# Prompts

These three CSVs come from three systems — loan origination, collections, and CRM — plus a university master.

They share no common key, names are inconsistent, and IDs changed across systems.

Reconcile them into a single customer master.

For each match give: a confidence score, the fields you matched on, and a one-line reason.

Flag anything below 0.8 for human review.

Do NOT merge records that only share a similar name.

Separately, reconcile the university codes against the master and tell me which codes are the same institution under two IDs.

Output the reconciliation table plus a short list of exceptions and suggested master-data fixes.

<!--

Note: This chat is not included yet in the data story. #TODO Include it?

- This chat reconciles the data via Local MCP without looking at the file contents: https://chatgpt.com/c/6a312764-d72c-83ec-8912-000dd0dbdacb
- Code is at ~/r2/files/pages/customer-masters-data/reconcile_customer_masters.py
- Output is at ~/r2/files/pages/customer-masters-data/reconciliation_report/

-->