Skip to content

Bill and subscription audit

Finds what you pay for every month and what you forgot about.

PersonalWorks with ChatGPT agent · Claude Desktop with MCP+2

What it does

  • Reads statements and receipts
  • Lists recurring charges
  • Flags ones you have not used

Your approval boundaries

Creates drafts

These actions always wait for your yes:

  • Canceling anything

You decide what happens next.

More about this workflow

This setup is for busy people who want their own day to run a little smoother. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads statements and receipts. Next, it lists recurring charges. Finally, it flags ones you have not used. It works with your email and bank export, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before canceling anything, and says plainly if a step cannot be undone.

Before you startEmail · Bank export accessScoped permissionsChatGPT agent or Claude Desktop with MCP
Explore required tools and model recommendations

Tools and access

  • Gmail

    Handles the email part of this job. Grant read-only plus compose (drafts) scopes.

    API required: Yes. Needs a Google Cloud project with an OAuth app and the Gmail API turned on. The agent signs in through OAuth with only the scopes you pick.

  • Bank export

    Handles the bank export part of this job. Grant a file you export, never your bank login.

    API required: No. A CSV export you download from your bank. No bank login for the agent.

    No sign-up needed

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Fast and careful with your inbox and calendar.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

Claude Haiku 5.5

Cheapest Claude option for daily sorting.

From $0.10 per million input tokens and from $0.50 per million output tokens.

Anthropic docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

2Your prompt

3 of 3 still empty
Fill these in before you run it: [WHERE YOUR STATEMENTS AND RECEIPTS ARE] [HOW MANY MONTHS TO REVIEW] [SUBSCRIPTIONS YOU KNOW YOU KEEP] You are the Bill and subscription audit agent. Finds what you pay for every month and what you forgot about. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads statements and receipts - Lists recurring charges - Flags ones you have not used What you must never do without a yes from a person: - Canceling anything Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: ChatGPT agent, Claude Desktop with MCP, Custom GPTs, Zapier Agents

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Gmail with its own login, not yours. Grant read-only plus compose (drafts) scopes.
  2. 2Set up Bank export. Keep it to a file you export, never your bank login.
  3. 3Paste the prompt where your harness takes instructions. See the note under the Copy button.
  4. 4Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  5. 5Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access24 / 30

Writes drafts and notes inside your tools, nothing leaves on its own.

Human approval27 / 30

Waits for a yes on: canceling anything.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope18 / 20

Runs on its own login across 2 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Human approval: Add a second named stop next to "canceling anything", so every step that leaves your hands waits for a yes, and have the confirm say plainly what cannot be undone +3
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Run it on one tool only, with its own login that can see just what this job needs +2

Do all of these to reach 91, up from 83.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Bill and subscription audit](https://trustcase.dev/badge/bill-and-subscription-audit.svg)](https://trustcase.dev/use-cases/bill-and-subscription-audit)
HTML
<a href="https://trustcase.dev/use-cases/bill-and-subscription-audit"><img src="https://trustcase.dev/badge/bill-and-subscription-audit.svg" alt="Trustcase trust score for Bill and subscription audit" height="20"></a>
  • Morning brief

    Starts your day with one short summary.

  • Family logistics

    Keeps track of school forms, pickups and appointments.

  • Morning AI news brief

    Gathers the day's AI news with simple scripts, then has the agent pick the best items and write a short PDF brief. It lands in your chat app before 7 AM.

  • Private money check-in

    Looks over your spending once a month and sends the summary only to you. It is set up so your numbers can never land in a shared channel.