THE MEDIA FOR AI THAT ACTUALLY HELPS.English edition · Understand & take action
Spotted on the web

Calculate daily production of several bakeries with scripts written by ChatGPT

Use described publicly by La Tribune des boulangers pâtissiers (March 2024), summarised by the desk. Not tested by iadujour.

The result to aim for

Bo&Mie, a Parisian bakery company, had ChatGPT write Google Sheets scripts that calculate daily the production forecasts of its stores from sales, unsold and breaking hours.

What was done

In an interview published by La Tribune des boulangers pâtissiers in March 2024, co-funder Jean-François Bandet explains that each store already followed on Google Sheets the production of the day, the stock remaining at night and the breaking hours of each product. The calculation covers the five establishments and 150 display products; The system works widely alone, with two people to follow it, and the team adjustments during period like Christmas or Easter. According to Him, after one month, end-of-day unsolds had drooped by an age of 25 per cent and breaks by 15 per cent, for an estimated saving of €450,000 out of 2023.Production sheets are calculated on a gram bases and feel to the laboratory every event.

Before you start

Tool cited by the source: ChatGPT. Fill in the bracketed items: [décrire]. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

  1. Gather the context

    Spot the bracketed items in the prompt ([décrire]) and prepare what they ask for.

  2. Adapt the prompt

    Copy the prompt below, replace the bracketed items, then paste it into ChatGPT.

  3. Reread before using

    Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.

Your starting point.

Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.

The prompt to customise
My Google Sheets spreadsheet contains, by store and product: date, quantity produced, evening unsold, first break time.
Column structure: [décrire].

1. Write a script Apps Script that calculates for tomorrow a recommended amount per product and per store, from the last 14 days.
2. Explains the calculation rule in plain English.
3. Add a column "to be checked" for holidays and new products.
I'm testing a copy of the file first.

What deserves your attention

A forecast script written by an AI must be tested on past data before being used, and reviewed as soon as the assortment or seasonality changes.
Origin of the case. Use described publicly by La Tribune des boulangers pâtissiers (March 2024).
Proof level: Testimony published by an identified source. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.

Useful skills

Official skills on the same task, paired by the desk: they are not part of the described case.

TO GO FURTHER

Other ideas to put to work.

The whole Productivity theme
DISCUSSION

Comments.

A field note, a question, a precision on this use case? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.