A non-coder had Claude Code build a finance tracker that pulls bank emails, categorizes spending, and runs nightly on a Raspberry Pi.
A non-coder had Claude Code build a finance tracker that pulls bank emails, categorizes spending, and runs nightly on a Raspberry Pi.
Fahad Hasin, who says he knows little coding, had Claude Code build a personal finance tracker that runs on a Raspberry Pi 5 he already owned. It combines bank update emails from several accounts and payment methods, categorizes spending, and adds context from merchant emails. A local Llama 3.2:3B model does the categorizing. A cron job runs it nightly with no manual steps.
He says it works better than he expected, and the nightly run needs no manual steps. The post gives no accuracy figures, and the author admits he can't judge the code quality.
Local model means no token costs and no third party seeing your transactions; the author says a small miscategorisation is tolerable here.
Build me a personal finance tracker that pulls transaction emails from my inbox, categorizes spending automatically, and runs on a schedule to keep an updated log. Have it produce a daily or weekly summary I can review, and confirm the categorization logic with me before running unattended long-term.
An app built with Claude Code extracts vendor, date, total, tax and line items from receipts, including foreign-currency ones at historical exchange rates, for freelancers and small businesses.
A tenant used ChatGPT and Gemini to review a landlord's apartment deposit dispute, identify legal violations, and avoid losing $4,200.
The poster used an AI assistant to summarize a denial PDF to draft an appeal, but it invented an appeal deadline.