Who is this assistant for?

You are renewing the menu and the conversation starts with the dishes the chef likes. You buy an expensive ingredient that works in a single dish almost nobody orders. Your menu grew by adding and now nobody knows how many references the house can carry.

Almost every menu is born from dishes the chef likes, and then someone tries to make the numbers fit. This assistant reverses the order: it starts from why your guest visits, sets how many items your kitchen and inventory can support, requires every major ingredient to appear in several preparations, and assigns each dish a target cash margin before naming it. The result is the economic architecture of your next menu.

AI assistant · N2 Ready-to-use piece

◆ Included in the annual plan🍽️ Menu Engineeringv1.1.1 · 2026-08-14

Profitable Menu Builder for Restaurants

Designs your next menu with profitability built into the blueprint: contained size, ingredients crossed between dishes, balanced kitchen stations and a target margin per dish before the first recipe is written.

Depth

8/23

Your data

Compatible AIs

Steps to use it

Depth of the resulttap a level to see what you get

◀ Put out today's fireRun the year ▶

📄

N2Ready-to-use piece

Produces a piece you can use as-is: a menu description, a service script, a supplier email. Copy and go.

◆ This assistant 7 of the 164 published assistants are at this level

Is this for you?

What it does and what you get

Almost every menu is born from dishes the chef likes, and then someone tries to make the numbers fit.
This assistant reverses the order: it starts from why your guest visits, sets how many items your kitchen and inventory can support, requires every major ingredient to appear in several preparations, and assigns each dish a target cash margin before naming it.
The result is the economic architecture of your next menu.

What you end up with

The complete menu architecture: number of categories and dishes per category, crossed-ingredient map, load per kitchen station and target margin per slot, ready to fill with recipes.

EXAMPLE This is what you getAn example built with Sazón de Origen, the house's fictional restaurant.Not your data: your result is built with YOUR restaurant's.See the full example →

Sample result

Sazón de OrigenFictional contemporary Colombian restaurant in Medellín, 2 locations, 6 years in business. Every sample result in the library comes from this same case. Fictional restaurant

The owner asked this: «I am renewing the menu. I have 34 references, 24 people and two locations. Tell me how many dishes this can carry and how they split up.»

Category	References today	Proposed	Consumption reason it serves	Station
Starters and picadas	6	4	Craving for home cooking	Cold and fryer
Soups and broths	5	4	Working lunch	Stockpot
Traditional mains	8	7	Working lunch and family celebration	Grill and oven
Fish	3	2	Family celebration	Grill
From the stove (casseroles)	4	0 — folded into mains	—	Stockpot
To share	3	2	Family celebration	Grill and oven
Desserts	5	5	Craving for home cooking	Cold
Total	34	24

The line that defends the number, and it is not the one you expect. The bottleneck is not kitchen speed: with 4,458 tickets a month across two locations —about 74 per location per day— and the peak concentrated at the Tuesday-to-Friday lunch, the grill never saturates. The bottleneck is mise en place: 12 of the 34 references sell under 40 units a month, and the three «to share» dishes add up to 35 units between them while still forcing fresh seafood in the walk-in every week. 24 references is what 18 operations people sustain with full weekly rotation on every ingredient. Each surplus reference is not paid in kitchen time: it is paid in cold storage, in waste, and in the shift's break-even point, which climbs in silence.

«From the stove» disappears as a category for the same reason: four references, 129 units a month and a station of its own. Its two worthwhile dishes move into traditional mains; the other two come off.

Every lead ingredient works in two or three preparations. One that shows up only once needs a written justification, because it drags its own rotation and its own waste.

Lead ingredient	Slots it works in	Alert
Beef	Platter, Posta negra, Oven-baked flank, Charcoal tenderloin, Beef sudado	Healthy: 5 slots
Chicken	Sancocho, Ajiaco, Stuffed breast, Chicken casserole	Healthy: 4 slots
Pork	Platter, Valluna cutlet, Meaty chicharrón	Healthy: 3 slots
Beans	Platter, Bean casserole, Frijolada	Healthy, but two of the three slots add up to 201 units against the platter's 620: beans cross almost on their own
Plantain	Platter, Patacón with hogao, Sancocho	Healthy: 3 slots
Trout	Garlic trout	Orphan with a written justification: 210 units a month and 44,900 COP of unit margin. It stays, and the reason goes into the blueprint
Shrimp and seafood	Seafood casserole, Shrimp casserole, Surf and turf platter	Disguised orphan: three slots, 68 units a month between them. Three dishes are not a crossing if none of them rotates
Pumpkin	Pumpkin and coconut soup	Orphan with no defence: 27 units a month. Off it goes
Arequipe	Figs with arequipe	Dessert orphan at 130 units: it stays if the second high-band dessert uses it
Lulo	Lulo ice cream	Dessert orphan at 115 units: it carries itself, but it goes on the record

The rule that comes out of this map, and that corrects the instinct: seafood does not come off because it sells little. It comes off because it costs cold storage, waste and a weekly purchase that only it justifies. The trout, with the same number of slots —one—, stays: 210 units pay for their own logistics. The criterion is not the number of dishes, it is whether the ingredient's rotation can carry the purchase.

Illustrative example generated with a fictional restaurant. Not a promise of results, not a client case.

This is 2 of 3 parts. Behind the wall: the **slot-by-slot economics** —price band, target margin in money, tolerable food cost and gram weight— with its SUPUESTO line, the five growth rules, and the 30-day launch checklist with the week each thing lands in.

See the full example — free account

Works with these AIs

ChatGPT — the best for this assistant The most reliable at holding the whole blueprint without dropping rows between blocks: size, slots, ingredient map and economics come out coherent in one pass. Put your restaurant data at the end of the message, which is where it reads it best.

How to use it

Define whether you are building a new menu from scratch or renewing the current one, and know your consumption reasons and peak-hour kitchen capacity.

Pick what you need on the card —for which occasion (regular menu, prix fixe lunch, tasting menu, kids' menu…)— and the assistant reframes itself: you don't need another prompt.

Copy the assistant into your AI, describe the project and let it ask what it needs before proposing structure.

Validate the resulting architecture with your chef, adjust, and only then create the recipes for each slot.

Which of your data it uses

of 23

This assistant works with 8 of the 23 fields in «My Restaurant», among them Cuisine or concept, Why they visit (consumption reasons) and Your main guest. It does not ask out of curiosity: these are what make the answer speak about YOUR scale instead of an industry average — the same calculation on a business of another size returns a number you cannot decide with. You fill them once and they apply across the library, so the second assistant you open already starts with them in place. Whatever you leave blank, the assistant asks for one thing at a time instead of inventing it, and says so before answering, so you know what it is working from.

Cuisine or conceptWhy they visit (consumption reasons)Your main guestAverage check (with currency)Approximate food cost (%)Active sales channelsTeam sizeMenu price range