Who is this assistant for?

You write what you want to sell first and then invent a guest problem to make it fit. You named a delay in a video that your kitchen still has, and the comments filled with people who lived it. Your pieces sound like a TV commercial and the team is embarrassed to share them. Tuesday lunch leaves the dining room half full and you have no idea what to post to fill it.

An owner who sits down to write content starts from the end —what he wants to sell— and ends up inventing a problem to justify it. The audience catches that in the first line. Here the order runs backwards: first you build the inventory of what people ask at the table, what got written in the reviews and what makes someone not come back, plus the owner's own problems in the operation; then you drop whatever this kitchen cannot fix, because naming a problem you do not solve leaves the house worse off than saying nothing; and the hook comes last, with the proof that turns the exit into something checkable.

AI assistant · N5 Complete system

◆ Included in the annual plan🎬 Hooks, Scripts and Viral Contentv1.0.0 · 2026-08-20

Problem-Solution Hook Generator for Restaurants

A hook that names a problem without an exit is a complaint; one that offers an exit without proof is an infomercial. This piece builds the inventory of the problems your people actually have, filters the ones this house can solve today, and only then writes the problem → exit pair, with its proof attached.

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

An owner who sits down to write content starts from the end —what he wants to sell— and ends up inventing a problem to justify it.
The audience catches that in the first line.
Here the order runs backwards: first you build the inventory of what people ask at the table, what got written in the reviews and what makes someone not come back, plus the owner's own problems in the operation; then you drop whatever this kitchen cannot fix, because naming a problem you do not solve leaves the house worse off than saying nothing; and the hook comes last, with the proof that turns the exit into something checkable.

What you end up with

The problem inventory with its source (table, review, operation), frequency, who it happens to and whether the house solves it today; the pair matrix of problem → exit with its proof beside it, the dish or daypart holding it up, the channel and the 14-day metric; and one hook template per pair, with the first line in the guest's own words, the exit, the proof on camera, the owner and the shooting 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: «Sazón de Origen, contemporary Colombian cooking in Medellín: 2 sites, 6 years, 24 people, 48,000 COP average check. My strong daypart is Tuesday-to-Friday lunch, but Tuesday runs thin: the main site does around 45 covers at midday against 80 on Thursday. I sell dine-in, own delivery and one platform; I post on Instagram and WhatsApp. I want hooks that name real problems, mine and my guests', and that hand over the exit in the same piece without sounding like a TV commercial.»

The problem, as people say it	Source	Frequency	Who it happens to	Does the house solve it today?
«How long does it take?»	Table	6 times a day	Professionals with a 45-minute break, Tuesday to Friday	Yes: three dishes leave in under 12 minutes
«I always order the same thing and I am bored»	WhatsApp	4 times a week	Office regular during the week	Yes, with the daily suggestion
«Delivery arrived cold»	Reviews, 5 mentions in 90 days	5 in 90 days	Own-delivery guest on rainy days	Partly: the packaging does not hold up yet
Tuesday midday leaves the room half full	Operation	Every week	The owner	This is the problem these pieces attack
«Do you have anything without pork?»	Table	3 times a day	Weekend families	Yes: garlic Trout

How it was sorted. All five came from three sources and none from the owner's head: two from what gets asked at the table, one from messages, one from reviews and one from the operation. They were sorted by daypart and Tuesday came first, because 45 covers against 80 on Thursday is the week's widest occupancy gap and a well-told exit pays there. Frequencies are approximate, taken from the floor team's memory; adjust them with two weeks of real counting.

#	First line, in the guest's words	The exit	The proof shown	Daypart or dish	Channel	14-day metric
01	«I get 45 minutes for lunch and I am afraid it will not be enough.»	Three set-lunch dishes leave in under 12 minutes, ordered by name on sitting down	A timer on screen from comanda to pass, uncut	Tuesday lunch	Dine-in	Tuesday midday covers (target: 45 to 58)
02	«I always order the same because I do not know what else to ask for.»	The daily suggestion goes out on WhatsApp at 11:00 a.m. to whoever asks for it	The real message from a Tuesday, with the photo sent that day	Weekday lunch	WhatsApp	People signed up to the suggestion (target: 120)
03	«With two kids I never know what both will eat.»	The house Bandeja gets split into two plates at no extra cost	The pass splitting the bandeja on camera	Sunday midday	Dine-in	Split bandejas ordered on Sunday (target: 18)
04	«Sancocho is too heavy for a working Tuesday.»	Half portion of three-meat Sancocho, Tuesday and Wednesday	The half portion beside the full one, same table	Tuesday lunch	Dine-in and own delivery	Half portions sold (target: 40)

What holds the matrix up. Every pair pushes the midday workhorse or fills the emptiest daypart, and none asks for a discount: with a 48,000 COP average check and the goal of lifting operating margin from 8% to 14% in 12 months without touching the menu, an exit paid for by cutting the price solves the video and breaks the month. Proof is compulsory and it gets filmed: the timer in pair 01 beats any adjective, because the guest can count it in his head while watching. Illustrative figures; targets get recalculated with the house's real count at 2 weeks.

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 **capacity filter**: the table of problems this house cannot solve yet, with the reason, the concrete condition that would return them to the inventory and the review date, plus the rule that stops you naming in public a failure the guest lived on his last visit.

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

Fill in My Restaurant with your main guest, consumption reasons, dayparts and promise: the inventory gets sorted by those four fields.

Pick what you need on the card —how far it goes (the text only, the text and the sketch, the text and the designed pieces); how many hooks (1, 3, 5, 10)— and the assistant reframes itself: you don't need another prompt.

Copy the whole assistant and paste it into the AI you use daily.

Answer its questions one at a time, starting with what your guests ask you that you still do not answer in public.

Receive the inventory, the pair matrix and the hook templates; cross out any problem your kitchen cannot solve today before approving anything.

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 Cuisine or concept. 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 typeCuisine or conceptCity and countryYour main guestWhy they visit (consumption reasons)Strong and slow daypartsBest-selling dishesActive sales channelsCommunication toneWhat makes you differentAverage check (with currency)Main goal this year

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.

Which hook type

curiosityproblem and solutionstorytelling controversy offer Viral Hook Engine for Restaurants