How Cornell Recovered $100,000 in Unidentified Payments With AI – Cornell AI Innovation Hub
Skip to main content<br>Search: Submit Search Search Filters Search This Site Search Cornell
How Cornell Recovered $100,000 in Unidentified Payments With AI<br>Written by<br>Pete Stergion<br>Desktop Engineer
How Cornell Recovered $100,000 in Unidentified Payments With AI
This is the story of how a two-semester collaboration between the Cornell AI Innovation Hub, graduate students, and the Treasury team transformed a time‑consuming, manual investigation process into a tool that helps staff complete the work more efficiently.<br>The Problem: Money Cornell Couldn’t Spend<br>Every year, Cornell’s bank account receives hundreds of wire transfers and ACH payments that arrive without enough information to route them anywhere. No invoice number. A vague or abbreviated vendor name. No department code. The money lands in a generic General Ledger holding account and sits there, unavailable to the departments it belongs to.<br>If a payment isn’t resolved in time, New York State law requires Cornell to escheate the funds, turning them over to the state as unclaimed property. Historically, the backlog has peaked at $4 million.<br>Cheryl Barnes and Marie Graves on the Cash Management team were spending up to half their workday on this problem. The work is painstaking: searching old emails, Googling vendor abbreviations, calling contacts, cross-referencing past transactions. Some payments take hours to resolve. Many stay unresolved.<br>The active backlog stood at roughly $1 million across a couple hundred transactions.<br>The Team<br>This project started in Fall 2025 as a collaboration between the AI Hub and Cornell Treasury Operations, and continued through the spring semester.<br>On the AI Hub side: Pete Stergion and Phil Williammee served as co-tech leads. Ayham Boucher and David Keith Nelson provided oversight and kept the project on track. A cohort of graduate students spent the fall semester doing the foundational work: analyzing payment data, prototyping automation workflows in n8n, and testing AI models across Gemini, GPT, and Claude. Their analysis confirmed the key insight that shaped the entire approach: vendor names are present on 99% of unidentified payments, while invoice and PO numbers appear on fewer than 4%. That finding told the team where to focus.<br>On the Treasury side, Cheryl Barnes, Marie Graves, Kevin Mooney, and Debra Federation were collaborative partners throughout. Kevin provided three years of General Ledger (GL) history from Oracle, over 10,000 resolved payment records. That data became the backbone of the tool.<br>How We Built It
Data Protection and Responsible AI Use<br>This project uses moderate‑risk financial data and is conducted within Cornell’s approved Cornell AI Gateway. Data is handled according to university security standards, is not used to train external models, and is only accessible to authorized users. The team applies a “know your data” approach to ensure appropriate safeguards at every step.
At the start of Spring 2026, the team had a semester of groundwork: meeting notes, data analysis, workflow prototypes, manual process documentation, and a sanitized version of the payment and GL data with PII removed. The question was how to turn all of that into a production tool.<br>Using Claude Code’s Plan Mode, the team loaded in everything: the project background, the manual process Treasury staff follow today, all the meeting notes from the fall semester, the student workflow prototypes, and the sanitized data files. Rather than jumping into writing code, Claude Code read through all of that context and proposed a full implementation architecture for the team to review and approve before a single line was written. The plan covered the pipeline structure, the matching strategy, how the AI layer would be used, and where the tool would live. Once approved, execution happened within that structure.<br>That context-first, plan-then-build approach is what made it possible to go from a semester of notes and prototypes to a working tool in a single session.<br>Before running the tool against the current backlog of unidentified payments, the team validated it with a backtest. We fed it thousands of historical payments Treasury had already resolved, hid the known answers, and checked whether the tool reached the same conclusions. Three scenarios were run against the full GL dataset of 9,131 resolved payments, each mirroring a situation Treasury staff hit in the field.<br>For returning vendors with consistent routing, the most common case, the tool hit 97% accuracy across 500 test payments on the base fuzzy-matching pass and 100% with the full AI pipeline. For vendors it had never seen, identification jumped from 76% to 100% once the Gemini search and Claude synthesis layers kicked in, confirming the AI layer earned its keep on the hardest cases.<br>The backtest also surfaced the tool’s main limitation: vendors who pay multiple Cornell departments. It...