When teams receive folders of intake documents, the hard part isn’t storage — it’s quickly understanding what’s been submitted, what was extracted, and what needs follow-up before approval. In this demo, I show how to build a reusable intake review agent using LangChain Agent Builder and Box MCP. The agent securely connects to Box, analyzes documents using Box AI, reasons across files, and writes a structured review packet directly back into the folder — all without writing custom code. You’ll see how to: - Connect LangChain Agent Builder to Box using MCP and OAuth - Use a prebuilt agent template for intake review workflows - Run the agent with a simple prompt - Extract key fields, classify documents, and flag missing information - Generate a durable review artifact saved back into Box This pattern is designed to support real review and approval workflows — helping teams move faster while keeping humans in the loop. For more on Model Context Protocol (MCP) and Box integrations, check out the documentation: https://developer.box.com/guides/box-mcp

 93      1