AWS for Industries
Author: Min-Oh Heo
Min-Oh Heo has worked as an AI Research Scientist and Engineer. He currently leads the Language AI Technology Team, focusing on LLM-centered technology development for internal needs and B2C service development for Hyundai Motor Group (HMG). Recently, he has been particularly interested in approaches that empower developers at Hyundai AutoEver to leverage AI on their own, beyond just solving problems directly.
Hyundai AutoEver: Building a multi-tenant generative AI sandbox and production AIOps on Amazon Bedrock
This post is a technical deep dive. It explains the Sandbox’s multi-tenant isolation model along with its inherited security and cost controls. It then examines two production-grade multi-agent AIOps systems our teams built on top of it, including the LangGraph (an open source multi-agent orchestration framework) state model, Retrieval-Augmented Generation (RAG) design, OpenSearch query patterns, parallel root cause analysis (RCA) with self-falsification, and the human-in-the-loop safeguards that help make agentic recovery safe in production. Code samples are illustrative and simplified for readability.