The best enterprise AI experiences work where your team already works. As a launch partner for Slackbot's new MCP Client, the Box MCP server extends Box's existing @SlackHQ integration with powerful new AI capabilities. Search, query, and act on all of your Box content directly from a Slackbot conversation, all governed by your existing Box permissions and security controls. Watch how it works. 👇

BoxWorks 2025 is a must for Developers looking to build smarter, faster apps with agentic AI. Unlock practical skills, connect with industry peers, & join master classes to get the latest details on advanced content tools & real-world use cases: boxworks.box.com/series/boxw…

Watch Box Doc Gen team up with @OpenAI Agents SDK + Responses API and @Pydantic to turn raw claim data and damaged car photos into full insurance inspection reports.

The @Snowflake Openflow connector for Box is now LIVE! Turn each of your contracts into structured insights you can act on. See it in action below and learn more in the Box blog: bit.ly/43tTmcw

In our latest Box AI Enterprise Eval, we tested @Anthropic’s Claude 4 Sonnet and Opus models, now integrated into Box AI, across enterprise Q&A tasks, technical workflows, and advanced coding scenarios—revealing major advancements in developer productivity and content intelligence. AI-assisted coding and development just reached a new milestone! Here's what we discovered: Claude 4 significantly improves understanding, generating, and debugging code across multiple programming languages. Developers can: ↳ Accelerate code generation ↳ Improve debugging ↳ Enhance technical documentation ↳ Build smarter AI agents 👉 Automating Financial Analysis with Code Generation: We evaluated Claude 4 by using the Box AI API to analyze ten complex 10-K financial reports. Claude 4 dynamically generated Python code to fetch file IDs from a Box folder, automating data extraction. Within two minutes, it accurately extracted key company data such as revenues, metrics, and highlights—demonstrating its potential to streamline demanding analytical tasks. 👉 Understanding Enterprise Content: Our evaluation confirms Claude 4 maintains strong performance on enterprise Q&A tasks, effectively extracting precise details from single documents and reliably synthesizing information across multiple sources. This ensures seamless integration of structured and unstructured data alongside powerful coding capabilities. 🔓 Developer-Centric Use Cases Unlocked: Organizations can leverage Claude 4 within Box AI to: ↳ Create custom engineering agents referencing technical documents stored in Box, pulling real-time data from Jira, or finding solutions on Stack Overflow. ↳ Build intelligent technical support bots capable of analyzing user-provided code snippets against internal manuals. ↳ Automate secure code reviews by evaluating repository code (stored in Box) against security policies. ↳ Efficiently migrate legacy systems by translating old codebases into modern languages or platforms. Ready to empower your developers and accelerate innovation? To explore Claude 4 Sonnet and Opus through Box AI Studio and APIs, contact us at [email protected] and request early access today! Learn more: blog.box.com/first-look-clau…

Today, @AnthropicAI's Claude Code is now GA. See how it accelerates building a document generation app using the Box API and Box DocGen, cutting development from days to under an hour. Learn more: blog.box.com/build-faster-an…

Build powerful Box agents with @LangChain using @OpenAI 4.1 mini, leveraging custom tools or the Box MCP server for flexible, efficient agentic workflows that integrate seamlessly with your applications.

Discover how to integrate the Box MCP server into agentic workflows using @pydantic and @OpenAI's GPT-4.1 mini model. Automate tasks like invoice extraction, file uploads, and document generation with minimal code and maximum efficiency.

See how the Box MCP server turns Box into a LLM-ready toolbox. In this demo, we showcase @Cursor_ai to fast track AI-powered content workflows.

Box AI integrates seamlessly with @OpenAI's new o3 model. See how the Box AI API can extract invoice metadata in bulk and answer image questions 👀👇

Box AI uses @OpenAI models to deliver smart RAG capabilities natively in a Box Hub. With the Box AI API, you can easily search a Hub, extract insights from multiple docs, generate code snippets, and get answers to complex questions—all within your custom apps ⚡️

See @Google’s Gemini 2.5 Pro in action with the Box AI API! We put it to the test on complex invoice calculations and analyzing 10-K financial documents. Leverage Gemini 2.5 Pro via the Box AI API for advanced document processing, data extraction, and Q&A in your applications.

Box AI now has support for @xAI's Grok 3 in beta. Check out how to use Grok 3 in the Box AI API for advanced document processing, data extraction, and Q&A in your app.

Today, @OpenAI has just launched GPT-4.1, a powerful upgrade to the GPT-4o multimodal model, now available in Box AI Studio! Get the latest details on how this new version excels in complex tasks and check out our full evaluation: blog.box.com/first-look-gpt-…

Every day, AI gets better at generating code from prompts. But as with any AI work, the results are only as good as the context you provide. With Box and @cursor_ai, software development can be done in a fraction of the time. Upload your Product Requirement Documents (PRD) and coding standards into Box, then Cursor and our Model Context Protocol (MCP) server will take care of the rest. Install Cursor into your IDE today and see what’s possible: 🛠️ Build to your requirements and standards: Ask Cursor to find your PRD and standards in Box and build the application described based on the best practices you require 🛑 Troubleshoot with ease: Highlight the error, click ‘add to chat’, and let Cursor fix the problem ⏲️ Do away with busy work: Let Cursor do the repetitive tasks of setting up your environment, designing your app, and building out the framework and tests, so you can focus on the more complex problems and take it over the finish line In this demo, we purposely chose not to write a single line of code. The entire app was built through natural language prompting with Cursor, and we were able to get 95% of this app written in just a few hours. With the Box MCP server and Cursor, you can turn your data into a powerful ally for your development needs.