Who is this assistant for?

Sunday midday fills on its own and on Saturday at the same hour half your room sits still. You know you have slow hours, but not what each empty seat in those hours is worth in money. You ran a mid-afternoon promotion and people ended up ordering it at night, when you were already full. You launched a campaign, never knew when to pull it, and it is still running and unsettling your sales mix.

Your restaurant does not run one sales day: it runs six or seven different businesses under one roof, each with its own guest, check and cost of serving. This assistant identifies which of your slow moments has idle capacity worth fighting for, builds it a named offer with a closed schedule, and sets up a short pilot to decide from real sales whether the campaign stays or retires.

AI assistant · N3 Analysis with a verdict

◆ Included in the annual plan✍️ Copywriting and High-Impact Campaignsv1.3.0 · 2026-08-25

Dining Moments Campaign Builder for Restaurants

Turns your slow dayparts into named campaigns: a weekly demand map, the choice of the moment with real potential, an offer and copy for that schedule, and a short pilot that decides with numbers.

Depth

11/23

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

Your restaurant does not run one sales day: it runs six or seven different businesses under one roof, each with its own guest, check and cost of serving.
This assistant identifies which of your slow moments has idle capacity worth fighting for, builds it a named offer with a closed schedule, and sets up a short pilot to decide from real sales whether the campaign stays or retires.

What you end up with

The weekly slot map as a table, the argued choice of the moment to attack, the full proposal with offer, price, copy and internal script, and the pilot design with its decision date.

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: "Saturday middays the room runs at half speed: Sunday fills on its own and on Saturday barely twenty of my sixty seats move. I post on Instagram and WhatsApp, and I run my own delivery."

It was built from the eight clean weeks between 6 June and 25 July: out went the 29 June public holiday and out went the Feria de las Flores, which in Medellín distorts Saturday. This location only, with its 60 seats and the 9 operations people who stay here. Occupancy = seats taken at the slot's peak, out of 60.

Slot	Weekly sales	Occupancy	Guest	Status
Lunch Tuesday to Friday, 12:00–14:30	9,744,000 COP	78% · 47 of 60	Professional aged 30 to 45, alone or in twos, with 50 counted minutes	Strong, declared
Saturday midday, 12:00–15:00	1,269,000 COP	35% · 21 of 60	Sunday's family, one day early and with no plan made	Hole
Sunday midday, 12:00–15:30	5,168,000 COP	92% · 55 of 60	Neighbourhood family, tables of three and four	Strong, declared
Thursday night, 19:00–21:30	1,428,000 COP	41% · 25 of 60	Work groups stretching Friday forward	Hole, already spoken for
Tuesday and Wednesday night, 19:00–21:30	1,326,000 COP	26% · 16 of 60	A couple from the neighbourhood, a 51,000 check	Dead
Friday and Saturday night, 19:00–22:00	3,596,000 COP	63% · 38 of 60	Groups of four to six, long check	Middling
Afternoon Tuesday to Saturday, 15:00–18:00	512,000 COP	10% · 6 of 60	Coffee and a stray dessert	Dead
Monday, all day	1,368,000 COP	22% · 13 of 60	Nearby offices, nobody in the other chair	Dead

They add up to 519 covers and 24,411,000 COP a week at this location: 74 covers a day, which is what the 214,000,000 COP a month across both locations gives once spread over seven days. The average lands a point under the declared month because it skips the weeks with a public holiday, and in Medellín those weeks run higher.

The check per head changes a great deal from slot to slot: 68,000 COP on Sunday midday, 51,000 on a weeknight, 47,000 on Saturday, 42,000 at weekday lunch, 16,000 in the afternoon. Against the house figure of 48,000 COP there is a single slow slot already charging like the average, and that is the finding in this table. Illustrative figures, built from the data you gave.

Two axes that measure themselves: how many seats stay free at the slot's peak, and what its check earns against the 48,000 COP of the house.

	The check comes near 48,000	The check falls short
Many free seats	Saturday midday. It wins. 39 seats free at the peak and a 47,000 COP check, with nothing built on top of it yet. Thursday night lands in the same box, with 35 free seats and a 51,000 check, and it loses for a reason that is not money: that night already has an owner, it is worked as a dated event, and two campaigns in one week fight over the same nine-person crew.	Afternoon, Monday, Tuesday and Wednesday. They wait their turn. The afternoon charges 16,000 and Monday 38,000. With 54 seats free at four in the afternoon, matching lunch would mean nearly tripling the traffic. And none of those slots is slow: it is dead. Asking a family to go out on a Wednesday at eight is asking them to change their routine, and no copy wins that.
Few free seats	Sunday and Friday and Saturday night. Hands off. 92% and 63% occupancy, on checks of 68,000 and 58,000. An offer there is a discount on what already sells full.	Lunch Tuesday to Friday. Not a campaign, a menu problem. 78% occupancy on a 42,000 check: six thousand under the house average with the room nearly full. That gets fixed in the price and in what comes alongside the plate, not by opening a new slot.

The risk of the chosen one, written before the start. Saturday midday sits right beside Sunday midday, which is the fullest moment of the week and, on top of that, the same guest: the neighbourhood family. If Saturday takes the family that was coming on Sunday, the campaign moved people between days and brought nobody: the same sales with one more kitchen shift on top. Two things work against that, and both live in the pieces that follow. The Saturday dish cannot be the one that already sells itself on Sunday. And the pilot measures both slots, because the retirement rule hangs on Sunday, not on Saturday.

Sobrebarriga del sábado. Saturdays from 12:00 to 3:00 p.m., dining room only.

None of the three signature dishes works as the anchor here, and each one falls for its own reason.

Signature dish	On the menu	Cost	Food cost	For Saturday
Trucha al ajillo	52,000 COP	19,900 COP	38.3%	Out on cost. To fit under 32% it would have to sell at 62,200 COP. The problem there is not the offer, it is the menu price, looked at separately.
Bandeja de la casa	42,000 COP	14,300 COP	34.0%	Out on cost. It is the exact menu average and two points over the 32% ceiling; it would need 44,700 COP.
Sancocho de tres carnes	38,000 COP	11,800 COP	31.1%	Fits with room to spare and still stays out: it is what already sells itself on Sunday midday. Putting it on Saturday is the cannibalization, not the campaign.

The anchor was built for the slot, from cost towards price. The flank goes into the oven on Friday at eleven at night, already hot, and cooks itself for six hours. On Saturday it is only portioned and finished, so it does not fight the rest of the menu for a burner.

What goes in, per person	Cost	The same, à la carte
Soup of the day, starter portion	1,900 COP	9,000 COP
Sobrebarriga from the oven with papa chorreada, rice and the salad of the day	13,400 COP	46,000 COP
Jug of fresh juice, one for every two people	1,300 COP	6,000 COP
Total per person	16,600 COP	61,000 COP

Price: 53,000 COP per person. Food cost 31.3%, under the ceiling. It leaves 36,400 COP of margin per cover against the 31,020 COP that Saturday's loose check leaves today.

The hour of table rises only a little: from 53,200 to 58,200 COP, on a table of two assumed at 70 minutes today and 75 with the new dish. It rises little because this slot already charges like the house, and that is the point: the money in this campaign lives in the 39 empty seats, not in the check. Illustrative figures, built from the data you gave.

Kitchen ceiling: 28 portions a Saturday, the two whole flanks that fit in Friday's oven. The number goes in the announcement and it does not stretch.

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 five texts ready to paste, each with its hour: the Wednesday Instagram post at 6:30, the Saturday story at 10:40, the Friday WhatsApp status, the card inside the lunch bill and the insert in the own-delivery packaging; plus the server's fifteen-second script and the figure that keeps the delivery platform out. And the pilot across the four Saturdays of September, with the columns Saturday, Prepared beforehand, Watched that day and Written down at close: the baseline of 1,269,000 COP, the window that shuts at 3:00 sharp, the three bands read on Monday the 28th at nine, and the rule that retires it if Sunday drops below 76 covers.

See the full example — free account

Works with these AIs

Claude con Claude Design — the best for this assistant The only one that COMPOSES the piece instead of describing it: it opens its canvas, builds one artboard per unit and sets the text in place. Ask it for the style contract before the first piece, and have screenshots of your reference account at hand.

How to use it

Record the approximate sales of your slowest slot over a normal week, even by hand.

Take the assistant to your trusted AI with your declared strong and slow moments and answer its capacity questions.

Run the 3-to-4-week pilot on the chosen slot and judge against the baseline on the written decision date.

Which of your data it uses

of 23

This assistant works with 11 of the 23 fields in «My Restaurant», among them Business type, Team size and Strong and slow dayparts. 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 typeTeam sizeStrong and slow daypartsWhy they visit (consumption reasons)Your main guestBest-selling dishesAverage check (with currency)Communication toneActive sales channelsActive social channels (with the @ or the link)Average monthly sales

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.

Same method, another variant

Inside the app this is a single control: you press it and the assistant reframes itself, including the variants that don't appear here because they don't have their own page yet.

On what criterion

the slow hours the reason for eating outthe occasionHigh-Impact Campaign Builder for Restaurants