Who is this assistant for?

You cost at the kilo price on the invoice and serve product already trimmed, correcting nothing. You suspect trim takes a large share and have nothing to prove it with in front of the supplier. Your actual food cost will not match the theoretical and you have already checked portions, purchases and tickets. You changed meat suppliers two months ago and the cards still carry the previous one's numbers.

Most costing cards in this trade are written at purchase weight and served at trimmed weight, and that difference shows up on no line at all: the margin eats it in silence. This assistant brings it into the open by weighing real product, three runs per item, and hands you the factor that turns a 24,000 kilo into what it truly costs once it is on the plate.

AI assistant · N5 Complete system

◆ Included in the annual plan👨‍🍳 Standard Recipes, Spec Sheets and Productionv1.0.0 · 2026-08-26

📷 Works best with an AI that sees photos (invoices, dishes, screens)

Yield Test Builder for Restaurants

Sets up the yield test for your items with a scale and three runs, pulls each one's real factor and turns it into the price per net unit every card already written has to be corrected by.

Depth

9/23

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 ▶

🏛️

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 level

Is this for you?

What it does and what you get

Most costing cards in this trade are written at purchase weight and served at trimmed weight, and that difference shows up on no line at all: the margin eats it in silence.
This assistant brings it into the open by weighing real product, three runs per item, and hands you the factor that turns a 24,000 kilo into what it truly costs once it is on the plate.

What you end up with

The one-page test protocol, the table of three runs per item, the factor matrix with price per net unit and hidden surcharge, the card-correction template with the month's difference, and the retest calendar with an owner.

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 buy the rib at 24,000 a kilo and cost the sancocho at 110 grams against that price. My chef tells me it does not add up. I want to weigh it properly and know what the error has cost me.»

Three different lots from the same Medellín supplier, three shifts, the same scale. You take the median, not the best.

Run	Gross weight	Trim and bone	Net raw	Factor
1 · Monday	10.0 kg	2.4 kg	7.6 kg	0.76
2 · Wednesday	10.0 kg	2.2 kg	7.8 kg	0.78
3 · Friday	10.0 kg	2.6 kg	7.4 kg	0.74
Median			7.6 kg	0.76

The purchase price is 24,000 COP/kg. Divided by 0.76, the NET kilo costs 31,579 COP. The old card costed 110 g at 24,000, that is 2,640 COP. Costed properly, that same portion is worth 3,480 COP.

Difference: 840 COP per sancocho. At 880 sancochos a month that is 739,200 COP, and 8,870,400 COP over the year. On one item, of one dish, on a two-location menu. Illustrative figures for this case.

The hidden surcharge is one over the factor, minus one: what you overpay for buying gross and serving trimmed.

Item	Purchase price	Measured factor	Price per net unit	Hidden surcharge
Hass avocado	14,000 COP/kg	0.63	22,222 COP/kg	+58.7 %
Cassava	3,600 COP/kg	0.69	5,217 COP/kg	+44.9 %
Chicken leg	12,800 COP/kg	0.75	17,067 COP/kg	+33.3 %
Beef rib	24,000 COP/kg	0.76	31,579 COP/kg	+31.6 %
Criolla potato	6,900 COP/kg	0.86	8,023 COP/kg	+16.3 %

Once the cards for the three fastest-turning dishes are corrected with these five factors, the house's theoretical food cost rises 2.1 points. The kitchen did not get worse: the paper had been repeating a figure the scale will not hold up, and the declared 34 % stopped being a mystery.

And an honest concession: the avocado has the worst factor and the smallest weight in the plate, so correcting it moves little money. The expensive conversation is the rib. Rank by money, not by percentage.

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 what stops the test from being done once and forgotten: the one-page protocol with the four weighings in order and who answers for each, the template that turns every new factor into old cost, corrected cost and difference for the month, and the retest calendar with its indicator —how many items carry a measured factor less than 180 days old. Without it, in six months the cards start lying again with a different supplier.

See the full example — free account

Works with these AIs

Claude — the best for this assistant The best one here: it holds the three runs per item without averaging them too early and respects the median when you ask for it. Tell it to write SUPUESTO: on any factor that did not come off a scale; it is the one that will not fill the gap with a textbook figure.

How to use it

Fill in My Restaurant: kitchen, format, city, team size, star dishes, peak hours, monthly sales and declared food cost.

Get a gram scale, a notebook and the chef's permission to interfere with 8 items for a week.

Paste the assistant into your everyday AI and answer its questions one at a time, without running ahead.

Run the weighings outside peak hours, with an owner per item and a date.

Correct the costing cards the same day the factor comes out, and book the quarterly retest.

Which of your data it uses

of 23

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.

Business typeCuisine or conceptCity and countryTeam sizeBest-selling dishesStrong and slow daypartsAverage monthly salesApproximate food cost (%)Main goal this year