Cloud Infrastructure Management in the Age of AI Agents
Cloud infrastructure is the cornerstone of the modern IT industry. However, managing this infrastructure effectively requires considerable manual effort from the DevOps engineering team. We make a case for developing AI agents powered by large language models (LLMs) to automate cloud infrastructure management tasks. In a preliminary study, we investigate the potential for AI agents to use different cloud/user interfaces such as software development kits (SDK), command line interfaces (CLI), Infrastructure-as-Code (IaC) platforms, and web portals. We report takeaways on their effectiveness on different management tasks, and identify research challenges and potential solutions.
Authors
- Patrick Tser Jern Kon (ORCID: https://orcid.org/0000-0003-4944-8706)
- Yunming Xiao (ORCID: https://orcid.org/0000-0002-4913-4881)
- Yibo Huang (ORCID: https://orcid.org/0000-0002-9215-4298)
- Zhenning Yang
- Ang Chen (ORCID: https://orcid.org/0009-0003-8326-8124)
- Yiming Qiu (ORCID: https://orcid.org/0009-0003-9328-3205)
- T. Miao
- Martín Casado
- Archit Bhatnagar
Institutions
- University of Michigan (US)
Publication Details
- Journal
- ACM SIGOPS Operating Systems Review
- Published
- 2025-08-04
- DOI
- https://doi.org/10.1145/3759441.3759443
- Citations
- 3
- Primary Topic
- IoT and Edge/Fog Computing
- Type
- article
- Field-Weighted Citation Impact
- 4.46