The Independent
Voice on AI

Shuhua Xu

Guest Author

Shuhua Xu is a Lead Data Engineer with 13 years of experience across data engineering and data science. He focuses on large-scale enterprise data platforms, distributed systems, LLMs, AI agents and AI-assisted engineering workflows. He has actively integrated LLMs into enterprise engineering workflows and has been involved in building multiple AI agents within his current organization.

Control layer

AI agents can be unpredictable. Your control layer shouldn't be.

In multi-agent systems, agents can be individually correct and still produce a wrong result when they work together. One agent’s output becomes another agent’s context. Information can be lost or misinterpreted during a handoff, shared state can drift, and agents can get stuck in loops or deadlocks. When several agents rely on the same underlying model, they may even reinforce the same mistakes rather than catch them.
Messy data

Enterprise AI agents are only as reliable as the messiest documents behind them

Enterprise AI has largely been built around context engineering. Teams connect enterprise systems, generate chunks and embeddings, build retrieval pipelines, and assemble the context needed by individual AI applications. While this approach works well for isolated assistants and copilots, it treats enterprise knowledge as application-specific context rather than a shared enterprise asset.