Led and built a system that finds the same company across Finance's monthly SAP exports, puts it under its parent group, leaves out the company's own group, and adds up sales and purchases per group and currency.

• Works on any file layout: the AI sees only headings and digit-masked samples to find the columns

• Seven steps: read, normalize, exclude, match, group, check, summarize

• Every number comes from pandas. The AI only answers narrow batched questions and sees company names and countries only

• AI answers are claims, checked against a YAML knowledge file that outranks them and open to a person's override. Stored answers make a second run take seconds

• Every record shows how it was matched, who decided, and why

• Web backend with finance, IT and admin roles: upload, run, review, release, and exports to Excel, PDF, Word and PowerPoint in four languages

• Runs go through a NATS JetStream queue to Python workers, with Go services for the edge, AI gateway pacing, and worker scaling

• Project manager: coordinated with Finance and designed the architecture