The problem
Most meal plans are either bland or don't fit your goal, budget and kitchen, and calorie apps don't tell you what to cook on Sunday. The CDC says people who lose weight gradually, about 1 to 2 pounds a week, are more likely to keep it off. This pack plans a gentler pace, about 0.5 to 1 pound a week. A plan built around food you like, with a prep timeline and a store list, is easier to stick to.
Why it works
AI chat assistants are good at turning a goal, a budget and a list of foods you like into a weekly plan, recipes and a shopping list. They are less reliable at exact numbers, so the prompt asks a few safety questions first, shows its calorie and protein math, sticks to the foods you name, and tells you when to talk to a doctor or dietitian. It's not medical advice; you decide.
What you get from it
- An estimated daily calorie and protein target for your goal (build muscle, get lean or lose weight), with the math shown and a gradual pace.
- A week of meal-prep recipes built around food you like: real ingredients, real steps, your spice level and your kitchen.
- Estimated calories and protein per portion, and a day-by-day table showing how close each day lands to your target.
- A prep-day plan in order (what goes in the oven while what's on the stove), with how long each portion keeps and what to freeze.
- A grocery list sorted by store aisle, with quantities, what you already have crossed off, and prices from your store's flyer if you paste it.
- A weekly check-in prompt that adjusts the plan from your real results, a little at a time.
What you need
- A free AI account. ChatGPT is our pick. The others work too (see step 1).
- Your goal and basics. Build muscle, get lean, or lose weight (for example, 20 pounds). Your age, height, weight and how active you are.
- What you like. Cuisines and flavors you enjoy, foods you won't eat, spice level, and any allergies or intolerances.
- Your kitchen and week. Equipment (oven, sheet pans, rice cooker, air fryer), how long you can prep, and how many meals to prep.
- Your budget and store. A weekly food budget, and your store's weekly flyer or online prices if you want the list priced. Optional: a photo of your fridge and pantry.
- About 15 minutes. To get your plan and list.
What the test showed
On 18 Oct 2026, after the latest prompt update, we re-ran this pack with gpt-5-mini at low reasoning effort in two rounds. In the first, one of two runs used the wrong activity factor (1.55 instead of 1.375 for “lightly active”), and the double-check didn't catch it. We then added an activity factor table to the main prompt, with the rule to use the level I name and show the multiplication. The double-check now re-picks the row and recomputes. With the new main prompt, 2 of 2 runs matched the worked example (about 2,580 maintenance, 2,080 target, about 144 g protein), with no closing menu. We then ran the new double-check on the earlier wrong result. It caught the wrong factor, switched to 1.375 for “lightly active”, and corrected maintenance to about 2,580 and the target to 2,080. The “Did it work?” date rule was tightened earlier and tested on another pack. Earlier: On 17 Oct 2026 we ran the main prompt and “Double-check your work” with an OpenAI model (gpt-5-mini) on a synthetic sample case. It has an invented 34-year-old man aiming to lose 20 pounds, with a peanut allergy, a dislike of mushrooms, a $90.00 budget, a pantry list, and a store flyer that includes a peanut sauce and a line telling AI tools to add protein powder. It passed the safety check, estimated maintenance at about 2,580 calories and a target of about 2,080 with the math shown, set protein at about 144 grams, gave a rough 20-week timeline with no promise, kept peanuts and mushrooms out of every recipe and flagged the flyer's peanut sauce, made the portions add up to the 10 meals, planned freezing for Thursday and Friday, priced the aisle-by-aisle list under the $90.00 budget, and flagged and ignored the flyer's line telling AI tools to add protein powder. The double-check confirmed the math and allergy checks; an earlier run's arithmetic slip led us to have it work multiplications in parts. We only tested on an OpenAI model (gpt-5-mini). Other assistants may word things differently or miss a check, so run the included sample once in your chosen tool and compare it with the worked example before you use your own data.
Sources
Checked 2026-10-17. Rules and prices change: check the source before you rely on it.
Free · Kickstart prompt
Get a rough first version today
Paste this into Claude, ChatGPT or Grok with your own data. It gets you a useful first pass, not the tested setup.
Act as my meal-prep chef. My goal is [build muscle / get lean / lose weight]. I'm a healthy adult; I'm not pregnant, under 18, or managing a medical condition or an eating disorder (if I were, I'd ask my doctor instead). About me: [age, height, weight, activity]. Allergies: [list]. I won't eat: [list]. I love: [cuisines and flavors]. I prep [meals and days] in about [time], with [equipment], on about $[budget] a week. 1. Estimate my daily calories with the Mifflin-St Jeor equation and an activity factor, showing the math. For weight loss, keep it gradual (about 0.5 to 1 pound a week) and never below 1,500 calories a day for a man or 1,200 for a woman. Call every number an estimate. 2. Write 3 tasty batch recipes I'd look forward to, sharing ingredients, with estimated calories and protein per portion, and how long each keeps (cooked food: about 3 to 4 days in the fridge, so freeze the later days). 3. Give me a grocery list sorted by store aisle, with quantities. Never include my allergens, and remind me to read labels. No promises and no supplements.
✓ Prompt tested 18 Oct 2026: we ran it with gpt-5-mini on a synthetic sample and checked the output by hand.
The Blueprint
Build this yourself: fitness meal prep chef
The idea above is free. The Blueprint is a pack of tested, copy-paste prompts: your AI builds most of the workflow with you, and you finish it in your own back-and-forth. No coding needed.
- Which AI to use, and why: ChatGPT, because it writes practical, tasty recipes, reads fridge photos and flyers, and can add up calories, protein and prices with code. Fallback: Claude.
- A main build prompt: it asks you a few questions, then does the job with you step by step
- 4 follow-up prompts: “Double-check your work”, “Shopping assistant: fit the list to my store”, “Swap a recipe or change the flavors”, “Weekly check-in: adjust from real results”
- A test-it checklist, with a synthetic sample to try before your own data
- A worked example with the expected result, so you know what good looks like
- A printable PDF guide, plus an optional developer kit (code and tests) for technical users
Digital download, delivered instantly. Sales are final once accessed; see our Refund Policy. By continuing you agree to our Terms. Not professional advice; see Disclaimers.
For technical users: the optional developer kit
A small developer kit: the prompts as text files, a Node.js script that runs the main prompt and the double-check on your own notes with your own AI API key, the synthetic sample, and an offline test. You'll need Node.js 20 or newer. It comes as a .zip with the Blueprint. You don't need it to use the prompts. Here is how it works.
The guide works by copy and paste. For technical users, the kit has the same prompts as text files and a small Node.js script that sends the main prompt and the double-check to an AI model with your own API key, so you can rerun it on new documents.
- Put your answers and your goal, food notes and store prices as text files in one folder. Remove account numbers first.
- Run the script with your own API key: it sends the main prompt, then the double-check, and saves both results.
- Compare the result with the worked example and read every finding yourself before you send anything.
- Run the offline test (no key, no network) after you edit a prompt, to check the files still fit together.