AI assistant · N5 Complete system
Social Media Dashboard Builder for Restaurants
The board that turns social media into money: bookings and orders attributed by channel, the content that sold a dish — not the one that got liked —, paid ads with their return and vanity metrics put in their place — in a redes.html that answers how much social sold this month.
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 restaurant's social channels produce figures every week — reach, followers, likes — and almost none answers the only question that pays payroll: how much did they sell?
- This assistant builds the translating board in one file: each channel with its business metric — bookings that arrived through Instagram, orders that entered through the link, calls and directions from the profile —, content crossed against the sales of the dish it showed, paid ads with their return in money, and vanity metrics demoted to what they are: context.
- The retention analyzer watches whether the video holds the eye; THIS board watches whether the eye ended at an occupied table or a paid delivery.
What you end up with
The attribution map per channel — which business metric each one answers and how it gets captured —, the redes.html file with its four blocks and the content-sales cross, and the Monday routine written into the file: what gets posted this week based on what sold last week.
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 have 14,000 followers on Instagram and I don't know whether they've brought me a single guest. I want a board that tells me how much money social media left this month.»
| Network | Business metric | How it is captured | Frequency | Owner |
|---|---|---|---|---|
| Attributed bookings and covers seated | Fixed question at booking: «how did you find us?» | weekly | floor manager | |
| Orders entered through the link | A different measurable link per network | weekly | manager | |
| Calls and get-directions from the profile | Profile panel, weekly capture | weekly | manager | |
| TikTok | — | NO CAPTURE: no measurable link installed | — | PENDING · manager, this week |
Verdict: today only Google is genuinely capturing. Instagram enters as PENDING until the booking question has been asked for 2 weeks; TikTok contributes no figure until it has its own link. SUPUESTO: no «normal share of bookings from social» is hard-coded. The board starts at measured zero and climbs with whatever the capture records; if the owner brings their own figure, where it came from is stated.
| Content | Dish shown | Portions before (7 days) | Portions after (7 days) | Change |
|---|---|---|---|---|
| Chicharrón reel | House Bandeja | 96 | 121 | +26% |
| Dessert carousel | Tres leches | 41 | 44 | +7% ⚠ week with a 2-for-1 promo — not counted |
| Team photo | — | — | — | NO DATA: shows no dish |
The warning is printed on the board: the cross suggests, it does not prove. The tres leches week ran a promotion, so that row is marked and left out of the calculation — crediting a carousel with the sales of a 2-for-1 is the most expensive error this board makes.
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 paid media with its return on margin** and **the redes.html file with the Monday routine**: the break-even per campaign, the minimum-return rule, the 15-min loading zone and the monthly review checklist.
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 City and country. 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 duelo debt: it scored 70.7 out of 90.0. Two signals read ZERO. `cifras`: a board whose entire trade is translating social media into money carried not one figure with a unit —not the cross window, not the loading time, not the return rule's deadline—; the cross now says 7 days before and 7 after, the Monday load fits in 15 min, and the review has its date. `lexico`: it spoke of «sales» and «figures» without naming what a restaurant's sales are made of, so attribution now counts covers seated and portions on the order tickets, paid-media return is calculated on contribution margin with a break-even per campaign, and the sales-mix warning says why repeating the star-dish content and never the workhorse throws the kitchen off balance. `verificacion` sat at 2 because BEFORE YOU DELIVER was written as a row of questions. And the TASK ran as prose, so `metodo` counted 4 of 6: it is now six numbered steps with five «fields» injected, which is what arraigo requires since its cutoff —the nine fields were declared under YOUR RESTAURANT and none was used again—. A SUPUESTO line is added. Rises to 94.2.v1.0.02026-08-18Initial version. Born in batch 13, second published c16 assistant, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: the retention analyzer studies whether the video holds the eye; this board says whether the eye ended in a sale — bookings, orders and ads with return, never likes as a result.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
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
