[3F1-GS-10] AI application: Language model

[3F1-GS-10-02] Automating Chaos Engineering with Large Language Models

〇Daisuke Kikuta¹, Hiroki Ikeuchi¹, Kengo Tajiri¹, Yuusuke Nakano¹ (1. Nippon telegraph and telephone corporation)

Keywords:LLM, Chaos Engineering, Communication Network

Chaos Engineering (CE) is an engineering technique that improves the resiliency of communication networks by intentionally injecting faults in the networks and taking precautions in advance. Although some CE tools partially automate the CE workflow, the parts that require try-and-error along with domain knowledge and text understanding remain manual. Here, we propose ChaosEater, a system for automating the entire CE workflow with Large Language Models (LLMs). In this paper, we share the architecture and experimental results demonstrating our system's effectiveness in automating the CE.