve Morales, J. (2025). Generative Artificial Intelligence in Agile Software Development Processes: A Literature Review Focused on User eXperience. A. Coman ve S. Vasilache (Ed.), Social Computing and Social Media içinde, Lecture Notes in Computer Science (C. 15787, ss. 228-246). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-93536-7_16
  52. Sainio, K., Abrahamsson, P. ve Ahtee, T. (2024). Prompt Patterns for Agile Software Project Managers: First Results. S. Hyrynsalmi, J. Münch, K. Smolander ve J. Melegati (Ed.), Software Business içinde, Lecture Notes in Business Information Processing (C. 500, ss. 190-204). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-53227-6_14