--- title: How Box AI built enterprise content agents with Deep Agents description: Box built its enterprise AI agent (Box Agent) on LangChain's Deep Agents framework to enable cross-document search, multi-document synthesis, and structured... canonical: https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Box AI built enterprise content agents with Deep Agents | daily.dev og:description: Box built its enterprise AI agent (Box Agent) on LangChain's Deep Agents framework to enable cross-document search, multi-document synthesis, and structured... og:url: https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp og:image: https://api.daily.dev/og/posts/fDLNsa9kp.png og:image:alt: How Box AI built enterprise content agents with Deep Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Box AI built enterprise content agents with Deep Agents **[LangChain](https://daily.dev/sources/langchain)** · 6 min read · 0 upvotes · 0 comments ## Summary Box built its enterprise AI agent (Box Agent) on LangChain's Deep Agents framework to enable cross-document search, multi-document synthesis, and structured report generation across 100,000+ enterprise customers. The architecture uses a parent/child model where a Global Agent classifies intent and dynamically spawns child agents as needed, replacing an earlier hardcoded sub-agent design that caused unnecessary latency. Key engineering decisions include full LLM provider agnosticism (OpenAI, Anthropic, Google), a shared tool registry covering BM25 search, vector search, and file operations, and a middleware layer handling citation generation, prompt caching, and context management at 170K+ token thresholds. The new architecture shipped 4x faster than its predecessor and reduced new agent development time from months to weeks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Why We Rebuilt LangChain’s Chatbot and What We Learned](https://daily.dev/posts/why-we-rebuilt-langchain-s-chatbot-and-what-we-learned-h1oubdlqy) · LangChain · 9 upvotes · 0 comments - [How to Build Deep Agents for Enterprise Search with NVIDIA AI-Q and LangChain](https://daily.dev/posts/how-to-build-deep-agents-for-enterprise-search-with-nvidia-ai-q-and-langchain-t61dheiyx) · NVIDIA Developer · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#rag](https://daily.dev/tags/rag), [#langchain](https://daily.dev/tags/langchain) [View this post on daily.dev](https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How Box AI built enterprise content agents with Deep Agents","url":"https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp"},"datePublished":"2026-07-08T19:23:05.732Z","dateModified":"2026-07-08T19:23:45.183Z","description":"Box built its enterprise AI agent (Box Agent) on LangChain's Deep Agents framework to enable cross-document search, multi-document synthesis, and structured...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d22cbdef5f16a00f7f0b568262a7466e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d22cbdef5f16a00f7f0b568262a7466e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-box-ai-built-enterprise-content-agents-with-deep-agents-fdlnsa9kp","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,rag,langchain","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"How Box AI built enterprise content agents with Deep Agents"}]} ```