Intelligent Software Agents for Continuous Delivery: Leveraging AI and Machine Learning for Fully Automated DevOps Pipelines

References

[1] R. McCreadie et al., “Leveraging data-driven infrastructure management to facilitate AIOps for big data applications and operations,” Technol. Appl. Big Data Value, pp. 135–158, 2022, doi: 10.1007/9783030783075_7.

[2] S. Johnson, “DEVOPS IN A BOX : AN OPEN-SOURCE STARTER KIT FOR NEW STARTUPS,” vol. 3, no. 2, pp. 143–160, 2021.

[3] A. M. Thakur et al., “Towards a Software Development Framework for Interconnected Science Ecosystems,” Commun. Comput. Inf. Sci., vol. 1690 CCIS, pp. 206–224, 2022, doi: 10.1007/978-3-031-23606-8_13.

[4] A. Alnafessah, A. U. Gias, R. Wang, L. Zhu, G. Casale, and A. Filieri, “Quality-Aware DevOps Research: Where Do We Stand?,” IEEE Access, vol. 9, pp. 44476–44489, 2021, doi: 10.1109/ACCESS.2021.3064867.

[5] Y. Ramaswamy, “AI - Optimized Bioinformatics Pipelines in DevOps,” vol. 1, no. 2, pp. 147–161, 2021, doi: 10.56472/25832646/JETA-V1I2P117.

[6] S. Tatineni and V. R. Boppana, “AI-Powered DevOps and MLOps Frameworks: Enhancing Collaboration, Automation, and Scalability in Machine Learning Pipelines,” J. Artif. Intell. …, vol. 1, no. 2, pp. 58–88, 2021, [Online]. Available: https://aimlstudies.co.uk/index.php/jaira/article/view/103%0Ahttps://aimlstudies.co.uk/index.php/jaira/article/download/103/97

[7] E. Ok and J. Eniola, “Accelerating Software Releases : Implementing Continuous Integration and Continuous Delivery with Jenkins,” no. January 2024, 2025.

[8] V. M. Tamanampudi, “End-to-End ML-Driven Feedback Loops in DevOps Pipelines End-to-End ML-Driven Feedback Loops in DevOps Pipelines,” no. September, 2024, doi: 10.30574/wjaets.2024.13.1.0424.

[9] I. Tiedekunta, “CHATBOTS IN SOFTWARE RELEASE OPTIMIZA- TION : CASE STUDY,” 2024.

[10] S. Tistelgrén, “Artificial Intelligence in Software Development: Exploring Utilisation, Tools, and Value Creation,” 2024.

[11] A. Goyal, “Optimising Cloud-Based CI / CD Pipelines : Techniques for Rapid Software Deployment,” no. December, 2024.

[12] T. A. Tran, T. Ruppert, and J. Abonyi, “The Use of eXplainable Artificial Intelligence and Machine Learning Operation Principles to Support the Continuous Development of Machine Learning-Based Solutions in Fault Detection and Identification,” Computers, vol. 13, no. 10, 2024, doi: 10.3390/computers13100252.

[13] R. Manchana and C. O. Company, “The DevOps Automation Imperative : Enhancing Software Lifecycle Efficiency and Collaboration The DevOps Automation Imperative : Enhancing Software Lifecycle Efficiency and Collaboration Ramakrishna Manchana,” no. July 2021, 2024, doi: 10.5281/zenodo.13789734.

[14] M. Bedoya, S. Palacios, D. Díaz-López, E. Laverde, and P. Nespoli, “Enhancing DevSecOps practice with Large Language Models and Security Chaos Engineering,” Int. J. Inf. Secur., vol. 23, no. 6, pp. 3765–3788, 2024, doi: 10.1007/s10207-024-00909-w.

[15] Y. Sierhieiev, V. Paiuk, A. Nicheporuk, A. Kwiecien, and O. Huralnyk, “Detection and prediction of the vulnerabilities in software systems based on behavioral analysis with machine learning,” CEUR Workshop Proc., vol. 3736, pp. 239–254, 2024.

[16] R. Ouaarous, I. Hilal, and A. Mezrioui, “On Using Artificial Intelligence in Software Quality Assurance: A State of the Art,” CEUR Workshop Proc., vol. 3845, 2024.

[17] A. Mankotia, S. Manager, D. Fueling, and S. Llc, “Impact of AI and Language Models on DevOps and DevSecOps,” vol. 14, no. 07, pp. 61–81, 2024.

[18] S. Chittala, “ORCHESTRATING THE CLOUD : AI- ENHANCED RELEASE AUTOMATION IN,” vol. 7, no. 2, pp. 864–878, 2024.

[19] A. Shukla, J. K. Vijay, U. Sen, and J. Jain, “From Prototyping to Production: LLM Chains carrying the Software Development Pipeline,” vol. 11, no. 3, pp. 193–200, 2024.

[20] S. Shah, “THE RISE OF AI AGENTS IN ENTERPRISE,” vol. 15, no. 5, pp. 803–813, 2024.

[21] N. Nivedhaa, “EVALUATING DEVOPS TOOLS AND TECHNOLOGIES FOR EFFECTIVE CLOUD,” vol. 1, no. 1, pp. 20–32, 2024.

[22] N. Gadani, “ARTIFICIAL INTELLIGENCE : LEVERAGING AI-BASED TECHNIQUES FOR ARTIFICIAL INTELLIGENCE : LEVERAGING AI-BASED TECHNIQUES FOR SOFTWARE QUALITY Artificial Intelligence in Software Development,” no. July, 2024, doi: 10.56726/IRJMETS60018.

[23] S. Kumar, “AI/ML Enabled Automation System for Software Defined Disaggregated Open Radio Access Networks: Transforming Telecommunication Business,” Big Data Min. Anal., vol. 7, no. 2, pp. 271–293, 2024, doi: 10.26599/BDMA.2023.9020033.

[24] H. W. Marar, “Advancements in software engineering using AI,” Comput. Softw. Media Appl., vol. 6, no. 1, p. 3906, 2024, doi: 10.24294/csma.v6i1.3906.

[25] F. Bayram, “Towards Trustworthy Machine Learning in Production : An Overview of the Robustness in MLOps Approach,” no. Ml, 2024, doi: 10.1145/3708497.

[26] J. Kohl et al., “Generative AI Toolkit -- a framework for increasing the quality of LLM-based applications over their whole life cycle,” 2024, [Online]. Available: http://arxiv.org/abs/2412.14215

[27] P. Sowinski, I. Lacalle, R. Vano, C. E. Palau, M. Ganzha, and M. Paprzycki, “Overview of Current Challenges in Multi-Architecture Software Engineering and a Vision for the Future,” pp. 1–21, 2024, [Online]. Available: http://arxiv.org/abs/2410.20984

[28] B. Eken, S. Pallewatta, N. K. Tran, A. Tosun, and M. A. Babar, “A Multivocal Review of MLOps Practices, Challenges and Open Issues,” 2024, [Online]. Available: http://arxiv.org/abs/2406.09737

[29] M. Fu, J. Pasuksmit, and C. Tantithamthavorn, “AI for DevSecOps: A Landscape and Future Opportunities,” vol. 1, no. 1, 2024, [Online]. Available: http://arxiv.org/abs/2404.04839

[30] P. Nama, A. Technology, and S. Chinta, “Autonomous Test Oracles : Integrating AI for Intelligent Decision-Making in Automated Software Testing,” no. October, 2024.

[31] P. Ganesan and G. Sanodia, “Journal of Artificial Intelligence & Cloud Computing Smart Infrastructure Management : Integrating AI with DevOps for Cloud-Native Applications,” vol. 2023, no. October, 2024, doi: 10.47363/JAICC/2023(2)E163.

[32] J. Yang, “Next-Gen Enterprise Architecture : Unlocking AI and Cloud Potential Through DevOps Integration Date : November , 2024,” no. November, 2024, doi: 10.13140/RG.2.2.12984.97286.

[33] F. Dine, “Transforming IT Operations : The Power of AI-Enhanced Cloud , DevOps , and DataOps in Enterprise Architecture,” no. November, 2024, doi: 10.13140/RG.2.2.31416.97285.

[34] A. Schmelczer and J. Visser, “Trustworthy and Robust AI Deployment by Design: A framework to inject best practice support into AI deployment pipelines,” Proc. - 2023 IEEE/ACM 2nd Int. Conf. AI Eng. - Softw. Eng. AI, CAIN 2023, pp. 127–138, 2023, doi: 10.1109/CAIN58948.2023.00030.

[35] S. Dinesh, “A Framework of DevSecOps for Software Development Teams,” no. June, 2023, [Online]. Available: https://urn.fi/URN:NBN:fi-fe2023073192373

[36] M. Underwood, “Continuous Metadata in Continuous Integration, Stream Processing and Enterprise DataOps,” Data Intell., vol. 5, no. 1, pp. 275–288, 2023, doi: 10.1162/dint_a_00193.

[37] A. Sunny, “Artificial Intelligence’s Effect on Contemporary Computer Software,” no. December, 2023, [Online]. Available: https://www.researchgate.net/publication/376645343

[38] M. Cankar et al., “Security in DevSecOps: Applying Tools and Machine Learning to Verification and Monitoring Steps,” ICPE 2023 - Companion 2023 ACM/SPEC Int. Conf. Perform. Eng., pp. 201–205, 2023, doi: 10.1145/3578245.3584943.

[39] C. Birchler, S. Khatiri, B. Bosshard, A. Gambi, and S. Panichella, “Machine learning-based test selection for simulation-based testing of self-driving cars software,” Empir. Softw. Eng., vol. 28, no. 3, 2023, doi: 10.1007/s10664-023-10286-y.

[40] A. M. Thakur et al., “Towards a Software Development Framework for Interconnected Science Ecosystems,” Commun. Comput. Inf. Sci., vol. 1690 CCIS, no. July, pp. 206–224, 2022, doi: 10.1007/978-3-031-23606-8_13.

[41] P. Pham, V. Nguyen, and T. Nguyen, “A Review of AI-augmented End-to-End Test Automation Tools,” ACM Int. Conf. Proceeding Ser., 2022, doi: 10.1145/3551349.3563240.

[42] E. Mosqueira-Rey, E. H. Pereira, D. Alonso-Ríos, and J. Bobes-Bascarán, “A classification and review of tools for developing and interacting with machine learning systems,” Proc. ACM Symp. Appl. Comput., pp. 1092–1101, 2022, doi: 10.1145/3477314.3507310.

@article{1707064,
      author = {Gireesh Kambala},
      title = {Intelligent Software Agents for Continuous Delivery: Leveraging AI and Machine Learning for Fully Automated DevOps Pipelines},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {8},
      number = {1},
      pages = {662-670},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707064.pdf},
      abstract = {The contribution of intelligent software agents, artificial intelligence (AI), and machine learning (ML) in allowing totally automated DevOps pipelines for continuous delivery is investigated in this review paper. Organisations may automate important software development lifecycle activities?including code integration, testing, deployment, and monitoring?by combining artificial intelligence and machine learning technology. The study looks at the advantages of automation?that is, more efficiency, less time-to-market, better software quality, and proactive issue prediction and resolution capacity. Emphasising key technologies like predictive analytics, intelligent monitoring, and autonomous rollback systems, we show how they maximise DevOps practices. Furthermore covered in the paper are the difficulties integrating several technologies, controlling data quality, and guaranteeing scalability in automated pipelines. It offers chances to enhance cooperation among teams for operations, quality assurance, and development. In the end, our work emphasises how intelligent software agents may transform DevOps, boost output, and inspire software delivery innovation.},
      keywords = {Drug abuse, Relationships, Deterioration, Familial bonds, Mechanisms},
      month = {July},
  }