Use Case Intelligence RSS Search use cases Search
Google Cloud Software / SaaS United States

BOX

Enterprise Knowledge Search

The biggest agentic AI challenge they face, according to Kus, is that AI agents can't keep secrets.

Read the original story Explore all use cases
Over 100,000 global companies work with Box to transform how they work with data
Today, over 100,000 companies trust Box to get more from their data. The biggest agentic AI challenge they face, according to Kus, is that AI agents can't keep secrets. If AI agents have access to data, they'll try to use it. That's where…

Reported impact

Business outcome

Over 100,000 global companies work with Box to transform how they work with data; AI built with Gemini for its intelligence, accuracy, speed, and cost-efficiency

  • Cost Reduction
  • Customer Experience
  • Productivity Improvement
  • Revenue Growth

Solution

The biggest agentic AI challenge they face, according to Kus, is that AI agents can't keep secrets. Box supports all of the latest frontier AI models, but Gemini, accessed through Gemini platform , has been part of the stack powering Box AI since the beginning. "We've always been impressed by Gemini, as it's not only one of the best models in terms of the… Additionally, Box uses BigQuery extensively for reporting and processing the structured aspects of unstructured data, leveraging native integrations to Gemini platform. Key components include Gemini platform coordinates multi-agent workflows, tool calling, and governed automation across the application; BigQuery stores and queries the analytics and AI-ready datasets that power the workload. Reported outcomes include Over 100,000 global companies work with Box to transform how they work with data; AI built with Gemini for its intelligence, accuracy, speed, and cost-efficiency.

Solution architecture

2 components · 2 layers
  1. Storage
    • BigQuery Stores and queries the analytics and AI-ready datasets that power the workload.
  2. Orchestration
    • Gemini platform Coordinates multi-agent workflows, tool calling, and governed automation across the application.

Architecture clues

  • AI agents have massive potential to benefit businesses, including the ability to rapidly extract essential insights from vast quantities of a company's own data. According to Ben Kus, CTO at Box, the key to unlocking…
  • The AI agents can automatically pull structured data from unstructured files, populate other corporate systems, and trigger new workflows. They can also create new documents based on results and save them back into Box.
  • Today, over 100,000 companies trust Box to get more from their data. The biggest agentic AI challenge they face, according to Kus, is that AI agents can't keep secrets. If AI agents have access to data, they'll try to…
  • With Google Cloud, Box is building the best possible platform to help customers get the most out of their unstructured data through AI.
  • models . The agents authenticate to the company's Box instance so the employees can quickly and safely tap into insights from troves of unstructured data across the organization's files, folders, and Box Hubs—all within…

Evidence from the source

"We're a big fan of democratizing agents," explains Kus. "Companies that have the most success with AI tend to be ones where innovation comes from those doing the work. Those employees know their own pain points and can…
AI built with Gemini for its intelligence, accuracy, speed, and cost-efficiency
Box builds its customizable AI and AI agents with Google Cloud to democratize the power of AI into workers' hands.
Over 100,000 global companies work with Box to transform how they work with data
Today, over 100,000 companies trust Box to get more from their data. The biggest agentic AI challenge they face, according to Kus, is that AI agents can't keep secrets. If AI agents have access to data, they'll try to…
With Google Cloud, Box is building the best possible platform to help customers get the most out of their unstructured data through AI.
Transparency Evidence & methodology 87/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value87/100
  • Problem clarity12/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Google Cloud

    BOX customer story

    First-party
    https://cloud.google.com/customers/box-ai
    Source type
    Vendor-published customer story
    Published
    Nov 1, 2023
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Nov 1, 2023 · Google Cloud Press Corner · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Google Cloud Archived · Jul 31, 2026 Aible Software / SaaS United States Aible needed to deploy secure enterprise AI agents quickly while keeping customer data inside each enterprise cloud boundary, avoiding idle GPU cost, and proving that large-scale analytics and model orchestration could… 1000x analytics cost efficiency gain Enterprise Knowledge SearchReal-time Analytics BigQuery · Cloud Run · G4 GPUs Google Cloud Archived · Jun 30, 2026 Growth Protocol Software / SaaS United States Growth Protocol needed to build an enterprise reasoning platform for regulated industries that could combine large-scale data pipelines with deterministic recommendations while guaranteeing zero data retention for… grew 5x Enterprise Knowledge SearchReal-time Analytics BigQuery · Cloud Run · Gemini Google Cloud Archived · Jun 17, 2026 Syft Software / SaaS Singapore The cost of running deep research on every news channel created a financial barrier that would have forced the company to restrict access to a wealthy niche, directly contradicting its mission to democratize information. Enterprise Knowledge Search BigQuery · Firebase · Gemini models