Who is this assistant for?

You have a date bearing down —a contract expiring, a supplier waiting on an answer— and you still have not decided. Deep down you already decided, and what you are looking for is arguments to hold it up. Getting it wrong scares you more than missing the chance, so you have not moved in weeks.

The three things that most paralyse an owner —a decision that has been going round for weeks, an opportunity that glitters, a new line that just occurred to them— are settled by the same act: criteria and weights are agreed BEFORE looking at the options, scoring cites evidence, and out comes a verdict with a date and a written reversal condition. What changes between the three is the evidence to demand and the arithmetic to do, and the selector changes that: an opportunity must name the lever it moves and separate the verifiable from the promised; a new line gets its OWN books, with cannibalisation and kitchen hours, because a line that only stands because the kitchen is already paid for is not a business, it is a subsidy. The referee does not sign for you, but neither will it let you hide behind «it depends».

AI assistant · N3 Analysis with a verdict

◆ Included in the annual plan🎯 General Management and Strategyv1.4.0 · 2026-08-27

Decision Verdict Builder for Restaurants

You choose what you put on the table —a business decision, a growth opportunity or a new business line— and out comes the verdict in writing: criteria and weights agreed before looking at the options, the scored matrix with cited evidence, the cost of being wrong in cash, the pre-mortem and the reversal condition with a date.

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 ▶

📊

N3Analysis with a verdict

Crosses YOUR numbers and takes a stand, with a table, units and currency. Not options: a recommendation you can defend.

◆ This assistant 24 of the 164 published assistants are at this level

Is this for you?

What it does and what you get

The three things that most paralyse an owner —a decision that has been going round for weeks, an opportunity that glitters, a new line that just occurred to them— are settled by the same act: criteria and weights are agreed BEFORE looking at the options, scoring cites evidence, and out comes a verdict with a date and a written reversal condition.
What changes between the three is the evidence to demand and the arithmetic to do, and the selector changes that: an opportunity must name the lever it moves and separate the verifiable from the promised; a new line gets its OWN books, with cannibalisation and kitchen hours, because a line that only stands because the kitchen is already paid for is not a business, it is a subsidy.
The referee does not sign for you, but neither will it let you hide behind «it depends».

What you end up with

The decision in three lines -statement, deadline and door type-; the weighted matrix with weights fixed before the first score and evidence cited in every cell, including the «do nothing» option with its costs; the cost of being wrong in cash and in covers; the winner's pre-mortem with its three likely causes, early signal and prevention; the minimum trial that tests it without committing kitchen or cash; and the 30-day checklist with the reversal condition written down.

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: «The lease on location 2 expires in six weeks. Do I renew for three years, negotiate just one, or move?»

The sentence: before October 6, decide whether location 2 renews its lease for 3 years, renews for 1 year, or relocates within the same neighborhood.

The real deadline: October 6. The owner did not set it: the contract requires 60 days' notice, and what rules here is the calendar, not the urge to think about it a while longer.

The type of door: one that closes behind you. Three years of rent cannot be undone on reasonable evidence, so this decision demands hard evidence and location 2's break-even calculated on its own, never the consolidated figure for both.

And one referee's note before scoring: the decision arrived with two options, "renew or move". It is almost never two. Four compete here, and one of them is doing nothing.

The weights were agreed and written down before a single option was scored. It is the only way to stop the weighting bending toward the favorite.

Criterion	Weight	A · Renew 3 years	B · Renew 1 year	C · Relocate	D · Let it lapse	Evidence cited
Effect on operating margin	30%	7	6	8	2	Location 2 rent over its last 8 weeks of sales
Cash at risk over 6 months	25%	8	9	3	5	Quoted fit-out and 3 weeks with no service in a move
Execution capacity of the 24 people	20%	9	9	4	6	Neither location has a written opening protocol today
Reversibility	15%	2	9	3	4	SUPUESTO: the landlord accepts one year with an adjustment. Unconfirmed
Customer and location	10%	8	8	5	8	Neighborhood families, the reason location 2 opened there in 2024
Weighted	100%	7.00	8.00	4.90	4.45

Verdict: B, renew for one year. It does not win on rent —A is cheaper per square meter— but on reversibility and cash: one year turns a door that closes into one that can be opened again, exactly while the house does the cost work that will say whether location 2 deserves three years.

The criterion that was not declared: B stings this owner because he fears the landlord will raise the rent in 12 months. That is a criterion, not a hunch, which is why it went into the table with a name and a weight instead of sitting underneath it. Confirming the adjustment with the landlord is the week's first task, not its last.

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 is **the cost of being wrong**: cash at risk and weeks to recover for every option, the winner's pre-mortem with its three failure causes and their early signals, and the reversal condition written out to be signed.

See the full example — free account

Works with these AIs

Claude — the best for this assistant The value of this arbitration lies in the weights not moving after the scores appear, and in the pre-mortem not going soft to avoid discomfort. It holds both best, and it names the criterion the owner did not declare.

How to use it

Pick what you are deciding at the top: a business decision, a growth opportunity or a new business line. The chip changes the evidence you will be asked for and the arithmetic that gets done, not just the label.

Before you start, have the decision's real deadline and the last eight weeks of sales.

Fill in My Restaurant with team size, channels and your yardsticks: without them the matrix is scored in mid-air.

Copy the whole assistant and paste it into your AI of choice. Agree the criteria and weights BEFORE letting it see the options.

Demand that every score cites its data or confesses to being an assumption. A silent cell is an opinion with a number on it.

Write the verdict and its reversal condition on one sheet, and set the 30-day review the same day.

Which of your data it uses

of 23

This assistant works with 9 of the 23 fields in «My Restaurant», among them Restaurant name, Business type 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.

Restaurant nameBusiness typeCity and countryTeam sizeActive sales channelsAverage check (with currency)Average monthly salesMain goal this yearApproximate food cost (%)