// AI news · 2026-11-05 · TechCrunch
Box integrates Nvidia's Nemotron for agent-first retrieval
Box integrates Nvidia's Nemotron embedding model into its content retrieval system, enabling faster, more accurate agent responses with up to four times faster query speeds, 20% fewer errors, and 90% fewer tokens.
Published 2026-11-05 22:00 (Beijing time)Source TechCrunchAuto-summarised, fact-checked against source
01Summary
The feature leverages semantic understanding beyond keywords, improving relevance in professional contexts like legal research and is set for rollout early next year to Enterprise Advance customers.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- Box integrates Nvidia's Nemotron embedding into its agent-first retrieval system.
- Queries are four times faster with 20% fewer errors and 90% fewer tokens.
- System relies on Box’s existing metadata and access controls.
- Enhances semantic search for professional use cases like legal precedent lookup.
03Source
Box taps Nvidia’s Nemotron for new agent-first content retrieval system
TechCrunch · published 2026-11-05 22:00 Beijing time
05Related news
- Same source · Meta Acquires AI Coding Startup Conductor2026-11-05 · TechCrunch
- Same source · Readwise launches app to challenge Kindle ecosystem2026-11-03 · TechCrunch
- Same topic · Hogwarts Legacy Gets NVIDIA DLSS 5 Upgrade2026-11-05 · NVIDIA Newsroom
- Same topic · NVIDIA's Full-Stack Codesign Boosts AI Memory Efficiency2026-11-06 · NVIDIA Newsroom
- Same day · Aina Launches Smart Ring to Control AI Agents2026-11-05 · WIRED
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-05 · Archive by date · All AI news · Today