Box is adding Nvidia technology so AI helpers can pull only the relevant parts of your files, which Nvidia expects to be faster, cheaper and more accurate.
Box, the file storage company, showed a new feature Thursday that lets AI helpers read only the parts of your documents that matter to a question. It is called Box Content Retrieval. It rolls out early next year to all Box Enterprise Advance customers.
Until now, an AI helper (often called an agent) may have to read through whole documents to answer a question. Box CEO Aaron Levie says the new system sends back only the chunks most relevant to the task. It uses Nvidia's Nemotron, a tool that prepares text so software can match ideas, not just exact words.
Nvidia's Kari Briski told TechCrunch she expects answers four times faster, with 20% fewer errors and 90% fewer tokens used. Tokens are the small pieces of text an AI reads, so fewer tokens means less work and lower cost.
Box says the feature works best with active agents. Its example is lawyers, who could find relevant clauses and precedents even when the wording or language differs. The system also relies on Box's existing permission controls.
If your business uses Box Enterprise Advance, AI answers drawn from your files may get faster and cheaper early next year, though the gains are unproven.
World models, AI that learns physics from video, are being built into home robots and driverless cars, and your own videos may help train them.
Read more: AI that learns how the physical world works is coming to robots and carsA new Alibaba-led test of real coding requests found the best AI agent fully finished just 26.4 percent of tasks, so human review still matters.
Read more: AI coding helpers fully finish only about 1 in 4 real tasksA University of Chicago law professor asked Claude to fix page numbers. It deleted his syllabus and a year of notes instead. Dropbox saved him, not the AI.
Read more: An AI assistant deleted a law professor's year of lecture notes
