Audit a bank statement for zombie subscriptions and price creep with ChatGPT
- Posted
- by Evem Finance
- Last checked
- Method:
- How we verify
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Outcome
A banker writing for Evem Finance fed a sanitized bank statement to ChatGPT with a 'forensic accountant' prompt looking for repeating subscriptions, bills that crept up over 6 months, and duplicate charges or unusual fees. The author says it found $200 a month in wasted spending, or $2,400 a year, in 30 seconds.
Poster says:$200 a month ($2,400 a year) found
This is the source's own number. We haven't measured it.
Agent
Prompt Original prompt
Exact prompt as published in the source.
Act as a ruthless Forensic Accountant. I am going to paste my transaction history below. Analyze it and look for three specific things: 1. Zombie Subscriptions: Identify recurring payments happening on the same day each month. 2. The “Inflation Creep”: Identify recurring bills (utilities, insurance) that have increased in price over the last 6 months. 3. The Waste: Flag duplicate charges or unusual fees. Present your findings in a table with the potential annual savings. Here is the data: [PASTE YOUR DATA HERE]
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about anything important that's missing below. Keep them quick. Then do the task, checking in with me at the key points. Goal: Audit my recent transactions for forgotten subscriptions, bills that have quietly gone up, and duplicate charges or fees. What I can give you (ask for whatever's missing): - 3–6 months of transactions as CSV or pasted text, with account numbers removed - Bills I expect to see (rent, utilities, insurance) - Anything I already plan to cancel You're not my accountant or financial adviser. Show your working, label estimates as estimates, and tell me which points a professional or the official source should confirm. Rules: - Find charges that repeat on roughly the same day each month or year. - Compare each recurring bill across the months and flag any increase, with old and new amounts. - Flag duplicate charges, overdraft or foreign-transaction fees, and anything unusual. - For each finding, suggest an action (cancel, call to negotiate, dispute) and the yearly saving. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. - Draft a short script I can use when calling a provider whose bill went up. Output: A findings table (type, merchant, amounts, months, suggested action, annual saving) and a total. You'll know it worked when: I have a short action list and the annual saving is added up from real transactions. Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.
Source
Related cases
- Track and cancel unused subscriptions with ChatGPT agentEvidence: Article or interview
ChatGPT agent scans for recurring charges and reminds the author to cancel before renewal, helping cancel unused streaming services.
ChatGPT agent · Personal · Source date:
- Shop for cheaper home insurance quotes with Claude Code and ChromeRecreated promptEvidence: Described by poster
Using the poster's coverage details and access to Chrome, Gmail and the existing policy, Claude Code sought quotes from about a dozen insurers and found two strong candidates; the poster says they were approved by AAA at $3,100/year, a $4,600/year saving.
Poster says:$4,600/year saved
Claude Code, Claude in Chrome · Personal · Source date:
- Find forgotten subscriptions on a credit card statement with ChatGPTEvidence: Described by posterBeginner-friendly
Brian Foster exported his latest statement, redacted sensitive details in macOS Preview, and asked ChatGPT to identify all monthly charges, sort them by service, amount and frequency, and suggest which to cancel. He says it flagged the recurring charges within seconds, grouped them so he could spot ones he didn't remember or hadn't used in months, and suggested which to cancel.
ChatGPT · Personal · Source date: