AI assistant · N5 Complete system
HR Dashboard Builder for Restaurants
The team on one board: turnover with its replacement cost, absenteeism by time band, the cross-training matrix that says who can cover which station, and why leavers leave — in an rrhh.html read once a month with one people decision.
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
- In restaurants, people get managed by crisis: turnover is felt when the kitchen second quits, the skills gap is discovered the day the grill cook falls sick, and nobody knows what replacing the last leaver cost.
- This assistant builds your people board in one file: turnover translated to replacement money, absenteeism with its time band, the cross-training matrix — who can cover which station and where the house depends on a single person —, and the exit interview: why leavers leave.
- The leaderboard rewards service-game performance and the labor-cost analyzer measures the month's money; THIS board watches the team's health, month after month.
What you end up with
The people indicator dictionary with formula, source, frequency and owner; the rrhh.html file with the four blocks — turnover with cost, absenteeism by band, cross-training matrix, interviewed exits — and the monthly people routine written into the file, with the single decision and the critical station's coverage plan.
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: «Four people have left this year and I don't even know what it cost me. The grill cook is the only one who knows the grill, and someone is always out on Mondays. I want to see my team in numbers.»
| Indicator | Formula | Data source | Frequency | Owner | Numeric target |
|---|---|---|---|---|---|
| Annualized turnover | departures over 12 months ÷ average headcount | Payroll | Monthly | Owner | see SUPUESTO |
| Replacement cost | recruiting + paid training + newcomer's curve | Payroll + POS | Per departure | Manager | visible on every departure |
| Absenteeism by slot | absences ÷ scheduled shifts | Schedule | Weekly | Manager | down against the previous 8 weeks |
| Stations with no backup | stations with 1 single capable person | Cross-training matrix | Monthly | Owner | 0 |
| Departure reasons | count by fixed-name reason | Exit interview | Per departure | Owner | none repeated 3 times |
SUPUESTO: no «normal» industry turnover is used as a target — it changes by country, by format and by year, and a borrowed figure on a board the owner shows the team is worse than none. The house's own turnover over the previous 12 months is taken as the baseline and the target is to lower it. If the owner finds a local, trustworthy reference, this target gets replaced and the traffic light recalibrated.
Today's verdict: 4 departures on a team of 9. The cost of the last one, counted in full — recruiting, 2 weeks of paid training and the newcomer's curve, which comes out with more waste and looser portioning —, appears on no profit-and-loss statement and is eating the labor cost, and with it half the prime cost.
Cross-training matrix (rows by station, columns by person):
| Station | Holder | Can cover 2nd | Can cover 3rd | Light |
|---|---|---|---|---|
| Grill | Jorge | — | — | 🔴 single person |
| Fryer | Doña Rosa | Camilo (partial) | — | 🟡 |
| Register | Marcela | Andrés | Manager | 🟢 |
| Dining room | Andrés | 2 more people | — | 🟢 |
Absenteeism with slot and reason: over the last 8 weeks, 6 of the month's 9 absences fall on MONDAY and 4 are from the same split shift. With 8 weeks behind it this can already be called a pattern, and the reading is not laziness: it is the Monday split shift against low occupancy, and it gets fixed with the schedule. The schedule is rebuilt against covers per person in each slot, with the delivery shift counted separately.
The backup rule: Jorge trains Camilo on the grill against that station's standard recipe, with a start date and the training shifts counted. The first-Friday cells are filled in under 5 min; where data is missing, the cell says PENDING with its owner.
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 is **the people routine template**: the 20 min of the first Friday, the single-decision rule with owner, deadline and the figure that confirms it, the 5-point checklist with the 3 exit-interview questions, and the two cross-links written out to the labor-cost analyzer and the leaderboard.
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 Team size. 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 72.1 out of 90.0. `lexico` was at 2 of 10 — a restaurant people board that never named the restaurant trade — and `cifras` at 3 of 12; the team's health is now counted in the terms it is paid in: turnover, labor cost, prime cost, occupancy, covers per person, sales channel, delivery, the station's standard recipe, and the waste and loose portioning of the newcomer's learning curve, which is precisely turnover's invisible cost. `metodo` was at 3 of 6 because the only numbered steps sat in the FORMAT and the TASK was a paragraph reading «One… Two… Three…»: it is now six numbered steps injecting «tamano_equipo», «ventas_mes», «momentos_fuertes», «canales_venta» and «meta_principal» (required by arraigo). `verificacion` was at 2 of 5: BEFORE YOU DELIVER goes from six questions to five imperative checks. And the hard-coded benchmark targets are removed — a «≤ 35%» turnover and a «≤ 3%» absenteeism written as universal truth —: the card now orders that figure declared with the SUPUESTO: line, because a normal turnover changes by country, by format and by year. Rises to 97.5.v1.0.02026-08-15Initial version. Born in batch 10 of the artifact titles, the ninth c19 area board, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: the leaderboard rewards the game, the analyzer measures the month's money, the staffing plan sizes; this one watches the health of the people already here.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.
