The author had Claude Code read a folder of credit card statements, learn his patterns, and put relevant expenses into an Excel sheet, saving hours; he plans to review subscriptions next.
The author had Claude Code read a folder of credit card statements, learn his patterns, and put relevant expenses into an Excel sheet, saving hours; he plans to review subscriptions next.
The author put all her personal credit card statements in one folder and ran Claude Code from inside it. She asked it to find likely business expenses to be reimbursed. It first talked through the early statements with her to learn her patterns and ask about anything unclear. At the end it wrote the relevant expenses to an Excel sheet in the same folder.
She says it saved her hours. She gives no accuracy figures or error rates. Reviewing and cancelling unneeded subscriptions is her planned next step.
Claude Code needs a Claude Pro ($20/month) or Max ($100-200/month) subscription. The post also notes that employer data-protection rules may limit use with work data.
Read all the credit card statements in [folder path] and work out which charges are [type of expense, e.g. business or reimbursable]. Put them into an Excel file with columns for date, merchant, amount, and category, and flag any charges you're unsure about instead of guessing. Finish with a short list of recurring subscriptions you found, but don't change or delete any of my original files.
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.