Lin Sun

As AI agents move into production, engineering teams face a growing set of challenges. How do you secure and govern MCP servers without modifying them? Route and fail over across multiple LLM providers? Enforce rate limits, access controls, and governance policies? Observe agent traffic, and scale...

AI agents are rapidly evolving from chatbots into autonomous systems that use tools, collaborate with other agents, and interact with enterprise data. But as their capabilities grow, so do the operational challenges. How do you know which agent consumed your AI tokens? Which tools were invoked? How...

Large Language Models (LLMs) have become the backbone of modern AI applications, but serving them efficiently and reliably at scale remains a major challenge. Traditional approaches to API serving, built around HTTP or gRPC traffic, do not adequately address the unique requirements of LLM inference...

Sidecar-less functionality has emerged as an alternative approach in service mesh architectures, addressing concerns related to costs and complexity associated with sidecars.