Box will give agents relevant document passages through Nemotron instead of making them read entire files
Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .
Corporate agents will be able to work with large document archives more cheaply and accurately while preserving existing access rights.
Box Content Retrieval builds Nvidia's open Nemotron embedding models into search across corporate content. The model converts documents into semantic representations in advance, while Box combines them with its metadata and access controls. An agent receives only the relevant passages rather than reading every file in full. The search can find related concepts even when different wording or another language is used. Nvidia expects responses to be delivered four times faster, with 20% fewer errors and 90% fewer tokens. The feature will become available to Enterprise Advanced customers in early 2027.
Sources 1