VeraTalk to us

Research

Vera is built on years of research into how agents write and run cloud infrastructure

  • Cloud Infrastructure Management in the Age of AI Agents

    • arXiv 2025
    • Position paper

    Zhenning Yang, Archit Bhatnagar, Yiming Qiu, Tongyuan Miao, Patrick Tser Jern Kon, Yunming Xiao, Yibo Huang, Martin Casado, Ang Chen

    Makes the case for AI agents that automate cloud infrastructure management, studying how agents perform across SDKs, CLIs, Infrastructure-as-Code and web portals, and outlining the research challenges ahead.

  • IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs

    • NeurIPS 2024
    • Datasets and Benchmarks Track
    • Benchmark

    Patrick Tser Jern Kon, Jiachen Liu, Yiming Qiu, Weijun Fan, Ting He, Lei Lin, Haoran Zhang, Owen M. Park, George S. Elengikal, Yuxin Kang, Ang Chen, Mosharaf Chowdhury, Myungjin Lee, Xinyu Wang

    The first benchmark for LLM-generated Infrastructure-as-Code: 458 human-curated scenarios across Amazon Web Services (AWS), each with an intent specification to verify the generated program.