Box taps Nvidia’s Nemotron for new agent-first content retrieval system
Summary
- Box announced a new agent-first content retrieval system integrating Nvidia's Nemotron embedding models.
- The feature, called Box Content Retrieval, aims to enable faster, more accurate, and less token-intensive queries for enterprise agents.
- According to Nvidia, the system is expected to answer queries four times faster with 20% fewer errors and 90% fewer tokens used.
- The feature will roll out early next year to all Box Enterprise Advance customers.
Why it matters
Integrating open-weight embedding models like Nvidia's Nemotron into enterprise platforms significantly enhances AI agent efficiency and retrieval accuracy, reducing computational costs for businesses.