# Box taps Nvidia’s AI models to build a rich context layer for autonomous enterprise agents

Digest AI · Enterprise & Industry · published 2026-11-05T06:00:00Z · updated 2026-11-05T14:00:00Z

Canonical: https://digestai.news/story/box-taps-nvidias-ai-models-to-build-a-rich-context-layer-for-autonomou

## Summary

Box Inc. announced a new partnership with Nvidia Corp. at its BoxWorks 2026 conference, unveiling a retrieval engine called Box Content Retrieval powered by Nvidia’s Nemotron Retriever embedding models. The engine turns unstructured enterprise data into a structured knowledge base, improving search accuracy by 20% and cutting token consumption by up to 90%, which can speed agent response times by about four‑times. The partnership also brings Nvidia’s open‑weight models, including the Nemotron 3 Ultra large‑language model, into Box AI, offering cheaper alternatives to proprietary models.

Box added an orchestration tool for multistep agentic workflows and new threat‑detection features that flag rogue agent activity in real time. The Nemotron models and security controls are immediately available to Enterprise Advanced and Shield customers, while the full context retrieval and threat‑detection features are slated for general availability early next year.

## Key points

- Box launches Box Content Retrieval engine powered by Nvidia’s Nemotron Retriever models.
- Search accuracy improved by 20%, token consumption reduced by up to 90%.
- Nemotron 3 Ultra open‑weight LLM available in Box AI for enterprise customers.

## Why it matters

Providing a secure, permission‑aware context layer lets autonomous agents work reliably in enterprises, boosting trust and adoption while cutting costs with open‑weight models.

## Sources

1. [Box taps Nvidia’s AI models to build a rich context layer for autonomous enterprise agents](https://siliconangle.com/2026/11/05/box-taps-nvidias-ai-models-to-build-a-rich-context-layer-for-autonomous-enterprise-agents) (siliconangle.com, 2026-11-05)
2. [Box taps Nvidia’s Nemotron for new agent-first content retrieval system](https://techcrunch.com/2026/11/05/box-taps-nvidias-nemotron-for-new-agent-first-content-retrieval-system) (TechCrunch AI, 2026-11-05)

## Cite

Digest AI, "Box taps Nvidia’s AI models to build a rich context layer for autonomous enterprise agents", 5 November 2026, https://digestai.news/story/box-taps-nvidias-ai-models-to-build-a-rich-context-layer-for-autonomou

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/box-taps-nvidias-ai-models-to-build-a-rich-context-layer-for-autonomou.json