Extract receipt data for freelancer bookkeeping
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.
The poster built a Claude Code personal finance agent to track investments, prepare for self-employment taxes and optimize credit utilization.
The poster built a Claude Code personal finance agent to track investments, prepare for self-employment taxes and optimize credit utilization.
The poster used Claude Code to help build Hearth, a local Python personal finance system that pulled data from Schwab, Robinhood, Coinbase, Plaid, Gmail through Google MCP, and a market-data API. Claude helped research investing and tax rules, build custom skills, and refine logic for portfolio allocation, Schedule C and mileage handling, plus credit-utilization alerts keyed to statement close dates; the user validated the rules and cross-checks.
The system consolidated investments, taxes, and credit monitoring in one dashboard and could flag issues like idle cash, dead connections, and discrepancies against bank data. The source gives no performance gains or savings figures, and says reproducing it would require significant technical skill.
The main catch is complexity: the source notes 547.7 million tokens over 80 active days, with no repo or prompt sequence provided.
Build a personal finance assistant in this folder from my files: [investment statements, income records, credit card balances and limits]. It should track my investments, estimate quarterly self-employment tax set-asides based on [my income and state], and show how to bring credit utilization under [target percent]. It is done when one command produces a dated summary with the assumptions listed, and it should never connect to accounts or move money without asking me first.
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.