EIGAN
About

A two-person company, built around one question.

What is a language model actually doing, as opposed to what it says it is doing? Eigan builds tools to observe what models represent while they run, publishes the research behind them as open papers, code and data, and makes the results available to the security and regulated teams that host their own models.

Founders

The people behind Eigan.

Illustrated portrait of James R. A. Henry

James R. A. Henry

Co-founder · Research and Technical Lead

James leads Eigan’s research and core technology. He has spent more than twenty-five years in internet service provider engineering and security, first as a systems architect at a Canadian cable provider and then in telecommunications cyber threat intelligence. That work comes down to one question: what is the system actually doing, as opposed to what it reports?

Since August 2025 he has applied that question to language models. He is the sole author of three papers on how concepts form across the depth of transformer models and how to extract stable probes from them, and of the open reference implementation, concept-pair corpus and activation data they rest on. He is largely self-taught in machine learning research.

Illustrated portrait of George Henry

George Henry

Co-founder · Product and Commercial Lead

George leads product, commercial strategy and the regulated-market side of Eigan. He has eight years in technology as a product manager and holds an MBA, with earlier experience in manufacturing.

His product work includes regulated and surveillance products, through the shift from lexical to semantic systems, which is where Eigan’s customers in security and regulated industries work every day. He writes about the security and policy consequences of autonomous AI agents on the Eigan blog.