Every night, ChatGPT checks orders and drafts the invoice
Completed orders needed checking against CRM records before billing. Every night ChatGPT reviews each order form against the CRM for mistakes, then creates a draft invoice in the accounting system for review.
Done withChatGPTSpotted· by X user @SunnyvaleSBay· Oct 21, 2026
Result Also logs each deal's name and amount to a Google Sheet
“Every night, ChatGPT pulls our completed orders. It reviews the order form against the CRM system entries for mistakes.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Each night, ChatGPT pulls the day’s completed orders. It reviews the order form against the CRM system entries for mistakes, then goes into the accounting system and creates a draft invoice. It also writes the name of the deal to a Google Sheets drive with the amount.
How it went
The invoice is left as a draft for the writer to review rather than sent automatically, and the deal name and amount are logged to a shared spreadsheet.
Try it yourself with ChatGPT
Each night, have [agent] pull your completed orders from [order system], then check each order form against your CRM entries for mistakes. Have it log into your accounting system and create a draft invoice, and write the deal name and amount to a [Google Sheets] tracker. Review and approve the draft invoice yourself before it is sent or finalized.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Buying small e-commerce brands, they codified everything they look for into a six page prompt. Given a listing's screenshots and financials, ChatGPT takes a first pass to decide whether a seller call is worth taking.
Booking flights for a Costa Rica trip, a picky traveler asked ChatGPT to look them up. It checked Kayak, noticed the return flights got in too late and offered other options; they ended up booking one.
Building their first AWS project by vibe coding, the writer designed the architecture and let Codex write the code. A flawed first design took a day, against an estimated three or four; the redesign also took a day and scaled.
Safari's lack of a favorite Chrome plugin was the writer's last complaint about it. ChatGPT pulled the source from their installed Chrome extension, ported it, and installed it in Safari in 20 minutes.
Financial data for 100 schools, from tax filings into a Google Sheet. Operator clicked through it in the background, but rounded numbers, sometimes grabbed the wrong school, and was so slow it was stopped at 25.
"What's for dinner?" with allergies, expiring food and a garden to use up. ChatGPT wrote the build plan and Codex built a local app. Two restarts and about 20 hours later, it's an MVP they use daily.