Agentic AI in Enterprise Software Engineering: Multi-Agent Frameworks for Autonomous Development Workflows
Keywords:
agentic AI, software engineering, LangGraph, MCP, multi-agent systems, code review automation, RAG, enterprise AI governanceAbstract
Software engineering organizations face a persistent productivity constraint: the routine cognitive and coordination tasks that constitute a substantial portion of development effort — code review, test generation, documentation, sprint planning, and incident triage — consume engineering attention that organizations would prefer to allocate toward design and innovation. Agentic AI systems, which combine large language model reasoning with tool access and stateful orchestration, offer a mechanism for automating these activities at production scale. This paper presents a multi-agent framework for enterprise software engineering that specifies six agent roles, their input-output contracts, human handoff triggers, and governance requirements. The framework is implemented using LangGraph for agent orchestration and Model Context Protocol (MCP) for tool connectivity to development infrastructure including Jira, Confluence, GitHub, PagerDuty, and monitoring systems. A production deployment study across an eight-team software engineering organization at a healthcare SaaS company demonstrates substantial improvements in sprint velocity, code review cycle time, and documentation coverage. The paper also proposes a governance architecture that maintains human override authority, provides explainability through reasoning traces, and enforces security boundaries between agentic read and write access across environments.
Downloads
References
D. Forsgren, J. Humble, and G. Kim, Accelerate: The Science of Lean Software and DevOps. Portland: IT Revolution, 2018.
Stack Overflow, "Developer survey 2023," Stack Overflow, 2023. [Online]. Available: https://survey.stackoverflow.co/2023/
E. Murphy-Hill, T. Zimmermann, C. Bird, N. Nagappan, W. Begel, and J. Czerwonka, "Cowboys, ankle sprains, and keepers of quality: How is video game development different from software development?" in Proc. 36th Int. Conf. Softw. Eng. (ICSE), 2014.
A. Kapoor and B. Narayanan, "LangGraph: Building stateful multi-actor applications with LLMs," LangChain Blog, 2024. [Online]. Available: https://blog.langchain.dev/langgraph/
Anthropic, "Model Context Protocol: Open standard for connecting AI assistants to the systems where data lives," 2024. [Online]. Available: https://modelcontextprotocol.io
M. Chen et al., "Evaluating large language models trained on code," arXiv preprint arXiv:2107.03374, 2021.
A. Ziegler, E. Kalliamvakou, X. A. Li, A. Rice, D. Rifkin, S. Simister, G. Sittampalam, and E. Aftandilian, "Productivity assessment of neural code completion," in Proc. 6th ACM SIGPLAN Int. Symp. Mach. Program., 2022. doi: 10.1145/3520312.3534864
L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin et al., "A survey on large language model based autonomous agents," Frontiers of Computer Science, vol. 18, no. 6, pp. 186345, 2024. doi: 10.1007/s11704-024-40231-1
C. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan, "SWE-bench: Can language models resolve real-world GitHub issues?" in Proc. 12th Int. Conf. Learn. Represent. (ICLR), 2024.
P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Kuttler, M. Lewis, W. Yih, T. Rocktaschel et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," in Advances in Neural Information Processing Systems, vol. 33, 2020.
D. Cinkusz and K. Chudziak, "Towards LLM-Augmented Multiagent Systems for Agile Software Engineering," in Proc. 39th IEEE/ACM Int. Conf. Autom. Softw. Eng. (ASE), 2024. doi: 10.1145/3691620.3695336
NIST, "Artificial intelligence risk management framework (AI RMF 1.0)," Natl. Inst. Stand. Technol., Gaithersburg, MD, USA, NIST AI 100-1, 2023. doi: 10.6028/NIST.AI.100-1
D. Schaul, J. Quan, I. Antonoglou, and D. Silver, "Prioritized experience replay," arXiv preprint arXiv:1511.05952, 2016.
O. Vinyals, M. Fortunato, and N. Jaitly, "Pointer networks," in Advances in Neural Information Processing Systems, vol. 28, 2015.
S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. doi: 10.1162/neco.1997.9.8.1735
T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv:1301.3781, 2013.
J. Pennington, R. Socher, and C. Manning, "GloVe: Global vectors for word representation," in Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP), 2014, pp. 1532-1543. doi: 10.3115/v1/D14-1162
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436-444, 2015. doi: 10.1038/nature14539
R. Sutton and A. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA: MIT Press, 2018.
D. Silver et al., "Mastering the game of Go with deep neural networks and tree search," Nature, vol. 529, pp. 484-489, 2016. doi: 10.1038/nature16961
V. Mnih et al., "Human-level control through deep reinforcement learning," Nature, vol. 518, pp. 529-533, 2015. doi: 10.1038/nature14236
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
