AI agent stories that use Python

2 stories name Python among the tools used. By outcome: Get tasks done 1 and Make money 1. Countries: Country unknown 1 and Singapore 1. Other tools named in 2 or more of them: Claude Code 2. Results are shown as claimed in each public source.

Get tasks doneBusiness size: SoloIncludes prompt

A Singapore data lead had Claude Code take his monthly bank and miles admin from 2 to 3 hours to 4 minutes

Rory Tan · Singapore · Claude Code, YNAB, Python

On top of his own Python pipeline, Claude Code loads bank statement files from several Singapore banks into YNAB, sorts transactions and asks him about unclear ones, learns new rules from his answers, and tracks each card's bonus cap per billing cycle.

Result, as claimed

Monthly work across his Singapore bank and card accounts (downloading statements, importing to YNAB, sorting 200+ transactions, checking card bonus caps) used to take 2 to 3 hours and now takes 4 minutes. A 45-minute manual import became a 30-second command. His categoriser matched 40% of transactions on its own at first and 85%+ after a month of his corrections.

Make moneyBusiness size: SoloIncludes prompt

Claude Code checked 267 court cases in under 15 minutes and flagged about $2K in garnished money to recover

Jon Taber @jontaber · Country unknown · Claude, Claude Code, Python

Jon Taber co-owns land in Brazil whose old property tax debts had led to money being garnished from family members' accounts, and some of it was never returned after the taxes were paid. He suspected more cases like it but checking meant clicking through judicial websites by hand. He used Claude to plan the automation and Claude Code to write and fix a Python script, after more than 30 rounds of troubleshooting.

Result, as claimed

"267 cases reviewed in less than 15 minutes, showing about 18 of those cases as potential recovery opportunities. Net benefit? About $2K."

Other tools