Cloud Infrastructure Management in the Age of AI Agents
This addresses the challenge of reducing manual effort for DevOps teams, but it is incremental as it builds on existing AI and cloud technologies without introducing a new paradigm.
The paper tackles the problem of manual cloud infrastructure management by proposing AI agents powered by LLMs to automate tasks, reporting preliminary findings on their effectiveness across different interfaces like SDKs, CLIs, IaC platforms, and web portals.
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.