Every engagement gets written up: the state we found, what we built, what changed, and what is still open. Research covers the parts of the problem that come up on every project.
Every operation has documentation that stopped being true at some point. This is a method for finding that point: extracting entities from records, building a graph of what should be, and reading the divergences against what is.
The pilot worked. A year later nothing is in production. The failure is almost never model quality. It is data nobody owns, permissions nobody granted, and a workflow nobody changed.
A seaweed supply operation running from Korean farms and factories to U.S. warehouses kept its truth in four disconnected spreadsheets. Discovery found 25 places the sources disagreed and 34 questions nobody had answered.
A distributor rebuilt its product list by hand every morning because the same item was named differently on every supplier site. The fix was less about the crawler than about deciding when two names mean one product.
An agent browsing a site takes dozens of actions before anything succeeds or fails. Scoring only the ending teaches it very little. Our NeurIPS 2025 Spotlight paper builds a reward model that reads every step.
Decades of pages sat as scanned images on a server nobody queried. Turning them into records meant extraction, a human review queue and an audit trail, inside a network with no route to the outside world.
Retrieval demonstrations work on clean public documents. Company documents are scanned, inconsistent, contradictory and confidential. Notes on making source-grounded answering survive contact with a real internal archive.
Most operations software is bought before anyone has written down how the operation works. The mapping is the cheap part, it takes two weeks, and it usually changes what you were about to buy.