Box
Also known as: Box Agent, Box AI Studio, Box AI
Intelligent Content Management platform whose Box Agent reasons over a company's unstructured content to search, analyze, and generate files across multi step tasks, paired with the Box AI Studio agent builder, all grounded in authorized content with enterprise security, model choice, and an MCP server.
Box is an intelligent content management platform that has built its agent layer on top of the content it already stores. The Box Agent takes natural language instructions and works across a company's files. It searches what the user is permitted to see, analyzes and synthesizes across large document sets, and generates new files in Box Notes, Word, PDF, Excel and PowerPoint. A Pro Mode adds deeper recursive reasoning, and an Expanded Mode allows larger context.
Box AI Studio is the agent builder, available on Enterprise Advanced. An admin gives an agent a name and description, custom instructions that set its reasoning style and can enforce step by step workflows, and knowledge bindings to named files or Hubs referenced with @mentions, including priority rules when sources conflict. Instructions cannot override human approval workflows, break safety policies enforced in code, reach restricted classifications, or force a tool the user's permissions block.
Admins choose the model per agent, selecting Auto or a provider from the list approved for their organization, and restrict what the agent may do, including read, write, move, delete, share and email. Before release, agents are exercised in a Playground against real content, and an agent's availability across AI Home, Files and Hubs expands as it passes evaluation tests for more complex knowledge configurations.
Everything runs inside Box's permission model. Answers come only from content the user may see, classification and retention rules apply, responses cite their sources, and customer data is not used to train third party models.
Admins watch usage through AI Insights in the Admin Console, with queries over time, usage by product, top agents by usage and downloadable activity reports by user and by agent, alongside audit trails for more than 300 actions. Box Zones gives customers a choice of storage region across ten regions.
Box holds FedRAMP certification, meets ISO 27001 and PCI DSS Level 1, reports SOC 1/2/3, and maintains HIPAA and ISO 27018 compliance. External agents reach Box content through a Box MCP server.
Box agents act on content and do not drive a browser or desktop. Agent capabilities sit on the Enterprise Plus and Enterprise Advanced plans.
Vendor details
Canonical URL
https://www.box.com
Category
Enterprise operations agent
Subcategory
AI agents and agent builder for enterprise content
Funding status
Independent and publicly traded on the New York Stock Exchange under the ticker BOX, headquartered in Redwood City, California, founded in 2005 by chief executive Aaron Levie and Dylan Smith. Box serves leading global organizations including JLL, Morgan Stanley, and Nationwide, was named a Leader in the 2026 Gartner Magic Quadrant for Document Management, and made the Box Agent generally available in April 2026 as part of a broad transformation into an AI powered enterprise content platform.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Box serves a Box MCP server so external platforms, including Claude, Microsoft Copilot, GitHub Copilot, Glean and custom LLMs, can reach Box content under the user's permissions. It also publishes a developer platform with APIs and an AI Studio API. Agents act on content inside Box and generate files in Box Notes, Word, PDF, Excel and PowerPoint. No integrations reach systems outside Box, such as a CRM or a ticketing system.
In practice
Your team wastes hours hunting through thousands of files and manually reviewing contracts. The Box Agent searches your permitted content, compares contracts against standard terms, flags the exceptions that matter, and cites every source.
You want custom AI agents for repeatable, high stakes work but cannot risk them touching the wrong data. Box AI Studio lets admins scope agents to approved files, set action guardrails, choose the model, and validate behavior in a Playground before rollout.
You need to answer a fifty page RFP fast without leaking sensitive material. The Box Agent autonomously searches your compliance guides and whitepapers, drafts a grounded response in minutes, and works only from content the user is authorized to access.
Sources & related URLs
Research sources
Agentic Index coverage score
10.5 / 14 capabilities · 75%
| Integrations & Tool Calling | Full |
|---|---|
|
Box agents act on enterprise content, and they write as well as read. They search, analyze and create files in Box Notes, Word, PDF, Excel and PowerPoint, with availability set across AI Home, Files and Hubs, and permissions gate every action. Box serves a Box MCP server so external platforms reach Box content, publishes an AI Studio API and a developer platform, and custom agents can query images and spreadsheets. No integrations reach systems outside Box, such as a CRM or a ticketing system, so what the agents act on is content and the platform around it. Sourcebox.com/agents, /ai/ai-studio (index copies); docs.box.com/en/box-ai/creating-and-configuring-agents; readread 2026-09-17 |
|
| Workflow Orchestration | Full |
|
Custom instructions and modes drive multi step work. Instructions can enforce step by step workflows, such as first analyze, then propose, then act, direct the agent to favor certain tools when several are available, and specify structured output. Pro Mode supports advanced agent behaviors such as recursive reasoning and enhanced document or video analysis, and Expanded Mode lets queries exceed standard limits. The Box Agent completes multi step tasks across content, locating files, analyzing large document sets and generating new files, iterating in agentic loops. There is no workflow surface with branches and retries, no versioning is described, and whether Box Automate workflows can invoke an agent step is not stated. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents; box.com/agents (index copy); readread 2026-09-17 |
|
| Knowledge Grounding & RAG | Full |
|
Agents are grounded in specific, permission aware content. An agent's Knowledge setting binds it to specific files, or Hubs for reference. Knowledge sources are referenced with @mentions in custom instructions, with explicit priority rules when they conflict, such as a single source of truth, or ProductSpecs highest, ReleaseNotes second and FAQ lowest, which keeps agents grounded in authoritative sources. Box AI pulls information only from the document loaded in preview and tells the user when a question falls outside it. AI Studio grounds agents in specific, admin-approved files or Hubs to reduce hallucinations, responses cite their sources, and custom agents can query images and spreadsheets. Hubs act as bindable, maintained knowledge scopes over the customer's content, and how Hub contents refresh is not described. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents; box.com/ai/ai-studio, /agents (index copies); readread 2026-09-17 |
|
| Human Oversight & Guardrails | Full |
|
Admins set guardrails on each action, and agents cannot override approval workflows. AI Studio governance applies policy-based guardrails on actions, validates inputs for prompt injection and keeps humans accountable for consequential decisions, and admins can restrict actions such as read, write, move, delete, share and email and switch capabilities such as search and content creation on or off. Custom instructions cannot override human approval workflows, break safety policies enforced in code, access restricted data or classifications, or force tool execution when permissions block them, and instructions can tell the agent to prioritize verification before responding or to ask when unsure. Where an approval step is configured or how it is routed is not described. Sourcebox.com/ai/ai-studio (index copy); docs.box.com/en/box-ai/creating-and-configuring-agents; readread 2026-09-17 |
|
| Security, Identity & Governance | Full |
|
Box holds a FedRAMP Class D certification, previously described as FedRAMP High authorized, meets FedRAMP, FIPS 140-2, ISO 27001 and PCI DSS Level 1 standards, maintains certified compliance with HIPAA/HITECH and ISO 27018, and reports SOC 1/2/3. Its information security management system is based on ISO 27001 and NIST 800-53, with SOC reports available under NDA. Agents answer only from content the user may see and respect existing permissions, classification and retention by default. AI Studio admins restrict agent actions, including read, write, move, delete, share and email, scope knowledge to named files or Hubs, control where an agent appears, and manage which users may use it. Box states customer data is not used to train third party models. Sourcebox.com/trust, /fedramp, /security/information-governance (index copies); docs.box.com/en/box-ai/creating-and-configuring-agents; readread 2026-09-17 |
|
| Observability & Auditability | Partial |
|
Admins see AI usage by agent and by user, but not a step by step record of each agent run. Admin AI Insights adds an AI usage dashboard in the Admin Console with AI queries over time, AI usage by product, and top agents by usage, both chargeable and non chargeable. Admins can download detailed user activity reports that break down unit spend by individual user or specific agent, and the Admin Console carries extensive audit trails for more than 300 actions. AI Studio governance includes maintaining audit trails and logs, and the AI Unit insight card runs about two hours behind. There is no per run trace of an agent's steps, tool calls or retrieved content. Citations show the sources behind an answer. Sourceblog.box.com/introducing-admin-ai-insights, box.com/security/it-admin-controls (index copies); docs.box.com/en/box-ai/understanding-ai-units-in-box; readread 2026-09-17 |
|
| Memory & State Persistence | Not documented |
|
Whether Box agents keep memory is not settled. The agent configuration covers details, custom instructions, knowledge, suggested prompts, availability, advanced model settings, Pro Mode and Expanded Mode, and none of these is a memory, session state or learned context surface. The AI Studio and Box Agent material describes grounding and modes and names no memory. Agents ground in enterprise content on each run. Box's AI documentation runs to several hundred pages, so a memory feature could sit somewhere not covered here. Nothing published describes Box Agent session history or a memory store with a stated scope and lifetime. Sourcedocs.box.com/llms.txt, /en/box-ai/creating-and-configuring-agents; tried; docs.box.com/_llms/en/ai.mdread 2026-09-17 |
|
| Deployment & Data Residency | Full |
|
Customers choose the region where their content is stored. Box Zones expanded to 10 regions, adding Switzerland, Singapore and Israel. Box is managed cloud with that regional choice, there is no on premises or customer cloud deployment, and the other seven regions are not named. Sourcebox.com/security/it-admin-controls and Box Zones announcement (index copies); readread 2026-09-17 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Admins get a builder for their own agents. AI Studio starts from New Agent, where the admin supplies a name, custom instructions, knowledge bindings, up to four suggested prompts, availability and model settings. Box lists example use cases a customer could build, such as extracting NDAs and liabilities from data room documents or pulling KYC details from onboarding forms. There is no prebuilt agent set, template gallery or catalog. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents; box.com/ai/ai-studio (index copy); readread 2026-09-17 |
|
| Triggers & Channel Coverage | Partial |
|
Every way into a Box agent is a person asking. Agents appear where admins publish them, in AI Home, Files and Hubs, and answer when a user asks, with suggested prompts to start an interaction. Box Automate and Relay trigger content workflows on content events, but no Box Automate workflow is described invoking an agent step, and no schedule, event or telemetry trigger starts an agent. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents; box.com/agents (index copy); readread 2026-09-17 |
|
| Model Flexibility & Routing | Full |
|
Admins choose the model for each agent. In an agent's Advanced settings, they select Auto or a model from the list of other providers available in the organization. Pro Mode is on by default, so the agent uses higher thinking levels and may access more capable and newer models, and Box's AI units guidance recommends Standard models or Auto for routine work and Premium models for complex reasoning. Models come from leading providers such as Anthropic, Google and OpenAI. Bringing your own model or customer hosted inference is not offered, and choice is from Box's provider list. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents, /en/box-ai/understanding-ai-units-in-box; box.com/ai/ai-studio (index copy); readread 2026-09-17 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Outside agents can reach Box content, and Box publishes developer APIs. Box-native agents run in Box Agent and Box AI Studio, and third-party platforms, including Claude, Microsoft Copilot, GitHub Copilot, Glean and custom LLMs, access Box content through the Box MCP server. Box also publishes a developer platform (developer.box.com) with APIs and an AI Studio API, and agents generate files in Box Notes, Word, PDF, Excel and PowerPoint for use elsewhere. Box agents consuming external MCP tools is not described. Sourcebox.com/ai/ai-studio, /agents (index copies); readread 2026-09-17 |
|
| Testing, Debugging & Optimization | Full |
|
Agents are tested before release, and evaluation tests gate where they can be published. AI Studio includes a Playground where admins validate behavior, refine instructions and confirm grounding before broader deployment, using custom suggested prompts against real Box content and swapping models in the same session. Availability expands as an agent passes evaluation tests for increasingly complex knowledge configurations, from single files to multiple files and Hubs, so passing those tests is the release path. The evaluation tests are not described in detail, and no scored regression suite is published. Sourcedocs.box.com/en/box-ai/creating-and-configuring-agents; box.com/ai/ai-studio (index copy); readread 2026-09-17 |
|
| Browser & Computer Use | Not documented |
|
Box agents work on content, not screens. They search permitted files, analyze document sets and generate files inside Box, and external systems reach Box through its MCP server. There is no browser, desktop or screen control, since the agent's tools are content operations, so breakage when an interface changes is not a concern. Sourcebox.com/agents, /ai/ai-studio (index copies); docs.box.com/en/box-ai/creating-and-configuring-agents; readread 2026-09-17 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
The new MCP Server Platform Activity report in Box gives admins platform level visibility into what content in Box is being used through the Box MCP Server, alongside the tool level tracking in the existing report. That report is renamed the MCP Server Tool Calls report and keeps its event level data by integration and user.
Bears on: Security / enterprise
View sourceValues extracted by Box Extract agents now come with citations in Box Preview, so clicking one jumps to the exact spot in the original file and highlights the source text. When a reviewer edits or deletes a value, its highlight disappears, so the field reads as confirmed by a person rather than generated.
Bears on: Human approval / guardrails
View sourceBox introduced Doc Split APIs to divide a PDF into separate documents and save them to a chosen Box folder. Manual mode uses explicit page ranges, while smart mode interprets natural language instructions such as splitting at QR code separators or isolating signature pages. The asynchronous API creates a job through POST /2.0/document_splits and exposes its status and generated files through a GET endpoint. Requests use API version 2026.0, and smart splits consume one AI Unit per four pages.
Bears on: Workflow orchestration
View sourcePricing
Public per user plans, from Business Starter at $5 per user per month billed annually. The Box Agent requires Enterprise Plus at $50 per user per month billed annually, or Enterprise Advanced, which is quoted.
Per user plans, with the Box Agent and Box AI Studio gated to Enterprise Plus and Enterprise Advanced.
What is public
Box publishes per user Business plans and prices Enterprise Plus, the first plan with the Box Agent, at $50 per user per month billed annually. AI Studio needs Enterprise Advanced, which is quoted rather than listed.
Billing mechanics
Per user subscription plans, with the Business tiers and Enterprise Plus published. The Box Agent comes with Enterprise Plus and Enterprise Advanced, and Box AI Studio with Enterprise Advanced, the one quoted tier.
Cost watchouts
The Box Agent and AI Studio are gated to the Enterprise Plus and Enterprise Advanced tiers, and file creation and Pro and Expanded modes are beta or Enterprise Advanced only, so the fuller agent features sit on the quoted Enterprise Advanced tier.
Variable cost rationale
Box bills per user, so cost grows with headcount, and the Box Agent's AI work is counted in AI Units on top. Enterprise Plus includes 2,000 AI Units a month and Enterprise Advanced 20,000. More volume is sold as an add on at $10 per 1,000 AI Units a month, on an annual contract. The included allowance limits what each plan covers before add on units are needed. AI Studio, Pro mode and the rest of the fuller agent features sit on Enterprise Advanced, which is quoted.
Additional watchouts
The Box Agent needs Enterprise Plus at minimum, and AI Studio needs Enterprise Advanced. File creation and Pro and Expanded modes are beta or limited to Enterprise Advanced, and AI usage past each plan's included AI Units is bought as add on volume.
Sales call required
Yes, required for paid access
Free / trial
Free Individual plan, and a free trial of Business Starter and higher plans
Lowest paid plan
Business Starter at $5 per user per month billed annually, for at least 3 users. The Box Agent starts on Enterprise Plus at $50.
Key ambiguities
Box's per user plans are public up to Enterprise Plus, the first plan with the Box Agent. Enterprise Advanced, required for AI Studio, is not publicly priced, and AI usage limits beyond the included AI Units are not fully disclosed.
Cancellation / refund
Listed rates are billed annually, with higher monthly rates. Platform add ons need an annual contract.
Support SLA / resale
Standard support on every plan, with Premier Support as an add on for Business plans. Enterprise Plus includes enhanced support with 24 hour coverage.
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — AI native accounting and bookkeeping firm whose agents run…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to Box
The closest documented capability profiles to Box among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Beam AI12.0 / 14Fuller documented coverage on Observability & Auditability and Prebuilt Agents, Templates & Packs
- Oracle12.0 / 14Adds documented Memory & State Persistence
- Boomi12.5 / 14Adds documented Memory & State Persistence
- Forest10.5 / 14Fuller documented coverage on Observability & Auditability and Triggers & Channel Coverage
- Uniphore9.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Adopt AI12.0 / 14Adds documented Browser & Computer Use
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded