Prompt
You are a menu-engineering analyst. Work only from the data I paste below — do not invent any number.

For each dish I give you: the ingredients with quantities and unit costs, the yield (portions), the menu price, and units sold last month.

Produce a table with, per dish: total plate cost, food-cost percentage, contribution margin (price minus plate cost), and monthly contribution (margin times units sold). Then classify each dish by popularity versus margin (star, plowhorse, puzzle, or dog) and recommend one specific move — reprice, re-portion, re-plate, or remove.

Rules:
- Use ONLY the figures I provide. Do not estimate or fill in prices, yields, or quantities. If something is missing, write [MISSING: what you need] and skip that calculation.
- Show every calculation step so I can check it against my spreadsheet.
- State your food-cost-percentage formula explicitly.
- Recommendations only — I make the final call on pricing.

My data: {{dish_data}}. My target food cost is {{target_food_cost}}.

Fill in your details and the prompt updates live — then copy.

What you get back (excerpt)

Shrimp Pasta - Plate cost: shrimp 6 x $0.55 = $3.30; pasta 4 x $0.09 = $0.36; sauce $0.80. Total = $4.46. - Food cost %: $4.46 / $22.00 = 20.3% (formula: plate cost / menu price). - Contribution margin: $22.00 − $4.46 = $17.54. - Monthly contribution: $17.54 x 340 = $5,963.60. - Class: high volume, strong margin = STAR. - Move: hold price; feature it prominently. Re-check every figure in your spreadsheet before repricing — confirm the shrimp cost is current.

The full workflow

  1. Pull current ingredient costs and yields from your invoices, not from memory
  2. Run the prompt, then re-do every plate cost and percentage in a spreadsheet or on a calculator
  3. Confirm supplier prices are current, since a stale cost prices the dish wrong
  4. Apply the classification with your own read of the room, then make the pricing calls yourself
  5. Re-cost on a set schedule as market prices move

Watch out for

Check the costing math, every time. Chatbots confidently miscalculate plate costs, percentages, and totals, and a wrong number can price a dish at a loss across thousands of covers.

Costs are only as good as the inputs. Verify each unit price against a current invoice — AI cannot know that shrimp went up $2 a pound last week.

Recipe formulas and supplier pricing are trade secrets. Avoid pasting confidential cost sheets and proprietary recipes into a consumer chatbot that may train on them; use generic values or a no-train tier.

Where this comes from

Every use case on this site is grounded in real reports from working chefs — not invented by us.

More AI use cases for chefs

← All 6 use cases: How Chefs Use AI