Who is this assistant for?

Messages go unanswered and you don't know how many. You've been offered bots and they all want to start from zero. You're afraid a bot will tell a customer something untrue. You've seen bots that speak like a brochure and not like your house.

A WhatsApp bot is neither bought ready-made nor written from scratch: the hard part —how it connects, how the number doesn't get blocked, how it doesn't invent a price— is already solved and measured inside the Universal WhatsApp Bot folder you download from your library, with its own specification inside. What no universal folder can bring is your menu, your Sunday hours, your delivery zones, your way of speaking and your prohibitions. That's what this assistant does, and in the right order: first it tells you with figures whether it pays —because a tool that doesn't pay gets switched off in two months—, then it pulls the real list of what your customers ask and cuts it in three (what's answered by reading a value, what needs judgement, and what a machine doesn't answer), and only then writes your data files ready to paste. Whatever you haven't told it gets marked PENDING, never filled in: invented data about your business is something it will say to a customer of yours.

AI assistant · N5 Complete system

◆ Included in the annual plan⚙️ Automationsv1.1.1 · 2026-08-27

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

WhatsApp Bot Implanter for Restaurants

The tool is already built and you can download it: what's missing is making it YOURS. This assistant produces the verdict on whether it pays, the inventory of what your customers ask with the cut between what a machine answers and what a person does, your written data files —menu, hours, zones, voice with its prohibitions— and the brake on what the bot never promises.

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

A WhatsApp bot is neither bought ready-made nor written from scratch: the hard part —how it connects, how the number doesn't get blocked, how it doesn't invent a price— is already solved and measured inside the Universal WhatsApp Bot folder you download from your library, with its own specification inside.
What no universal folder can bring is your menu, your Sunday hours, your delivery zones, your way of speaking and your prohibitions.
That's what this assistant does, and in the right order: first it tells you with figures whether it pays —because a tool that doesn't pay gets switched off in two months—, then it pulls the real list of what your customers ask and cuts it in three (what's answered by reading a value, what needs judgement, and what a machine doesn't answer), and only then writes your data files ready to paste.
Whatever you haven't told it gets marked PENDING, never filled in: invented data about your business is something it will say to a customer of yours.

What you end up with

The verdict with your figures and the sentence on whether it pays; the question inventory cut in three —no model, with model, to a person— with the data each one needs; your data files written and ready to paste, with the PENDING items marked; the brake on what the bot never promises with its handover line and its hours; and the switch-on order with what can be checked at each step, its owner with name and job title, the indicator with its numeric target and the monthly routine with its 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: «About 60 messages a day come in across Instagram and WhatsApp. We answer when we can; at the lunch peak nearly all of them drop. I know we're losing delivery orders but I don't know how many.»


Messages a day	60
Unanswered at the peak (12:00–14:30)	~26
Of those, asking a price or whether you deliver	19
Average delivery ticket	$38,000
If 1 in 4 is recovered	~$5.7M/month
Bot cost (machine + channel + model)	~$310,000/month

It pays for itself in the first week, and not because of the bot: because of the nineteen questions nobody answers today that are answered by READING a value. Caveat: the figure above comes from your 60 messages and my peak count — if the real count is half, it still pays.

Question	Channel	Times/wk	How it gets answered	Data needed
«how much is the platter?»	delivery	84	NO MODEL	menu with prices
«do you deliver to Laureles?»	delivery	61	NO MODEL	zones with cost and time
«how late are you open?»	direct	38	NO MODEL	hours with the Sunday exception
«where are you?»	direct	22	NO MODEL	address and landmark
«anything without pork?»	delivery	14	MODEL	menu with descriptions
«can you replace an order that arrived cold?»	delivery	6	TO A PERSON	—

The cut: 4 out of 6 need no model. Those cannot invent a price because they do not think: they read. And the first two rows are 65 % of the week's volume: that is the 20 % that must be perfect before switching on.

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 five written data files**, **the brake with its handover line** and **the switch-on with owner, indicator and a sixty-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 data files as files. With Cowork or Claude Code it leaves them built, not described.

How to use it

Fill in My Restaurant with your menu, your channels and your tone of voice: half the data files come from there.

Before you start, have three figures at hand: how many messages come in a day, how many go unanswered and what is lost on each one.

Copy the full assistant and paste it into your AI. Get the verdict and decide whether to go on.

Open last week's chats and paste what your customers actually write: that's where the inventory comes from, not from imagination.

Download the Universal WhatsApp Bot from your library, open the folder and paste into your AI the message it carries inside TOGETHER WITH the data files this assistant wrote for you.

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 countryNumber of locationsYour main guestActive sales channelsStrong and slow daypartsBest-selling dishesMenu price rangeWhat makes you differentCommunication toneMain goal this year