Engineer my menu using item sales and contribution margin
Sorts every menu item into stars, plowhorses, puzzles, and dogs, with specific actions for each and the next menu.
The prompt
Run a menu engineering analysis on my menu.
Period covered: [e.g. last 8 weeks]
Menu category to analyze: [e.g. mains only - analyze one category at a time]
Item data (paste a table): [ITEM, MENU PRICE, PLATE COST, NUMBER SOLD]
Current menu layout notes: [where items sit on the page, any boxes, photos, or callouts]
Constraints: [e.g. signature dish we must keep, kitchen station capacity]
Method:
1. For each item calculate contribution margin (price minus plate cost), total margin, and menu mix %.
2. Popularity threshold: an item is "high popularity" if its mix % is at least 70% of an equal share (0.7 x 1/number of items). Profitability threshold: the weighted average contribution margin for the category.
3. Classify each item: Star (high/high), Plowhorse (popular, low margin), Puzzle (profitable, unpopular), Dog (low/low).
4. Recommend actions by class: protect and feature Stars; re-cost, re-portion, or nudge price on Plowhorses; reposition, rename, or have servers recommend Puzzles; replace or rework Dogs unless they serve a strategic purpose I named.
Return:
- A table: item, CM, mix %, class, recommended action.
- The 5 changes with the biggest likely profit impact, with the estimated weekly margin effect, showing the math and assumptions.
- Menu layout advice: placement, descriptions, and removing currency signs or price columns that invite price comparison.
- Items to watch in the next period. Do not fill in missing data; list what you need instead.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. last 8 weeks
- e.g. mains only - analyze one category at a time
- ITEM, MENU PRICE, PLATE COST, NUMBER SOLD
- where items sit on the page, any boxes, photos, or callouts
- e.g. signature dish we must keep, kitchen station capacity
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Diagnose my digital subscription funnel and reader churnAn analysis of paywall, registration, conversion, and churn data that pinpoints the weakest stage and tests to run next.
- Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
- Analyze my clinic's claim denials and revenue cycle KPIsTurns denial and A/R data into root causes, benchmark gaps, and a prioritized fix list for the front end, coding, and billing teams.