AI assistant · N5 Complete system
Scenario Simulator for Restaurants
The «what if» with numbers instead of gut: rent goes up, sales drop, prices rise, Sundays open — every scenario runs on the house's real model, with declared assumptions and a verdict — in a simulador.html with movable levers.
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 big decisions get made with the gut: can I take the rent increase?
- what if sales drop 15%?
- does an 8% price rise save me?
- does opening Sundays add or subtract?
- This assistant builds your house's simple model — sales, contribution margin, fixed costs, break-even — and turns it into a simulator with levers: move price, volume, cost or fixed expenses and see the result in money before deciding in real life. The house rule is hard: every simulation declares its assumptions, and the simulator doesn't guess the future — it compares scenarios so the owner chooses with open eyes.
What you end up with
The house's simple model — sales, contribution margin, fixed costs and break-even — validated with your figures; the simulador.html file with price, volume, cost and fixed-expense levers, your saved scenarios and a per-scenario verdict; and the monthly recalibration routine written into the file, with the declared-assumptions 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: «My rent goes up 1.2 million and I'm thinking of raising prices 8% to cover it. Is it enough? Or should I open Sundays instead?»
| Piece | Figure | Source | Assumption if any |
|---|---|---|---|
| Monthly sales | 38.0 M | POS, against their mean of the last 8 weeks | — |
| Average contribution margin | 62% | Costed menu, last 3 months | Covers the 12 references concentrating 80% of sales; the rest is left out and said so |
| Fixed costs | 16.4 M (rent 4.2) | Books | — |
| Break-even | 26.5 M/month | Calculated | — |
| Current cushion | 11.5 M above break-even | Calculated | — |
Validation: the model reproduces last month's real profit within 3% 🟢 — fit to simulate.
SUPUESTO: the margin per sales channel was split using the platform commission and the packaging cost the house handed over. If the real commission were 4 points higher, the Sunday scenario changes its verdict, because its sales arrive more through delivery than through the dining room. The figure can be moved inside the file.
What was NOT used: no industry benchmark elasticity. The volume lost to a price rise enters as a declared, movable assumption, not as a fact.
| Scenario | Declared assumptions | Profit | Cushion above break-even | How far it holds | Verdict |
|---|---|---|---|---|---|
| A · Absorb the increase | Nothing else changes | Drops 1.2 M: 7.2 to 6.0 | Falls from 30% to 26% | Holds as long as sales do not fall | Survives, but with no room for error left |
| B · Raise prices 8% | Assumed volume loss: 3% | Up 0.9 M net | Rises to 33% | Breaks even if the real loss reaches 6% | Covers the rent, with its most arguable assumption already written down |
| C · Open Sundays | Sunday sales at 60% of Saturday; +1 payroll shift; delivery margin, not dining-room margin | +1.4 M/month if the sales arrive | Rises to 34% | Stops paying if Sunday sells under 1.9 M/day | Tested over 8 Sundays against that cut-off figure |
The verdict is a comparison, not an order: B covers the increase with less risk than C, and C can be tested AFTERWARDS with its deadline and its cut-off figure. The owner signs the decision.
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 simulador.html file with its levers and saved scenarios** and **its governance template**: the monthly row with owner and day, the 5-point recalibration checklist and the deviation threshold that sends the model to review before it gets trusted again.
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, Business type and Average monthly sales. 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 69.6 out of 90.0. What sat near zero was `cifras` —1 of 12 in an assistant that exists to put numbers where there used to be gut feel: the body talked about «windows», «deadlines» and «deviation» without a single measurement window written as a figure— and `verificacion`, at 2. `metodo` measured 3 of 6 because the three tasks ran as prose inside a paragraph; it is now six numbered steps injecting «fields» into the TASK, which is what arraigo asked for (it measured 0 fields in the working sections with nine declared above). Splitting the margin by sales channel is added —without it a delivery scenario gets decided with the dining-room number— along with the SUPUESTO: line so elasticity and benchmark food cost get declared as a movable assumption and not as a fact of the trade. Rises to 97.5.v1.0.02026-08-15Initial version. Born in batch 11, c17's first artifact, with the full lead-magnet kit and a Sazón de Origen example. Its rules: every scenario declares its assumptions, the simulator compares without promising, and the model recalibrates monthly or stops being used.More assistants in this category
Hand your P&L spreadsheet to the AI and receive the verdict in owner's language: where the profit went, which …
N5 · Complete systemHand over your spreadsheet —sales, costs, P&L or all three— and get a board of twelve charts where the money s…
N5 · Complete systemYour restaurant's numbers told for a decision: the story in three acts, one figure per slide with its source a…
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
