At its recent developer conference, Box unveiled a new feature that integrates Nvidia’s Nemotron embedding system directly into the core of its platform.
Known as Box Content Retrieval, this update enables agents to answer queries significantly more effectively by leveraging the metadata generated by Nemotron.
Box highlights improved speed, accuracy, and cost-efficiency for users. According to Nvidia’s VP of generative AI software, Kari Briski, queries will be answered four times faster, with 20% fewer errors and 90% reduction in token usage.
The feature is rolling out to Enterprise Advance customers early next year.
“This dramatically boosts both the relevance of our search technology for agents,” Box CEO Aaron Levie stated. “Instead of an agent having to kind of read through each document, we can send back chunks from the documents that are most relevant to the user’s query or whatever the task is that the agent is doing.”
This implementation relies on Nvidia’s Nemotron Embed project, which provides open-weight models to enhance automated retrieval systems.
While major labs frequently overlook embedding models—which use LLMs to pre-process data for better agent interaction—Nvidia has prioritized this area. Nvidia’s latest Nemotron release in July ranked first on the RTEB benchmark, a standard for measuring retrieval quality.
The system is particularly valuable when paired with active agents, such as lawyers who can now easily locate relevant clauses and precedents.
Because Nemotron’s embeddings map underlying concepts rather than just keywords, the search tool can surface related legal ideas even if the language differs.
Although the Nemotron models are freely available, the system depends heavily on Box’s existing metadata and permission controls, making it difficult to replicate from scratch. “We’re probably packing in five different technologies into one simple API,” Levie explained to TechCrunch.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.