1.5 hours back, every Monday
A local retailer with a two-person team spent hours each Monday on sales data. Staff pasted POS data into a sheet. Then they wrote a summary email by eye. A script now runs each Monday at 8 AM. It reads the sales sheet and calls the OpenAI API. It creates a Gmail draft. It does not send the mail. The owner reads the draft before it goes out. The cashier fills a short form each day. That form feeds the sheet. It takes about 30 seconds a day.
Start with one job only. Fill in the three lines. Keep the bot on that job.
The one job this bot does: ______________________________
What it may do on its own: ______________________________
What it must ask me first: ______________________________
Two lines from this case, side by side. No new figures.
A local retailer with a two-person team spent hours each Monday on sales data. Staff pasted POS data into a sheet. Then they wrote a summary email by eye. A script now runs each Monday at 8 AM. It reads the sales sheet and calls the OpenAI API. It creates a Gmail draft. It does not send the mail. The owner reads the draft before it goes out. The cashier fills a short form each day. That form feeds the sheet. It takes about 30 seconds a day.
After 8 weeks the shop saved about 1.5 hours a week. API calls cost about $0.04 a week. The draft flagged SKUs with falling sales. The owner said she would see them but rarely act on them. The POS export still needs a human. The system drafts only, so a person keeps the final say.
The after line is the source's claim, not our measurement.
smalloffice.space · Get a case like this in your inbox each morning. Subscribe free
Read this case on your phone now, and keep it for later. Type your email. We send this case to that address, and you get the next cases each morning too.