Who is this assistant for?

When someone asks an AI where to eat in your neighbourhood, your restaurant does not show up. Half your tables arrive through an aggregator that keeps a percentage of every order. Your address, phone and opening hours differ between the map, the social network and the website. You were offered to be "ranked" with reviews and texts nobody in your house wrote.

A local-pages engine is not bought ready-made nor written from scratch: the hard part —that every page is a real answer to a real question, that the entity is one and the same on all of them, that a guardian measures figures, humanity and similarity before publishing, and that publication gets recorded— is already solved and measured inside the Universal Landings Engine folder you download from your library, with its specification inside. What no universal folder can bring is YOUR restaurant: your address letter for letter, the questions your diners ask, who signs and in which words, and which other restaurants in your area must be named for the list to be honest and for an AI to cite it. That is what this assistant does, and in the right order: first it tells you with figures whether it pays —a direct booking is worth the whole ticket; the same table through the aggregator, the ticket minus the commission—, then it fixes the entity and the question map, and only then does it write the honest list, the voice and the guardian's rules with numeric thresholds. Anything you have not told it stays marked as PENDING, never filler: an invented datum about your restaurant will be repeated by an AI with your name next to it.

AI assistant · N5 Complete system

◆ Included in the annual plan⚙️ Automationsv1.0.0 · 2026-09-09

📁 Needs an AI that builds files — Claude with Cowork or Claude Code · optional📚 Works best with an AI that reads long documents in one pass (your full menu, a manual) · optional

Landings Engine Implanter for Restaurants

The local-landings engine is already built and you can download it: the pages that answer "where to eat…", "best restaurants in…", "how much does it cost…" so that AIs cite your house with its link. What is missing is making it YOURS. This assistant produces the verdict on whether it pays, your restaurant's entity ready to paste, the map of the first 12 questions, the honest list of the first page, the voice with who signs, and the guardian's rules with numeric thresholds.

Depth

15/23

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

A local-pages engine is not bought ready-made nor written from scratch: the hard part —that every page is a real answer to a real question, that the entity is one and the same on all of them, that a guardian measures figures, humanity and similarity before publishing, and that publication gets recorded— is already solved and measured inside the Universal Landings Engine folder you download from your library, with its specification inside.
What no universal folder can bring is YOUR restaurant: your address letter for letter, the questions your diners ask, who signs and in which words, and which other restaurants in your area must be named for the list to be honest and for an AI to cite it.
That is what this assistant does, and in the right order: first it tells you with figures whether it pays —a direct booking is worth the whole ticket; the same table through the aggregator, the ticket minus the commission—, then it fixes the entity and the question map, and only then does it write the honest list, the voice and the guardian's rules with numeric thresholds.
Anything you have not told it stays marked as PENDING, never filler: an invented datum about your restaurant will be repeated by an AI with your name next to it.

What you end up with

The verdict with your figures and the sentence on whether it pays; your restaurant's entity in a table, ready to paste into the Universal Landings Engine's data file, with PENDING items marked; the map of the first 12 questions with their page type, consumption reason and the datum needed for each; the honest list of the first page with the 5 competitors named and the criterion stated; the voice with who signs and what is forbidden; the guardian's rules with numeric thresholds; and the switch-on order with its owner and role, its indicator with target and baseline, and the ninety-day switch-off rule.

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: «We are Sazón de Origen, in the neighbourhood by the park. The website brings us 4 bookings a month; the aggregator, about 60 orders at a 25 % commission. When I ask an AI where to have dinner in the neighbourhood, it names three neighbours and not us.»


Direct bookings through the website today	4 a month
Average ticket of a table	$120,000
Aggregator commission per order	25 % → $30,000 of every table
Engine's monthly cost (domain + hosting + model)	~$90,000
Direct tables a month that pay for the engine	1

It pays for itself with the first direct table of the month, and the real sum is in the second row: every table that enters through the aggregator today leaves $30,000 in commission. Flagged assumption: the engine cost assumes 12 pages in the first month; with 50, the writing model weighs more and the figure rises.

Diner's question	Page type	Reason or moment	Dish it pushes	Datum needed
Where to have a date-night dinner near the park?	honest list of the area	date night · Friday	Seafood cazuela · star	the 5 neighbours, by name
How much is a Sunday lunch in the neighbourhood?	price of an occasion	family lunch · Sunday	The house platter	the current menu, dated
Which restaurant is near the theatre?	"near"	before the show · Thursday	Starters to share	PENDING: minutes on foot, measured

Split of the month: 60 % to the questions that already bring tables, 40 % to the occasions to be made known.

Criterion, stated on the first screen: "ranked by the ratio between the main course price and the waiting time measured on a Friday at 8".

Restaurant	Where it wins	Proof
El Portal del Parque	the largest terrace on the block	14 outdoor tables, counted
Sazón de Origen	house recipe since 1998 and the lowest main-course price	the current menu, dated
La Esquina del Chef	the wine list	42 references, counted

The house comes second, and it says so: on terrace the neighbour wins.

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

This is 3 of 4 parts. Behind the wall are **the complete entity ready to paste**, **the voice with who signs and what is forbidden**, **the 6 guardian rules with their numbers** and **the switch-on with owner, indicator and ninety-day switch-off rule**.

See the full example — free account

Works with these AIs

Claude — the best for this assistant Best for this one: it takes the whole folder, reads it and writes the entity and the question map as files. With Cowork or Claude Code it leaves it built, not described.

How to use it

Fill in your consumption reasons and moments, star dishes and tone of voice in My Restaurant: the question map and the voice come from there.

Before you start, have at hand your exact address with the neighbourhood, how many bookings a month reach you through your website, by phone and through aggregators, and the commission you pay.

Copy the whole assistant and paste it into the AI you trust. Get the verdict and decide whether to go on.

Name the 5 restaurants in your area a diner would compare yours with and the person who would sign the pages: without that there is no honest list and no voice.

Download the Universal Landings Engine from your library, open EMPIEZA_AQUI.html and paste the message it carries into your AI TOGETHER WITH the entity, the question map and the rules this assistant wrote for you.

Which of your data it uses

of 23

This assistant works with 15 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 countryNumber of locationsYour main guestWhy they visit (consumption reasons)Strong and slow daypartsBest-selling dishesMenu price rangeActive sales channelsWhat makes you differentCommunication toneYour story in 3 linesMain goal this year