NEWS · COMPANIES · #3143
Box integrates Nvidia’s Nemotron embeddings into Box Content Retrieval for agent-first search
At its developer conference, Box announced Box Content Retrieval, a new feature that embeds Nvidia’s Nemotron embedding models into the core of its product to improve agent-driven queries. Box says the feature — available to Enterprise Advance customers early next year — will yield faster, more accurate and cheaper queries; Nvidia’s Kari Briski told TechCrunch she expects up to ~4x faster responses, ~20% fewer errors and ~90% fewer tokens used.
KEY POINTS
- At its developer conference, Box announced Box Content Retrieval, a new feature that embeds Nvidia’s Nemotron embedding models into the core of its product to improve agent-driven queries.
- Box says the feature — available to Enterprise Advance customers early next year — will yield faster, more accurate and cheaper queries; Nvidia’s Kari Briski told TechCrunch she expects up to ~4x faster responses, ~20% fewer errors and ~90% fewer tokens used.
- Integrating open-weight Nemotron embeddings into Box's retrieval pipeline directly targets agent-driven enterprise search, promising measurable gains in speed, cost and relevance while leveraging Box's metadata and permissions.
WHY IT MATTERS
Integrating open-weight Nemotron embeddings into Box's retrieval pipeline directly targets agent-driven enterprise search, promising measurable gains in speed, cost and relevance while leveraging Box's metadata and permissions.