Building AI-Workflows with Box and n8n
Blog post from Box
Rui Barbosa demonstrates an AI-powered insurance claims workflow built with n8n, Box, the community Box MCP server, Box AI, and OpenAI agents to reduce the manual work of gathering and analyzing claim information. Using sample policy documents, claim reports, damage photos, and a customer report stored in Box, the workflow locates relevant files, separates them into branches, reads and analyzes the customer report, sends multiple images to Box AI for assessment, and extracts structured policy metadata through Box’s enhanced extraction endpoint. It then merges these results into a dynamically prompted preliminary claims report and uploads the completed report back to Box. The example emphasizes n8n’s visual interface and Box MCP’s abstraction of Box APIs as ways to make complex, cross-system AI automation understandable and adaptable, while positioning the generated report as a starting point that supports rather than replaces professional claims adjusters’ judgment.
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.