AI assistant · N5 Complete system
Dining Reasons Dashboard Builder for Restaurants
The WHY-they-come board: each dining reason with its weight in sales, which dish and message serves it, and the orphan reason nobody is working — in a razones.html that decides which why gets targeted 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 doesn't sell dishes: it serves reasons — the midday hunger, the weekend craving, the gathering that needs a table, the personal reward.
- Owners intuit them but don't measure them, so the menu and the marketing aim at everything and nothing.
- This assistant builds the reasons board in one file: YOUR house's reason repertoire under fixed names, each one's weight in sales — measured with the one-line question and POS signals —, which dish and message serves each reason, and the orphan reason: the one bringing money that nobody works.
- The decision falls out on its own: which why gets targeted this month, with an indicator and a figure.
What you end up with
The house's reason repertoire under fixed names with verdict; the razones.html file with each reason's weight, its dish and its message, the orphan reason flagged and the week's cells; and the monthly routine written inside — the chosen reason, its indicator with numeric target, owner and reading date.
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 think people come for Tuesday's sancocho and for office lunch, but on weekends the place fills with families and I don't know what brings them. I want to measure the why.»
A weight with no source is a well-dressed opinion. That is why the table carries a column for where it comes from.
| Reason (FIXED name) | How it is recognized | Estimated weight today | Where that weight comes from | Verdict |
|---|---|---|---|---|
| Work lunch | Mon-Fri 12-2, table of 1-2, orders fast, dining room | 38% of order tickets | POS by time slot, 8 weeks | Served: menu of the day — watch the timings |
| Tuesday's sancocho | Tuesdays, groups, they book | 14% | POS by day + reservation book | Served and with a message — the best worked |
| Family gathering | Weekends, tables of 5+, dessert and lingering | 27% | POS by table size | ORPHAN: high weight and ZERO work |
| The personal treat | Friday night, couples, starter + main | 11% | Floor manager's estimate — PENDING measurement | No message — second in line |
| Takeaway of the tired | Sun-Mon night, delivery | 10% | Sales channel report | Served by channel, margin under watch |
SUPUESTO: the weight of «the personal treat» is not measured yet; the floor manager's estimate over 2 weeks of observation is used. If marking the order tickets showed half of that, it drops out of the queue and the orphan stands alone in first place.
Repertoire rule: names do not change between weeks — renaming erases the series and the measuring starts over.
The one-line question, at the bottom of the order ticket, asked by whoever takes payment, 5 seconds: «What brought you in today: lunch, a craving, a get-together or a break?» — 4 fixed options, marked with a letter. Starts Monday; the cashier on each shift marks it.
| Reason | Dish that serves it | Message that speaks to it | Is it enough? | Light |
|---|---|---|---|---|
| Work lunch | Menu of the day | «Eat and get back on time» | Yes | 🟢 |
| Tuesday's sancocho | House sancocho | Tuesday post | Yes | 🟢 |
| Family gathering | None designed for 5+ | None | NO: the platter is single-serve | 🔴 |
| The personal treat | Platter + juice | None | Halfway: the starter that opens the night is missing | 🟡 |
The reading: the orphan reason weighs 27% of order tickets and has neither a dish to share NOR a weekend message. That is next month — and watch out: it is also the highest contribution margin per table, because lingering sells dessert and drinks.
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 razones.html file with the orphan reason flagged** and **the monthly routine template** — the chosen reason's full play, its indicator with a numeric target, its owner, its reading date at 30 days and the 5-point 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 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 duelo debt: it scored 63.7 out of 90.0. The `lexico` signal was at 1 of 10 — the board talked about «reasons» and «weights» without ever naming the trade — and `cifras` at 4 of 12; the reason–dish cross is now stated in the terms the work actually uses (menu engineering, sales mix, contribution margin, order ticket, sales channel, covers, table turnover) and the measurement windows are dated: 5 seconds per table, 4 weeks of marks, a reading at 30 days. `metodo` was at 3 of 6 because the only numbered steps lived in the FORMAT and the TASK was a paragraph reading «One… Two… Three…»: it is now six numbered steps injecting «nombre_restaurante», «platos_estrella» and «meta_principal» where decisions are made, and the three pieces are named by block. `verificacion` was at 2 of 5 — a string of questions with no checking verb — and is now five imperative checks. The SUPUESTO: line is added so the AI declares its own benchmark instead of the house hard-coding one. Rises to 95.0.v1.0.02026-08-15Initial version. Born in batch 12 (the category-boards one), c05's first artifact, with the full lead-magnet kit and a Sazón de Origen example. Its rule: reasons carry fixed names and the orphan — high weight, zero work — commands the routine.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.
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
