Box, Inc., the leading Intelligent Content Management (ICM) platform, announced the next evolution of its Box AI platform by introducing a new generation of AI Agents designed to transform how organizations work with content. With this new innovation, customers will be able to leverage AI Agents for Search, Deep Research, and enhanced data extraction so they can uncover more value from their content in Box — while taking advantage of Box’s industry-leading security and compliance standards. Box also introduced a new Box AI Agent for Microsoft 365 Copilot, to help customers unlock intelligent experiences that allow users to securely search, analyze, and act on Box content directly within Microsoft 365. Box will be showcasing all of these new announcements and more later today at the company’s annual Content + AI Summit.
“The future of enterprise AI will be defined by intelligent agents that can work together across systems, each bringing unique context and capabilities to the table,” said Aaron Levie, co-founder and CEO of Box. “Just as APIs once connected software, AI agents will change the way we work – and that transformation will be most profound when applied to enterprise content. With this next evolution of Box AI, we’re putting the intelligence of millions of files directly into the hands of users and into the AI tools they already use. These Agents will integrate seamlessly across platforms, helping teams make faster, more informed decisions while preserving the security and compliance enterprises depend on.”
Box AI Agents with Search, Deep Research, and enhanced data extraction capabilities
Box AI Agents are built with a layered approach to deliver value by combining five core components. Starting with enterprise knowledge securely found in Box, the Agents then leverage best-in-class AI models from Amazon, Anthropic, Google, IBM, Meta, OpenAI, and xAI to best match the task’s demands. Every Agent is aligned to an objective, follows a set of structured instructions that guide its actions, and is equipped with tools to complete its work with precision. Users will be able to interact with Box AI Agents to extract insights from content and automate enterprise workflows. Box AI Agents can also be customized in Box AI Studio.
With new AI-powered Search, Box AI Agents deliver precision across a spectrum of tasks. For quick lookups, they quickly surface targeted answers — like an expiration date in a contract or a client name in meeting notes. For more complex queries, Search uses high-precision semantic analysis to uncover relationships and insights across large volumes of content.
With Deep Research capabilities, Box AI Agents will be able to analyze large volumes of enterprise content to extract meaning and trends — automatically identifying the most relevant files using Box’s secure, permission-aware, retrieval-augmented generation (RAG) framework. The Agents then synthesize findings into digestible outputs, helping teams focus on decisions rather than sorting through fragmented files.
With enhanced data extraction, Box AI Agents will turn unstructured data, including scanned PDFs, images, and handwritten notes, into structured, actionable data. Using Optical Character Recognition (OCR), document intelligence, and natural language processing, Box AI Agents will automatically extract key information such as dates, financial figures, clause types, and contract terms.
With Box AI Agents:
- Legal teams will be able to instantly locate contracts containing specific liability or indemnification clauses across thousands of files, and extract key terms like expiration dates or renewal conditions to accelerate legal review while maintaining compliance;
- Product managers will be able to analyze competitor offerings by synthesizing insights from sales decks, analyst reports, and meeting notes to enable faster roadmap decisions based on real-world trends;
- Insurance auditors will be able to extract and aggregate policy terms, payout limits, and renewal dates from thousands of scanned PDFs and handwritten claims using enhanced data extraction to turn unstructured data into structured, reportable insights;
- HR specialists will be able to summarize employee survey results and sentiment trends across open-ended responses, and combine findings with policy documents or training feedback to prepare leadership updates.
- Financial analysts will be able to extract key financial figures, invoice terms, and renewal dates from supplier contracts, scanned receipts, and purchase orders to streamline audits, spend analysis, and renegotiations with precision and speed.
At the core of the new Box AI platform is a dynamic agentic reasoning framework designed to make sense of today’s complex content landscape. Box AI Agents operate where content lives, applying task-specific intelligence to identify relevant documents, synthesize insights, and extract key data — streamlining work and accelerating decisions without compromising security.
“AI is fundamentally changing how we work, but the real breakthrough will come when it can understand and act on the vast amount of content organizations rely on every day,” said Amy Machado, Sr. Research Manager, Enterprise Content and Knowledge Discovery Strategies at IDC. “With Box’s latest AI advancements, customers will be able to leverage AI to instantly find answers, extract insights, and create new content with their most critical information already securely stored in Box. It’s a big and important step forward in making AI truly useful across the enterprise.”
Expanding the agent ecosystem with Microsoft
Box also introduced a new AI Agent for Microsoft 365 Copilot, expanding its reach into Microsoft Teams, Microsoft Word, Microsoft PowerPoint, and Microsoft 365 Copilot Chat. These capabilities allow users to securely search, analyze, and act on Box content directly within Microsoft tools.
With this integration, joint customers will be able to:
- Analyze dense sets of documents to extract key insights and information for better decision making;
- Leverage existing templates to draft new content from a simple prompt for simplified content creation;
- Search and query across multiple documents to identify patterns, insights, and action items for quicker search and trend analysis;
- Ask targeted questions to clearly define milestones for improved project tracking and stakeholder communication.
“Box has been a trusted Microsoft partner for years, and we’re pleased to take our collaboration to the next level with this new Box AI Agent for Microsoft 365 Copilot,” said Dan Stevenson, General Manager, Copilot Ecosystem at Microsoft. “By bringing together Box’s enterprise-grade Intelligent Content Management platform and Microsoft’s AI-powered productivity platform, we’re making it seamless for joint customers to use the power of Copilot with all their content stored in Box, unlocking insights and taking actions across their enterprise tools.”
In addition to Microsoft 365 Copilot, Box AI Agents are available or in development with Google Agentspace, IBM watsonx Orchestrate, Salesforce Agentforce, Slack AI, ServiceNow AI Agent Fabric, and Zoom AI Companion. Developers can also build custom agents that leverage Box content using the Box MCP server, Google ADK, and OpenAI Agents SDK, as well as through their preferred developer and data platforms, including Airbyte, CrewAI, LangChain, LlamaIndex, Pinecone, Pydantic AI, Unstructured, and Weaviate.
Pricing and Availability
The next evolution of the Box AI platform with new Box AI Agents will be available to customers in the coming months, with pricing being announced closer to general availability. Additionally, customers looking to use the new Box AI Agent for Microsoft 365 Copilot can contact their Box representative. To learn more about how AI agents will transform the way you work with your content, check out the Box blog and register here for the Content + AI Summit on May 15.
For more such updates, follow us on Google News Martech News