AI assistant · N5 Complete system
Marketing Dashboard Builder for Restaurants
The customer-attraction machine on one board: content against its plan, ads with cost per new guest, your owned audience growing and first-timers with their entry door — in a marketing.html where vanity metrics don't get in.
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
- Owners spend on content and ads blind: posting when they can, paying when a rep insists, and measuring with the numbers the platform wants to show — reach and likes that don't pay payroll.
- This assistant builds your marketing board in one file: content against its plan with each piece's reading, ads with their cost per new guest by channel, your owned WhatsApp and email base growing or stalled, and the week's first-timers with the door they came through.
- The sales board measures what the register already recorded; this board measures the machine that brings guests to the door.
What you end up with
The marketing indicator dictionary with formula, source, frequency and owner; the marketing.html file with the four blocks — content vs plan, ads with cost per guest, owned base, first-timers by door — and the 15-minute Thursday routine written into the file, with the ad-cut 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 post three times a week and pay 300,000 a month on Meta. No idea what brings people in and what is wasted money.»
Census of the machine at Sazón de Origen: 3 pieces a week with no dish named in 2 of them · 300,000 a month on Meta with no result declared before paying · a WhatsApp base with no signup count · no door question at the table.
| Indicator | Formula | Source | Frequency | Owner | Target |
|---|---|---|---|---|---|
| Pieces posted vs plan | posted / planned | calendar + networks | weekly | manager | 3 of 3 |
| Reading per piece | named dish orders, 7 days against the previous 7 | POS | weekly | manager | the row must be fillable |
| Cost per new guest | spend / attributed first-timers | Meta + door question | weekly | owner | below the margin a first-timer leaves |
| Owned-base signups | WhatsApp + email signups | list + register | weekly | cashier | PENDING — baseline missing |
SUPUESTO: the cost-per-new-guest target is set against the contribution margin of the average ticket the house declared, not against a «benchmark» industry cost per guest, which shifts by city and by season. If the real margin were lower, the target drops and the Meta spend hits the cut rule sooner.
| What | Figure | Verdict |
|---|---|---|
| Meta (messages) | 300,000 a month, 41 messages, 9 attributed tables | Under watch for 30 days: cost per guest lands well above the margin that table leaves. New ad with the dish named; if it does not drop, it gets cut by written rule |
| «Ambience» carousel | no dish and no channel named | Cut: it cannot be read, and a piece that cannot be read does not count as done |
| Stock video, Tuesday 7 a.m. | sancocho orders up at 7 days | Stays and repeats: the only piece with a reading |
| Owned base | no count | Still unmeasured: enters the board this week with the cashier as owner |
Warning written into the board: sancocho is the highest food cost dish on the menu. Pushing it fills the dining room and thins the margin; that decision is taken in plain sight, not by accident.
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 marketing.html file with the first-timers-by-door block** and **the Thursday routine**: the 15 min with one content bet, the ads decision with the figure in hand and the 30-day cut rule written inside the file.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 9 of the 23 fields in «My Restaurant», among them Restaurant name, Cuisine or concept and Your main guest. 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.
v1.1.02026-08-25Body rewritten to pay down duel debt: it scored 65.3 out of 90.0. The `lexico` signal read ZERO —a marketing board can be written end to end without naming the trade, and this one did: it spoke of «guests», «pieces» and «ads» without touching sales channel, orders, contribution margin, average ticket, occupancy, covers, sales mix, delivery, food cost or star dish, which is exactly the vocabulary that separates a restaurant's board from a shop's—. `metodo` read 3 of 6 because the five criteria sat in one paragraph («First… Second…»): the TASK is now six line-leading numbered steps injecting «redes_activas», «cliente_principal», «razones_consumo», «platos_estrella», «momentos_fuertes» and «meta_principal» into the working sections, because arraigo saw ZERO fields outside «YOUR RESTAURANT». `verificacion` read 2 of 5 and `cifras` 3 of 12: the checks were chained questions and the body asked for deadlines without putting a number on them; they are now five imperatives and every window carries its figure —a 7-day reading, a 15 min Thursday, a 30-day ad cut, a file zone findable in 10 seconds, an initial 4-week load—. The SUPUESTO: line is added (recipe §0.1): the cost-per-guest target is set against the house's own margin, not against a baked-in «benchmark» cost. Lead-magnet kit regenerated against the new body.v1.0.02026-08-15Initial version. Born in batch 7 of the artifact titles, the fifth c19 area board, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: the sales board measures recorded sales; this one measures the machine that brings the guest — and vanity metrics don't get in.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.
More assistants in this category
Pick the area above and whether you watch one location or the network, and the assistant builds THAT board: th…
N5 · Complete systemThe «sábana» —Latin American kitchen slang for the wide sheet where everything fits at once— is the master mea…
N5 · Complete systemThe PASS on one board: ticket times per dish against their standard, kitchen returns with fixed reasons, 86'd …
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.