Skip to Content

William Du

Founding ML Engineer

William leads agentic evaluation and performance at Legion Intelligence. William dreams about auto-improving agent systems, ML system architectures and how to incorporate AI into user workflows seamlessly. Before Legion, William led applied machine learning teams and the technical roadmap for the natural-language model training platform at Primer. He’s most of his time thinking about how ML and AI can be deeply integrated into a product and how it can drastically improve day to day lives of the labor force.‍

No items found.
Back to blog
No items found.
Back to In The News
11 minute read

Why Retrieval Agents Fail: It’s Not Just the Model

Retrieval-focused agents fail for reasons beyond model capability. Performance is bounded by three independent constraints: the model, the retrieval stack, and prompt guidance. Evaluation finds the real bottleneck.
Back to Command Papers