What was the result?
self-reportedAn owner of a small e-commerce brand in Ireland cancelled his profit tracking app and rebuilt it with Claude and n8n. Against profit apps that run about 35 to 200 euros a month, he puts the saving at roughly 300 to 1,500 euros a year back, after n8n costs.
Costs lived everywhere except the store: ad spend in Google and Meta, overheads in Xero, drifting cost of goods and late refunds. His replacement is a live Claude artifact that re-pulls fresh data when opened. Shopify revenue ex VAT, orders and cost of goods come in through Claude's Shopify connector, daily ad spend comes through an n8n workflow, overheads are a daily rate from Xero actuals, and postage, packaging and payment fees sit in an adjustable settings panel. It shows a margin waterfall from revenue down to estimated profit over 1 to 60 day windows. It took him a few evenings.
Who did this?
How do I try it?
- Editorial adaptation: write down where each cost lives today (store, ad accounts, accounting software, per order costs).
- Connect your store data to the AI, and pull daily ad spend with a simple automation such as n8n.
- Turn overheads into a daily rate from your accounting actuals, and put postage, packaging and fees in a settings list you can adjust.
- Have the AI build a dashboard that goes from revenue down to estimated profit over 1 to 60 day windows.
- Treat the mid month number as a guide and check it against your books after month end.
Editorial adaptation, not the poster's exact prompt. Using my store sales (revenue ex VAT, orders, cost of goods), today's ad spend from [file or workflow], my daily overhead rate of [amount], and per order costs of [postage, packaging, fees], build a profit dashboard: revenue, minus cost of goods, minus fulfilment and fees, minus ad spend, minus overhead, equals estimated profit, for the last 1, 7, 30 and 60 days. Show your formulas. Do not change any settings in my store or accounting software.
Make it run every week
A play works once. Turn it into a routine in three small steps:
- Run it once and check the result yourself.
- Give your AI a schedule. Tell it when to run this play (every week, or every month) and to message you with what it found before you act.
- Keep a log. One line per run: what was checked, anything flagged, what you did.
What should I watch out for?
Self-reported. The 300 to 1,500 euro range is his estimate based on typical profit app prices, not a measured saving. He says if you are not already paying for Claude the subscription eats much of the saving, it took a few evenings versus an afternoon for an app, and APIs change so it needs a small fix once or twice a year. In a separate comment he mentions a side project consulting for small operators. Build it with Page: a private profit page that shows today's numbers.
Did it work for you?
PageMotor keeps this site free.