Who is this assistant for?

You open in three months and the to-do list lives in your head. Day one filled up and the kitchen could not cope: dishes went out at 25 minutes. You launch, start full, and by week three the dining room is empty again. You cannot tell whether to postpone or open anyway, and you decide it the night before.

Almost every launch is planned up to opening day and there the plan stops. That is why the pattern repeats: a queue on day one, a kitchen in pieces and, by week three, an empty dining room with the money already spent. This assistant counts backwards from day zero and keeps counting four weeks forward, separates the three launches that sell differently and fail differently —new location, new menu and new channel— and puts the capacity test before the poster, because a launch that wrecks the kitchen costs more than it bills. It is not the yearly plan and not a standalone campaign: it is the countdown of one business event, with its decision cut-off written before the count starts.

AI assistant · N5 Complete system

◆ Included in the annual plan🗺️ Marketing Planv1.1.1 · 2026-08-26

Launch Plan Builder for Restaurants

Counts backwards from the day something opens —a location, a menu, a channel or a new line— with the capacity test that sets the day-one cap, the decision cut-off that says what gets postponed and the four weeks after, which is where most launches fall over.

Depth

13/23

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

Almost every launch is planned up to opening day and there the plan stops.
That is why the pattern repeats: a queue on day one, a kitchen in pieces and, by week three, an empty dining room with the money already spent.
This assistant counts backwards from day zero and keeps counting four weeks forward, separates the three launches that sell differently and fail differently —new location, new menu and new channel— and puts the capacity test before the poster, because a launch that wrecks the kitchen costs more than it bills.
It is not the yearly plan and not a standalone campaign: it is the countdown of one business event, with its decision cut-off written before the count starts.

What you end up with

Five chained deliverables: the launch type with its two argued discards, the capacity test with the day-one cap, the launch account with a break-even of its own and a dated decision cut-off, the countdown by fronts week by week, and the plan for the four weeks after with its Monday metric.

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 opening the third location in Laureles on 15 October and the lease is already signed. I do not want a repeat of the 2024 opening: it started full and by week three the dining room was empty."

It is a new location, and that decides everything else. It is not sold to the customers of the two locations already running: it is sold to whoever walks through Laureles and does not yet know Sazón de Origen exists. That is why the count runs 8 weeks and not 4, and why the kitchen front weighs more than the media front.

Type	Who it is sold to	How it fails	Weeks of countdown	Figure that declares it alive
New location	The neighbourhood, 800 metres around	On capacity: it fills on day one with a green line	8	Covers per day in week four
New menu	The guest who already comes	On mix: the new dish steals sales from the Bandeja de la casa and drags the margin down	4	Contribution margin of the mix, not total sales
New channel	An eating occasion nobody serves today	On its own economics: commission, packaging and transit	6	Channel contribution margin after commission

The two discards, in writing. It is not a new menu: the nine opening dishes are already on the menu at the other two locations and change nothing for the weekday lunch professional or the Sunday family. Treating it that way would have put the effort into the mix instead of into the line, which is where the real risk sits.

Nor is it a new channel, even though your own delivery starts at this location: the channel already exists, already has its delivery zone and already has its economics measured at the other two. Folding it into the same count would have added a second debut on the same day, and debuting a slot and a product at once is the flaw this method rules out first. Laureles' own delivery starts in week two, with the kitchen already broken in.

Two closed-door services, with real product and the 8 people who will work on 15 October. What came out of that rules over the seating plan.

Slot	Sustained dishes per hour	Ticket time at the peak	Covers it holds	Day-one cap
Lunch 12:00–14:30	38	9 minutes up to dish 30; 21 minutes at the peak of 46	73	60

The arithmetic, so it can be argued with: 38 sustained dishes per hour across the 2.5 hours of lunch is 95 dishes, and at 1.3 dishes per cover —the average of the two locations already running— that is 73 covers. The day-one cap was set at 60, 18% under what was measured, because a line that has been together for two weeks does not perform the same with a full room and the door ringing. The 60 are spread across 30-minute booking slots, not a queue.

It opens with 9 dishes out of the 24 on the menu. The three that already carry the sale and six that came out under 12 minutes in both rehearsals.

Dish	Menu price	Cost per portion	Food cost
Bandeja de la casa	46,000 COP	14,700 COP	32%
Sancocho de tres carnes	44,000 COP	14,100 COP	32%
Trucha al ajillo	52,000 COP	18,700 COP	36%

SUPUESTO: the short menu's target food cost is the 32% you declared for this house, not a sector average. If Sazón de Origen's real target were 35%, the Trucha al ajillo would stop being a finding and the menu price would stay where it is.

A finding on the Trucha al ajillo: at 52,000 COP it will not come down to the declared target without cutting the portion weight, and cutting it on opening day is the worst possible first impression. There the problem is not the offer, it is the menu price: to fit under the target it would have to sell at 58,400 COP, still inside the 28,000 to 72,000 range. It goes on the short menu at its normal price and stays out of any welcome plate. Illustrative figures, built from the data you gave.

The new location's monthly fixed costs, all assumed until you confirm them: payroll for 8 people 24,000,000 COP, rent and utilities 11,000,000 COP, other fixed costs —insurance, platforms, maintenance— 4,000,000 COP. That is 39,000,000 COP a month.

With the 48,000 COP average check and the 34% menu food cost, every cover leaves 31,680 COP of contribution margin. The location pays its month with 1,231 covers, which across 26 service days is 48 covers per day. That 48 is the line read every Monday for the following four weeks.

Opening spend is kept apart and never touches the plate: two rehearsals with 120 courtesy covers at raw material cost (1,958,400 COP), three days of line training for 8 people (3,840,000 COP), leafleting and local media within 800 metres (3,200,000 COP), short menu printing and signage (1,400,000 COP) and the corozo lemonade welcome for the first 60 (108,000 COP). Total 10,506,400 COP, recovered with 332 covers above break-even: at week-four pace, some 24 service days.

The decision cut-off lands on Thursday 1 October, and it is read at 9 in the morning.

Signal	Threshold at 14 days	Where it comes from	What happens if it falls short	Who signs
Rehearsal signed off	38 sustained dishes per hour	The chef's log	Postpone by two weeks	Chef
Line trained	8 of 8 running the short menu on time	Training record	Open with 6 dishes, not 9	Floor chief
Suppliers	3 of 3 confirmed delivering to Laureles	Confirmation email	Postpone; this one is not negotiable	Administration
Day-one bookings	40 of the 60 seats	Room diary and WhatsApp	Open with no media buy and leaflet within 300 metres	You

Postponing by two weeks costs 18,200,000 COP in fixed costs, and that figure goes written next to the decision. It is not there to frighten anyone: it is there so postponing is decided with the number in sight rather than with the gut.

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

This is 3 of 5 parts. Behind the wall sit the two parts that get executed. The full countdown: nine rows from week minus eight to week minus one, with the columns Week, Front, What gets closed, Owner and Proof it closed, spread across kitchen, dining room, sales and money, and with the decision cut-off pinned to Thursday 1 October at nine in the morning. And day one with its clock from 9:00 to till close, followed by the table of the four weeks after, where every week carries what falls away, what gets held, the Monday metric and its owner, along with the rule that decides whether dishes get added and the one that says when own delivery starts.

See the full example — free account

Works with these AIs

Claude — the best for this assistant The best fit here: the launch type and its two discards are an argument, and it holds the eight-week table by fronts without shrinking it halfway through.

How to use it

Decide what is being launched and on what date: a location, a menu, a channel or a new line. If it is two things at once, pick one; the other waits for next month.

Measure before you copy the assistant: how many dishes per hour your kitchen sustains in the peak slot, and how many minutes a dish takes at the peak.

Copy the assistant into your preferred AI along with your business details and answer what it asks about capacity, team and date.

Hang the countdown on the kitchen door and mark the decision cut-off on the calendar, with the date and the name of whoever signs it.

Read each Monday's figure for the four weeks after day zero and write it beside the target, even when you do not like what it says.

Which of your data it uses

of 23

This assistant works with 13 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 countryNumber of locationsYour main guestBest-selling dishesTeam sizeStrong and slow daypartsAverage check (with currency)Menu price rangeApproximate food cost (%)Active sales channelsMain goal this year