Scale catering recipes for 25–30 people up to hundreds with ChatGPT and Claude
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Here's a screenshot of a recipe I make for 25–30 people. Scale it to 330 people, convert the amounts into sensible bulk units, and flag anything that doesn't scale straight up, like baking times or spices.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Scale a recipe for a large event accurately, in units my kitchen can actually measure. Questions to ask me first: - How many people does the recipe serve now, and how many do you need to feed? - What equipment and pan sizes do you have? - Is it baked, cooked on the stove, or cold? Inputs (fill in or confirm): - Recipe (screenshot or text): [RECIPE] - Current and target servings: [FROM / TO] - Equipment and pan sizes: [EQUIPMENT] - Units I prefer: [UNITS] Rules: - Read the recipe back to me first so I can catch any misread amounts. - Show the scaling factor and the math for each ingredient. - Convert to practical bulk units (pounds, quarts, cases) and round sensibly. - Flag items that don't scale in a straight line: salt, spices, leavening, baking times, pan depth. - Never change an ingredient without telling me. Checkpoint: Show me the read-back of the original recipe and wait for my OK before scaling. If you get stuck: If an amount in the screenshot is unclear, ask me rather than guessing. Verify before you finish: Spot-check three ingredients by working the math backward to the original amounts. Output: A scaled ingredient table, batch plan for my equipment, and a list of things to test or adjust. Done when: I have a scaled recipe I've double-checked and a plan for cooking it in batches.
AI tools
Outcome
Brian Reilly, co-owner of Arlington's Catering and Historic Venue in Springfield, took a six-week small-business AI workshop sponsored by Innovate Springfield. Reilly now uses ChatGPT and Claude to make routine checklists, such as cleaning procedures, and to scale recipes built for 25–30 people up to, say, 330. Reilly says accuracy depends on the input. When Reilly fed it information inaccurately, those mistakes were caught 'pretty quickly', and now Reilly screenshots the recipe into the tool instead to avoid user error. 'It might take a time or two, but it's been pretty accurate.'
Evidence: Article or interviewA newsletter, journalist or interview account of what happened.
Source
- Posted
- by Lynn Whalen (Springfield Business Journal)
- Last checked
- Method:
- How we verify
https://www.springfieldbusinessjournal.com/articles/local-small-businesses-put-ai-to-work/
Related cases
Draft and submit a $20,000 arts grant proposal in 12 minutes with ChatGPT
Mary Catherine Brooks, board president of the Greenville Arts Council in Mississippi, learned at 4:48 PM that a $20,000 grant proposal was due by 5:00 PM. Brooks opened ChatGPT, uploaded the council's past successful proposals and had it use them to produce a new draft. The proposal was submitted before the deadline and won the $20,000, which will support arts and education programming for children and families across the Delta. '12 minutes of ChatGPT is making an impact on the lives of thousands of kids,' Brooks says.
OpsChatGPTWorkedRecreated promptEvidence: Company case studyBeginner-friendlyView CaseRedline a vendor's standard OEM agreement with Claude for the first three rounds, then have a lawyer do the final check
jedberg regularly negotiates OEM agreements with vendors that mostly use the same template and draw the same objections. They tried Claude first, and their lawyer was impressed that it found things the lawyer had missed. jedberg then used Claude to redline that type of contract, and the other side remarked that the lawyer had been surprisingly thorough. The lawyer did the final check and by then basically said it looked good, and jedberg saved a lot of money by doing the first three rounds with Claude.
OpsClaudeWorkedRecreated promptEvidence: Described by posterView CaseSort a year of mixed Amazon business purchases into QuickBooks categories with Claude, including the fiddly split transactions
badlibrarian runs a business and sometimes buys things on Amazon. At tax time they used to search for the big business items and categorise them in QuickBooks Online until they gave up, using a janky browser plugin and two monitors full of Excel windows. Now Claude does it and doesn't give up, despite QuickBooks being slow. It will even click 19 times to split a transaction because they'd put a router and shampoo in the same Amazon cart one night in February 2025.
OpsClaudeWorkedRecreated promptEvidence: Described by posterView Case
