AI assistant · N5 Complete system
Local Competition Radar Builder for Restaurants
The «radar» is a page of yours that runs a free diagnosis for the owner of a business in your area and emails it to them: who really competes, which time slots the market is thin in, how dense the area is and which listings are abandoned. This assistant decides what the downloadable folder cannot know —your vertical, your radius, your promise and the finding it will produce— and leaves the page ready for your AI to build.
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 levelIs this for you?
What it does and what you get
- A contact form asks for something and gives nothing; this gives first, and that is why the visitor hands over their email willingly.
- The hard part of building a radar —where the data comes from, which signal misleads, how the directory quota doesn't blow up, where the key lives, how not to render a stranger's typing unescaped— is already solved and measured inside the Universal Local Market Radar folder you download from your library, with its full specification in docs/01…08.
- What no universal folder can bring is your vertical, your radius, your headline promise, where the report leads and —most important— what finding it will produce, because a report that says nothing the owner didn't already know is a pretty page with no product.
- That is what this assistant does, and in the right order: first the arithmetic of whether it pays, then the dry-run diagnosis without a single line of HTML —the part that might not work—, then the report mould, and only then the page data sheet.
- Plus one piece no generic builder carries: the translation into the trade, which turns «there's a gap on Sundays» into how many cubiertos that slot needs at your ticket promedio and which dish holds it up.
What you end up with
The start decision with its arithmetic —vertical, radius, headline promise, where the report ends, quota cost and what an email is worth— and the sentence on whether it pays; the dry-run diagnosis with the four cross-checks, the signal each rests on and the minimum below which it stays quiet; the report mould with its example headline and the «what I can't know» section; the translation into the trade of each gap into cubiertos, dish and sales channel; the page data sheet with the PENDING items marked; and the switch-on order with owner, indicator with its target and 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
The owner asked this: «I want to attract restaurant owners in Medellín. I've downloaded the radar folder but I don't know what I'm going to tell somebody who knows their own neighbourhood better than I do. And the directory bill scares me.»
| Vertical | table-service and casual dining restaurants |
| Radius | 2 kilometres from the address the visitor types |
| Headline promise | «Find out which consumption moments are free in your area» |
| Where the report ends | a 30-minute call, not one more download |
The arithmetic, in plain sight: 120 diagnoses expected in 30 dias × 1 directory query with a 7 dias cache ≈ $95,000/month of quota, plus ~$40,000/month of email sending. If a qualified owner's email is worth $25,000 in your funnel, the list of 120 is worth $3.0M and the cost is 4.5 % of that — above the house yardstick of 1.5 %, so it only pays if the radar delivers more than 90 reports a month. Below that, the problem is not the page: it is that nobody sees it.
| Cross-check | Signal it rests on | Minimum to speak | What it says otherwise |
|---|---|---|---|
| Who really competes | review count | 10 competitors in radius | «no statistics within 2 km; widen to 4?» |
| Opening-hours gaps | hours declared per slot | 20 listings with hours | «too many listings without hours; the gap isn't reliable» |
| Density | businesses per km² vs. other areas | 3 comparable areas | «only your area; without comparison there's no hard or comfortable» |
| Abandoned listings | no photo, no site, no recent review | 30 reviews per listing | «not enough data» |
The average rating is deliberately not in this table. It is the figure you most feel like using and the one that misleads most: a 4.8 with twelve reviews and a 4.3 with eight hundred are not comparable. If the report says «your competitor is better rated» resting on twelve reviews, that is invented advice wearing the face of data.
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 are **the example headline and the five-recommendation mould**, **the translation into the trade in cubiertos, dish and channel** and **the switch-on with owner, indicator and a 60-day switch-off rule**.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
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.
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.
v1.0.02026-08-28Initial version. Born from a measured, published zero: on 2026-08-27 the CONSTRUCTOR kit rule was set —a universal package is offered next to every card with `forma_entregable=herramienta` whose title names the tool— and the count came out dashboard 21, fichastecnicas 2, botwhatsapp 1 and **radargastronomico 0**: the radar package existed and there was not one card that built a radar. This is that card. It ships the files of version 1.1.0 of the Universal Local Market Radar kit. It is called a BUILDER and not an implanter at Diego's request —«so it is better understood»— and with reason: unlike the WhatsApp Bot, here the package carries the SPECIFICATION and the page does not exist until the AI builds it. The word «radar» stays in the title under the sabana rule (lexico_titulos.json, 2026-08-27): a trade term may be used PROVIDED the first line of the description explains it — and the first line of the summary does.Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
