Box integrates Nvidia Nemotron into new agent-focused retrieval system

Box has introduced Box Content Retrieval, a feature that incorporates Nvidia’s Nemotron embedding system into the company’s product. The tool is designed to help software agents respond to queries by using metadata generated from documents, rather than requiring an agent to process every document in full. Box says the approach can make searches faster, more accurate and less costly.

Kari Briski, Nvidia’s vice president of generative AI software, said the system is expected to deliver answers four times faster, with 20% fewer errors and 90% fewer tokens used. Box plans to make it available to all Enterprise Advance customers early next year. CEO Aaron Levie said the service can return the document sections most relevant to a query or an agent’s task.

The feature uses Nvidia’s Nemotron Embed project, which provides open-weight embedding models for automated retrieval. Box says it could help lawyers locate relevant clauses and precedents even when searches use different wording. The service also depends on Box’s existing metadata and permission controls, which the company says would make it difficult to reproduce independently.