AI assistant · N5 Complete system
Inventory Dashboard Builder for Restaurants
The stockroom on one board: theoretical vs physical per key item, inventory days that are idle money, stockouts that switch dishes off and upcoming expirations — in an inventarios.html that sustains the counting cycle week after week.
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
- Between one count and the next, the stockroom talks and nobody listens: the gap between what should be there and what is, the idle money on shelves, the dish that switches off at 8 because something ran out, and what expires on Thursday.
- This assistant builds your inventory board in one file: theoretical vs physical per key item with its variance in money, inventory days per family, stockouts with their hour and switched-off dish, and upcoming expirations with their exit plan.
- The leak detector organizes the FIRST count and finds the hole; THIS board sustains the cycle — each week's count, the trend and the fix with an owner.
What you end up with
The inventory indicator dictionary with formula, source, frequency and owner; the ABC classification of your items; the inventarios.html file with the four blocks — theoretical vs physical, inventory days, stockouts, expirations — and the weekly counting routine written into the file, with the single fix and its confirming figure.
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 count at month end and something's always missing that nobody explains. The fridge lives full, and still I ran out of chicharrón at 9 on Friday. I want the stockroom in numbers.»
The house ABC: A = pork, chicken, cheese, oil and rice — 68% of the month's purchased money, counted weekly; B every two weeks; C monthly. With 5 A items the count fits in 40 minutes, so the list is cut right: had 14 been left, it turns back into the whole afternoon nobody repeats.
| Indicator | Formula | Source | Frequency | Owner | Target |
|---|---|---|---|---|---|
| Theoretical-physical variance | (theoretical − physical) / theoretical | count + standard recipe + POS | Weekly (A items) | Storekeeper | ≤ 2% |
| Inventory days | stock / daily consumption | count + invoices | Weekly | Manager | Proteins ≤ 4 days |
| Stockouts | shortage with hour and switched-off dish | pass sheet | Daily | Head chef | 0 on A items |
| Upcoming expirations | units at 5 days or less | fridge review | Weekly | Storekeeper | 0 to the bin |
SUPUESTO: the ≤ 2% variance is not an industry truth: it is taken as a starting target because it is what your own July count already reached on chicken and cheese. If this house's real cut were 4%, the pork alarm switches off and the board stops being useful — which is why the target gets revised at the third count, with your data.
| A item | Theoretical | Physical | Variance | In money |
|---|---|---|---|---|
| Pork (chicharrón) | 41.0 kg | 38.2 kg | −6.8% | 96,000 this week |
| Chicken | 29.5 kg | 29.1 kg | −1.4% | within target |
| Cheese | 12.0 kg | 11.9 kg | −0.8% | within target |
The reading, accusing nobody: the pork variance does not come from portioning —the kitchen board's sampled portion weights came back green three weeks running—, so suspicion lands on scale-less receiving, which is exactly where the purchasing board had already been asking for one.
Idle money: rice holds 19 days of stock and turns in 6; 240,000 sleep on a shelf and Tuesday's order goes down.
Friday's stockout: the chicharrón switched off at 9:10 — 14 unsold bandejas in the dining room and 6 dropped delivery orders, which are not recovered the same way: a table changes dish, a delivery cancels. It is the star dish, so the stockout does not cost one plate, it costs the whole table.
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 inventarios.html file and the counting routine** — Thursday's 40 minutes over the A items, the single fix with owner and confirming figure, the expiration exit plan and the written cross-links to kitchen, purchasing and costs.
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 Best-selling dishes. 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 69.4 out of 90.0. The `metodo` signal scored 3 of 6 —criteria ran as a paragraph, «First… Second…», and the meter only counts steps at line start— and `lexico` scored 3 of 10 on the card with the strongest claim to trade vocabulary: a stockroom board that never said standard recipe, portion weight, costing sheet, food cost variance or sales mix. The TASK is now six numbered steps injecting «ventas_mes», «platos_estrella», «canales_venta», «food_cost» and «meta_principal» (required by arraigo), with a step of its own for declaring which recipe each theoretical comes from and flagging the dishes with no written recipe, which are the board's precision ceiling. A SUPUESTO line is added, and with it the example stops presenting «≤ 2% variance» as an industry truth: it is now declared as a starting target with its origin and its revision date. Rises to 96.7.v1.0.02026-08-15Initial version. Born in batch 9 of the artifact titles, the eighth c19 area board, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: the leak detector organizes the first count; this one sustains the cycle — weekly ABC count, trend and fix with an owner.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.
