AI assistant · N5 Complete system
Master KPI Sheet Builder for Restaurants
The «sábana» —Latin American kitchen slang for the wide sheet where everything fits at once— is the master measurement document: every indicator with its formula, its area, the role accountable for it, who reads it, when, and against which target. Every dashboard in the house then hangs off that sheet.
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 can own ten boards and still fly blind, because nobody wrote the mother document: what the WHOLE house measures, with which formula, who answers for each number and who reads it every week.
- This assistant builds the complete master sheet — by area and by job — and delivers it in one file: the server sees two numbers, the kitchen chief four, the owner eight, and every indicator declares formula, source, frequency, owner and target.
- Area boards show one slice; the master sheet is the map they all hang from.
What you end up with
The complete indicator sheet by area and by job — each with formula, source, frequency, owner and target —, the sabana.html file with its traffic light and reading order, and the weekly meeting routine written into the file, with the five-first 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 run two locations, one financial board I do read and twenty loose numbers nobody reads. I want the mother document: what my house measures, who answers for each number and what each job reads.»
Census at Sazón de Origen: 23 loose numbers found across the POS, a kitchen notebook and two spreadsheets. 18 were consolidated with an owner; 5 stayed OUT for having no verifiable source and are listed with the job that must bring it and the date.
| Area | Indicator | Formula | Source | Frequency | Owner | Target |
|---|---|---|---|---|---|---|
| Sales | Average ticket by sales channel | sales / checks, dining room and delivery split | POS | weekly | floor chief | computed on the house's declared sales |
| Sales | Sales mix by family | family portions / total portions | POS | weekly | manager | the highest-margin family must not fall |
| Kitchen | Real against theoretical food cost | theoretical recipe usage / period purchases | recipes + invoices | weekly | kitchen chief | gap shrinking against its own baseline |
| Kitchen | Waste | product written off / product received | write-off sheet | weekly | kitchen chief | PENDING — no sheet exists yet |
| Service | Covers and occupancy by slot | shift covers / seats per shift | POS + capacity | daily | floor chief | per the full hours the house declared |
| People | Labor cost over sales | period payroll / same period sales | payroll + POS | weekly | manager | on the declared figure, not on an average |
| Direction | Prime cost and contribution margin | food cost + labor cost; margin against the month's break-even | P&L | monthly | owner | against the year's goal |
SUPUESTO: targets are computed on the figures the house declared —sales, food cost and labor cost—, not on industry benchmark percentages, which shift by country, by format and by year. If the declared sales turned out to be a high-season month, every target in the table gets re-read against the 12-month average and several come down.
| Job | What they read | Frequency | What they decide |
|---|---|---|---|
| Server | their two numbers | daily | what they offer at the next table |
| Kitchen chief | their four | weekly | which standard recipe gets re-weighed and which purchase gets held |
| Floor chief | covers, occupancy and table turnover | daily | how staff is spread across the full hours |
| Manager | half the sheet | weekly | what gets corrected before next Monday |
| Owner | the five first | weekly | what gets opened in depth and what gets left alone |
The five-first rule: Monday's meeting opens with five numbers and their targets; the rest of the sheet only opens if one of the five left its range. The first meeting run this way closed in 40 min and the minutes fit on half a page.
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 sabana.html file with the printable cut by job** and **the Monday routine**: the 40 min meeting with the five-first rule, each week's deep-dive indicator and the written boundary against the area boards.
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 Number of locations. 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.
v1.2.02026-08-27Diego: «keep the sábana of indicators and explain it in the description». The word stays —in Latin American kitchens the sábana is the wide sheet where everything fits at once— and the first line now explains it instead of assuming it. A trade term that is explained teaches; one that is assumed excludes.v1.1.02026-08-25Body rewritten to pay down duel debt: it scored 69.6 out of 90.0. The `cifras` signal read ZERO on the card that builds the mother document of measurement, which is the corpus's costliest contradiction: the body ordered «15 to 25 indicators» and «three to five per area» without a single window carrying a unit. Deadlines are now measured —3 weeks before a copied sheet gets abandoned, 4 weeks before a borrowed target demoralises, a 40 min Monday meeting, a mute indicator retired at 30 days, a motionless indicator suspect at 90 days—. `lexico` read 2 of 10 despite this being the card that distributes indicators by area: each area now names its own —average ticket and sales mix by sales channel in sales; food cost, waste and standard recipe in kitchen; covers, occupancy and table turnover in service; labor cost in people; prime cost, contribution margin and break-even in direction; delivery where it splits from the dining room—, which is the real distribution and not filler. `metodo` read 3 of 6 with the five criteria in one paragraph: the TASK is now six line-leading numbered steps injecting «nombre_restaurante», «momentos_fuertes», «meta_principal», «ventas_mes», «food_cost», «costo_laboral» and «tamano_equipo» into the working sections, because arraigo saw ZERO fields outside «YOUR RESTAURANT». `verificacion` goes from 2 to five imperatives. The SUPUESTO: line is added (recipe §0.1), which here is the heart of the card: targets are computed on the house's own figures and not on an industry percentage. Lead-magnet kit regenerated against the new body.v1.0.02026-08-18Initial version. Born in batch 13, the one that closes the artifact queue, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: area boards show their slice; the master sheet is the mother document they all hang from, and when they disagree the sheet rules.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 PASS on one board: ticket times per dish against their standard, kitchen returns with fixed reasons, 86'd …
N5 · Complete systemPurchasing on one board: key-item prices against their history, supplier compliance measured at the scale, pur…
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.