AI assistant · N5 Complete system
Ideal Staffing Plan Builder for Restaurants
Sizes the team by time slot and day — not by average — crossing real sales load against the labor-cost ceiling, and says where you're over, where you're short and what each gap costs.
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
- Payroll is the business's second cost and it's almost always built by habit: the people «there have always been», spread across the usual shifts.
- The result is the two classic leaks — Tuesday at 4 with three people staring at an empty room, and Saturday at 1 with service bursting and guests who don't come back.
- This assistant builds the plan from load: how much sales enters per slot and day, how many people per position that load demands, what it costs against the labor ceiling, and how to move from the current roster to the ideal one without breaking service or the law.
What you end up with
The load map per slot and day with the sales entering each one; the ideal roster per position and shift with projected cost against the ceiling, and the gaps versus the current roster stated in money; and the 4-week transition plan with owner, peak rule and monthly review.
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 people and I feel there are too many midweek and too few on Saturday. I do not know where to start moving.»
Before touching payroll, the map. The daily average said «slow Tuesday, strong Saturday»; the 2-hour band says exactly where.
| Band | Tue | Wed | Thu | Fri | Sat | Sun |
|---|---|---|---|---|---|---|
| 12:00–14:00 dining room | 9% | 10% | 11% | 13% | 12% | 14% |
| 14:00–16:00 dining room | 3% | 3% | 3% | 4% | 5% | 6% |
| 19:00–21:00 dining room | 11% | 12% | 14% | 22% | 28% | 17% |
| 19:00–21:00 delivery | 6% | 7% | 7% | 9% | 11% | 10% |
The reading, in two lines: the real peak is Friday and Saturday from 19:00 to 21:00, and dining room and delivery load different roles in the same band. The leak is 14:00 to 16:00 Tuesday to Thursday, where three people cover 3% of sales.
SUPUESTO: the load criterion used is the cubiertos per server the house declares for its format, not a textbook standard. If the real criterion were one cover less per server, the Saturday peak calls for one more person and the valley gap stays the same.
| Role | Today | Ideal per shift | Gap in people | Gap in money/month | Shift that corrects it |
|---|---|---|---|---|---|
| Server, valley (14–16 h) | 3 | 1 | −2 | saving | Moved to the Friday peak |
| Server, peak (19–21 h Fri-Sat) | 3 | 5 | +2 | cost | Part-time starting 30 min earlier |
| Kitchen, peak | 2 | 3 | +1 | cost | Staggered, starts 18:30 |
| Driver | 2 | 2 | 0 | — | No change |
The verdict: the house does not need to hire two people; it needs to move two. The projected costo laboral stays under the declared ceiling and the Saturday peak ends up better covered than today.
A note printed on the plan itself: the first move is to redistribute, never to cut. Letting the valley people go leaves Saturday just as overwhelmed and takes the best day's ticket promedio down with it.
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 4-week transition with the peak rule**: what moves each week and who communicates it, why chronic overtime costs more than a part-time shift, the order of review to exhaust before any layoff, and the sales threshold that triggers the recalculation.
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.
v1.1.02026-08-25Body rewritten to pay down duelo debt: it scored 69.3 out of 90.0. The `verificacion` signal read 1 of 5 and `lexico` 1 of 10 —a card that sizes payroll and named neither costo laboral nor costo primo—, and the method ran as flat prose, so `metodo` counted 3 of 6 steps. The TASK is now six numbered steps that inject «fields» (required by arraigo, which flagged 0 fields in the working sections), BEFORE YOU DELIVER carries five explicit checks, and the SUPUESTO line makes the AI declare its own load criterion —covers per server, costo laboral ceiling— instead of the house hard-coding an industry standard. The card's declared limit is kept: it does not know local labor law and asks the rules before fixing shifts. Rises to 96.7.v1.0.02026-08-15Initial version. Born in batch 3 of the artifact titles, opens the Org Structure category, with the full lead-magnet kit and a Sazón de Origen example. Its rule: the average is payroll's great liar — the roster is built per slot against real load.Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
