AI assistant · N5 Complete system
Recipe Costing Builder for Restaurants
Loads today's purchase prices onto the recipe you already have and returns each dish's cost per portion with a verdict against the printed menu price, ranked by money and not by percentage.
N5Complete system
Several chained pieces you install and operate over time, with their review cadence. It changes how the business runs, not one decision.
◆ This assistant 110 of the 164 published assistants are at this levelIs this for you?
What it does and what you get
- Most owners carry a dish cost somebody worked out once and nobody touched again, while the supplier moved prices three times.
- This assistant re-costs the portion with this week's invoices, stamps an expiry date on the number and says, dish by dish, which one still pays for the price already printed and which one does not.
What you end up with
A costing card per dish with price and date per item, the portion cost split into product, invisibles and packaging by channel, the verdict matrix ranked by margin in money, the re-costing template with an owner, and the month-end checklist.
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
The owner asked this: «The menu has been printed since February and I buy meat three times a week. I want to know which of my three mains stopped paying, with numbers I can show the chef.»
The portion that leaves the pass was costed, not the one the menu describes. Every price carries the day of its last August invoice in Medellín, and it is per NET unit: it already has the measured yield factor applied. Without that step the table would charge trimmed weight at purchase-weight prices and the costing would come out low.
| Item | Unit | Net quantity | Unit price | Price date | Cost in the portion |
|---|---|---|---|---|---|
| Beef posta | kg | 140 g | 26,000 COP/kg | Aug 12 | 3,640 |
| Chicharrón | kg | 60 g | 32,000 COP/kg | Aug 12 | 1,920 |
| Chorizo | unit | 1 of 55 g | 1,100 COP/u | Aug 10 | 1,100 |
| Cooked cargamanto beans | kg | 180 g | 11,200 COP/kg | Aug 08 | 2,020 |
| Avocado | kg | 70 g | 14,000 COP/kg | Aug 12 | 980 |
| Arepa | unit | 1 | 950 COP/u | Aug 05 | 950 |
| Egg | unit | 1 | 800 COP/u | Aug 12 | 800 |
| White rice | kg | 120 g | 4,600 COP/kg | Aug 05 | 550 |
| Hogao (sub-recipe) | kg | 40 g | 12,500 COP/kg | Aug 08 | 500 |
| Ripe plantain | kg | 90 g | 4,200 COP/kg | Aug 08 | 380 |
| Portion close-out | Dining room | Delivery |
|---|---|---|
| Product | 12,840 | 12,840 |
| Invisibles (oil, salt, seasoning) | 460 | 460 |
| Channel packaging | 0 | 1,250 |
| Total portion cost | 13,300 | 14,550 |
| Against the 42,000 COP menu price | 31.7 % | 34.6 % |
The same plate clears the house costing rule at the table and breaks it on delivery by 2.6 points. Illustrative figures for this case.
The old card said 16,000 COP for the sancocho; the August purchase says 16,400. Nobody had looked at it in 6 months.
| Dish | Menu price | Portion cost | Percentage | Margin in money | Units that month | Margin for the month | Verdict |
|---|---|---|---|---|---|---|---|
| House bandeja | 42,000 | 13,300 | 31.7 % | 28,700 | 1,420 | 40,754,000 | Passes · watch on delivery |
| Three-meat sancocho | 46,000 | 16,400 | 35.7 % | 29,600 | 880 | 26,048,000 | Fix |
| Garlic trout | 52,000 | 18,900 | 36.3 % | 33,100 | 610 | 20,191,000 | Fix |
Ranked by percentage, the trout looks worst. Ranked by the month's money, the one to touch first is the sancocho: 26,048,000 COP of margin against 20,191,000, and every point recovered there is worth more. The proposed fix is not a price rise: it is a review of the three meats' portion weights, which together account for 9,100 COP of the 16,400.
And an honest concession: the trout is a fished product and its price moved three times in the quarter. That cost is declared as a band, not a number, and it is reviewed every 30 days.
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 sits the part that turns costing into a habit: the re-costing template with an owner per item family and its review date, the one-page closing checklist, and the indicator you look at on the first Monday of every month —how many dishes on the menu carry a costing older than 30 days. Without it you costed once; with it the number stops ageing in silence.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 9 of the 23 fields in «My Restaurant», among them Business type, Cuisine or concept and City and country. 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.
Always up to date
Every assistant carries a visible version and date. When an AI changes how it works, the assistant's version goes up and you see what changed.
v1.0.02026-08-26The piece that puts a date on the cost is born. It opens c28 from the money side: it takes the recipe you already have, loads this week's purchase price onto it and closes with a verdict per dish against the printed price. It does not open the plate line by line —that is the cost breakdown— nor weigh product —that is the yield test—: here the number gets fixed and stamped with an expiry.More assistants in this category
Compares the same recipe costed on two dates, splits every difference into price effect and quantity effect, a…
N5 · Complete systemHolds every spec sheet against real service with four tests —the weighed plate, the photo, the server and the …
N5 · Complete systemTurns the kilo you bought into real portions and Saturday's demand into a purchase list, using a yield factor …
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.