Research

The long-form pieces. How we think about getting AI to work in places where the answer matters and the rules live in people’s heads.

Learning from corrections

When an expert overrides an AI system, that correction is not noise. It is a teacher. We study how to turn corrections into rules the system can apply next time, without retraining.

Context engineering

A model is only as good as what you put in front of it. We study how to pick the right context — the right documents, the right examples, the right structure — so accuracy comes from what the model sees, not how big it is.

Capturing how work actually happens

Operators rarely write down what they do. We study how to watch real work and turn it into rules an AI system can follow — no interviews, no workshops, no policy documents.

Specialization without retraining

Fine-tuning is expensive and hard to undo. We study how a living knowledge graph can turn a general-purpose model into a domain expert at the moment it answers, with no model weights touched.

Working on something similar?

We collaborate with researchers and teams building serious enterprise AI.

Get in touch