Agentic Artificial Intelligence in Software Engineering: Integration Points, Architectural Frameworks, Empirical Evaluation, and Governance

Therefore, agentic Artificial Intelligence (AI) represents a paradigm shift in terms of tool use from reactogenic and generative systems to computer programs that can reason and sequentially plan and execute tasks. There are many interests regarding agentic AI, but current studies are yet to provide any well-structured information on points of insertion into the SDLC process, capabilities needed, and effects compared to the limitation posed by the governance mechanism. This study aims to develop and validate a framework for introducing agentic AI into the software development process. Our methodology involved a combination of both qualitative and quantitative research approaches that included a systematic literature review (2024–2025) and a quasi-experimental multi-case empirical analysis based on four enterprise software development projects (April–September 2025). A literature synthesis provided a list of integration points and architectural capabilities that were further evaluated using pre-vs. postintegration comparisons with baseline studies. The effects on DORA metrics, defect density, code coverage, Mean time to recovery (MTTR), and number of violations were analyzed using descriptive statistics and the Wilcoxon signed-rank test. For four projects (N = 4 teams, 9–12 individuals per team), agentic AI integration reduced cycle times by 40–55% (difference median = -2.4 days, 95% CI [-3.1, -1.7], p = 0.01), test coverage by 11–45%, improvements in MTTR by 33–48% (difference median = -29 minutes, 95% CI [-38, -20], p = 0.02), and decreases in change failures by 7–11%. No compliance breaches were observed despite the higher release frequency. Agentic AI systems guided by policy are operationally valuable for enterprise software engineering, especially during the development, testing, and operation stages. Nevertheless, the findings are context-specific and require validation through stronger quasi-experimental approaches. However, the findings are context-specific and derived from a limited number of enterprise projects; therefore, they should be interpreted as indicative rather than broadly generalizable.

Agentic AI; DevSecOps; Empirical software engineering; Governance; Multiagent systems; Self-healing infrastructure

Abou-Ali, M., Dornaika, F., & Charafeddine, J. (2025). Agentic AI: A comprehensive survey of architectures, applications, and future directions. Artificial Intelligence Review, 59(11). https://doi.org/10.1007/s10462-025-11422-4

Alenezi, M., & Akour, M. (2025). AI-driven innovations in software engineering: A review of current practices and future directions. Applied Sciences, 15(3), 1344. https://doi.org/10.3390/app15031344

Allmendinger, S., Bonenberger, L., Endres, K., Fetzer, D., Gimpel, H., & K¨uhl, N. (2026). Multi-agent AI. Electronic Markets, 36(18). https://doi.org/10.1007/s12525-025-00862-z

Al-Omari, O., Alyousef, A., Fati, S., Shannaq, F., & Omari, A. (2025). Governance and ethical frameworks for AI integration in higher education: Enhancing personalized learning and legal compliance. Journal of Ecohumanism, 4(2), 80–86. https://api.semanticscholar.org/CorpusID:275464187

AlSayyad, A., Huang, K. Y., & Pal, R. (2026). Agenttrace: A structured logging framework for agent system observability. LLM-based multi-agent systems: Towards responsible, reliable, and scalable agentic systems. https://doi.org/10.48550/arXiv.2602.10133

Amershi, S., Begel, A., Bird, C., DeLine, R., Gall, H., Kamar, E., & Zimmermann, T. (2019). Software engineering for machine learning: A case study. 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), 291–300. https://doi.org/10.1109/ICSE-SEIP.2019.00042

Arinze, C. A., Izionworu, V. O., Isong, D., Daudu, C. D., & Adefemi, A. (2024). Integrating artificial intelligence into engineering processes for improved efficiency and safety in oil and gas operations. Open Access Research Journal of Engineering and Technology, 6(1), 39–51.

Atri, S. (2025). Trustworthy agentic AI: Balancing autonomy with human oversight. International Journal of Computer Science and Mobile Computing, 14(3), 112–128. https://doi.org/10.47760/ijcsmc.2025.v14i11.013

Burlutskaya, Z. V., Sharko, P. A., Gintciak, A. M., & Zakharov, P. A. (2026). Intelligent decision support system based on multi-agent interaction models by the example of the oil and gas industry. International Journal of Technology, 17(2), 344–358. https://doi.org/10.14716/ijtech.v17i2.8242

Burte, S. (2025). AI-powered software development life cycle: From requirements to maintenance. AI Systems Engineering, 1(1), 1–8. https://doi.org/10.64229/ykh1jf83

Chevrot, A., Vernotte, A., Falleri, J. R., Blanc, X., Legeard, B., & Cretin, A. (2025). Are autonomous web agents good testers? Proceedings of the ACM on Software Engineering, 2(ISSTA), 206–228. https://doi.org/10.1145/3728879

Dhayakar, D. (2025). The four pillars of enterprise agentic AI readiness: A strategic framework for organizational implementation. Journal of Engineering and Computer Sciences, 4(8), 588–597.

Durrani, U. K., Akpinar, M., Adak, M. F., Kabakus, A. T., ¨Ozt¨urk, M. M., & Saleh, M. (2024). A decade of progress: A systematic literature review on the integration of AI in software engineering phases and activities (2013–2023). IEEE Access, 12, 171185–171204. https://doi.org/10.1109/ACCESS.2024.3488904

Ekundayo, F. (2024). Leveraging AI-driven decision intelligence for complex systems engineering. International Journal of Research Publication and Reviews, 5(11), 1–10.

Ganapathi, J. K. (2025). AI-driven product development: Cognitive software delivery at enterprise scale. Journal of Computer Science and Technology Studies. https://doi.org/10.32996/jcsts.2025.7.8.99

Gangavarapu, R. (2025). AI governance: Preparing for the rise of agentic AI. In Mastering AI governance: A guide to building trustworthy and transparent AI systems (pp. 111–119). Springer. https://doi.org/10.1007/978-3-031-93681-4_12

Garg, V. (2025). Designing the mind: How agentic frameworks are shaping the future of AI behavior. Journal of Computer Science and Technology Studies, 7(5), 182–193. https://doi.org/10.32996/jcsts.2025.7.5.24

Gody, R., Goudy, M., & Tawfik, A. Y. (2025). ConvoGen: Enhancing conversational AI with synthetic data: A multi-agent approach. 2025 IEEE Conference on Artificial Intelligence (CAI), 252–257. https://doi.org/10.1109/CAI64502.2025.00046

Haidemariam, T. (2025). From the logic of coordination to goal-directed reasoning: The agentic turn in artificial intelligence. Frontiers in Artificial Intelligence, 8, 1728738. https://doi.org/10.3389/frai.2025.1728738

Hosseini, S., & Seilani, H. (2025). The role of agentic AI in shaping a smart future: A systematic review. Array, 100399. https://doi.org/10.1016/j.array.2025.100399

Hughes, L., Dwivedi, Y. K., & Malik, T. (2025). AI agents and agentic systems: A multi-expert analysis. Journal of Computer Information Systems, 489–517. https://doi.org/10.1080/08874417.2025.2483832

Kumar, R., & Yadav, A. K. (2025). Automating software development pipelines with artificial intelligence (AI). International Journal of Leading Research Publication, 6(7), 1–8.

Kusmenko, E., Pavlitskaya, S., Rumpe, B., & St¨uber, S. (2019). On the engineering of AI-powered systems. 2019 34th IEEE/ACM International Conference on Automated Software Engineering Workshop (ASEW), 126–133. https://doi.org/10.1109/ASEW.2019.00035

Luo, H., Liu, Y., Zhang, R., Wang, J., Sun, G., Niyato, D., Yu, H., Xiong, Z., Wang, X., & Shen, X. (2025). Toward edge general intelligence with multiple-large language model (Multi-LLM): Architecture, trust, and orchestration. IEEE Transactions on Cognitive Communications and Networking. https://doi.org/10.1109/TCCN.2025.3612760

Modi, M. D. B. (2024). Transforming software development through generative AI: A systematic analysis of automated development practices. International Journal, 10(6), 536–547.

Ozurumba, E., & Eboh, I. P. (2024). Leveraging AI-driven decision intelligence for systems engineering complexity. International Journal of Research, 5(11), 4374–4389.

Raji, I. D., Smart, A., White, R. N., Mitchell, M., Gebru, T., Hutchinson, B., & Barnes, P. (2020). Closing the ai accountability gap: Defining an end-to-end framework for internal algorithmic auditing. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 33–44. https://doi.org/10.1145/3351095.3372873

Rombaut, B., Masoumzadeh, S., Vasilevski, K., Lin, D., & Hassan, A. E. (2025). Watson: A cognitive observability framework for the reasoning of llm-powered agents. 2025 IEEE/ACM International Conference on Automated Software Engineering (ASE), 739–751.

Shaikh, S. H. (2025). LLM-based multi-agent systems: Frameworks, evaluation, open challenges, and research frontiers. International Joint Conference on Computational Intelligence, 149–170. https://doi.org/10.1007/978-3-032-15632-7_9

Spieser, J., Balapour, A., Meller, J., Patra, K. C., & Shamsaei, B. (2026). A review of multi-agent AI systems for biological and clinical data analysis. Methods and Protocols, 9(2), 33. https://doi.org/10.3390/mps9020033

Tamanampudi, V. M. (2024). AI-enhanced continuous integration and continuous deployment pipelines. Distributed Learning and Broad Applications in Scientific Research, 10, 56–96.

Venkiteela, P. (2026). An enterprise agentic architecture framework for governance and scalable autonomy. Scientific Journal of Computer Science, 2(1), 1–17. https://doi.org/10.64539/sjcs.v2i1.2026.368

Whulanza, Y., Kusrini, E., Budiyanto, M. A., Arnas, & Skhvediani, A. (2026). Bridging technological sovereignty and global progress through open science. International Journal of Technology, 17(2), 322–328. https://doi.org/10.14716/ijtech.v17i2.8510

Whulanza, Y., Kusrini, E., Harwahyu, R., Fitri, I. R., & Asvial, M. (2025). Viewing ai studies from an ijtech perspective. International Journal of Technology, 16(6), 1888–1893.

Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., & Wang, C. (2024). Autogen: Enabling next-gen llm applications via multi-agent conversations. First Conference on Language Modeling.

Zheng, Y., Hu, Y., Yu, T., & Quinn, A. (2025). Agentsight: System-level observability for ai agents using eBPF. Proceedings of the 4th Workshop on Practical Adoption Challenges of ML for Systems, 110–115. https://doi.org/10.1145/3766882.3767169