Box taps Nvidia’s Nemotron for new agent-first content retrieval system
Reported by TechCrunch1 source ↓
Nvidia says Box Content Retrieval is expected to answer queries four times faster, with 20% fewer errors and 90% fewer tokens used.
Key points
- Box plans to roll out the feature to Enterprise Advance customers early next year
- Nvidia’s Kari Briski expects queries to use 90% fewer tokens and have 20% fewer errors
- The system uses Nemotron embeddings to help agents retrieve relevant document content
Details
TechCrunch reports that Box demonstrated Box Content Retrieval at its developer conference. The feature integrates Nvidia’s Nemotron embedding system into Box, using metadata to return relevant document excerpts for agent queries.
Nvidia vice president of generative AI software Kari Briski told TechCrunch she expects queries to be answered four times faster, with 20% fewer errors and 90% fewer tokens used. These are expected results, not reported measurements of the launched system.
Box says the feature will be available to all Enterprise Advance customers, with rollout planned for early next year. Box says its existing metadata and permission controls are also part of the system.
Written from coverage as of
Images
- TechCrunch
Stocks in this story
Change since open: 20 Nov to 21 Nov 2026
Last refresh