AI assistant · N5 Complete system
Multi-Location Purchasing Dashboard Builder for Restaurants
Purchasing as a NETWORK: the same item compared across locations, consolidated volume negotiating for all, the standardized master catalog and the supplier who can survive your next opening — in a compras-red.html that buys as a group, not as scattered stores.
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
- When the second location opens, purchasing splits in two without anyone deciding it: each manager negotiates alone, the same cheese arrives at two prices, and the volume that together would earn a discount is lost to separate buying.
- This assistant builds the NETWORK purchasing board in one file: the same item compared location against location, consolidated volume with the figure that creates negotiating power, the master catalog of standardized items — one specification per item for the whole house — and the supplier test: who can survive the next opening and who is already at their limit.
- A single location's purchasing board watches the price at its own door; THIS one compares the doors against each other and buys as a group.
What you end up with
The same-item comparator across locations with the gap in money, the standardized master catalog with one specification per item, the compras-red.html file with its four blocks, and the monthly negotiation table written inside, with owner and deadline per agreement.
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 three locations and each administrator buys on their own. I suspect the same cheese comes in at two prices, but I have never put it in a table.»
Every price was brought to the same unit before being compared — comparing different presentations manufactures gaps that do not exist.
| Item | Centro | Norte | Sur | Gap % | Money per month |
|---|---|---|---|---|---|
| Mozzarella (kg) | $18,400 | $21,900 | $19,100 | 19% | $612,000 |
| Beef loin (kg) | $42,000 | $43,100 | $46,800 | 11% | $498,000 |
| Sunflower oil (l) | $9,200 | $9,400 | $9,300 | 2% | $36,000 |
The verdict: Norte buys expensive on 7 of the 12 key items. The network average said cheese was «in line» — and the average was exactly what hid the location paying 19% more.
SUPUESTO: the discount this volume should win is taken from what the house has already negotiated before, not from a textbook figure. If the real achievable discount were half, the saving over 12 meses halves and the negotiating table is still worth holding.
The volume that pools the three locations is what goes to the table — one negotiation, not three.
| Item | Network volume/month | Supplier | Proposed unified price | Saving over 12 meses |
|---|---|---|---|---|
| Mozzarella | 340 kg | Lácteos del Valle | $18,400 | $7,344,000 |
| Beef loin | 180 kg | Cárnicos Unidos | $42,000 | $5,976,000 |
Master catalogue, the row that prevents the fake saving:
| Item | Single specification | Location already meeting it |
|---|---|---|
| Mozzarella | 5 kg block, low moisture, for oven | Centro |
| Beef loin | Centre cut, aged 21 días, 180 g per portion | Sur |
A note printed on the board itself: the specification is set by the dish's escandallo, not by the invoice. Dropping the loin calibre to win on the purchase is paid back next month in merma from porcionamiento and in food cost.
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 compras-red.html file, the supplier test and the monthly table**: which supplier holds the next opening and which is already at its limit, the single-source critical items with their deadline, and the negotiating routine with an owner and a signed agreement.
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 City and country. 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 72.3 out of 90.0. The `cifras` signal was literally ZERO —a network purchasing board without a single figure carrying a unit— and `lexico` read 2 of 10; the method ran as flat prose and `metodo` counted 4 of 6. The TASK is now six numbered steps that inject «fields» (required by arraigo, which flagged 0 fields in the working sections), the BEFORE YOU DELIVER checks are five and explicit, and a SUPUESTO line is added so the AI declares the discount it expects from volume instead of the house hard-coding one. What sets this card apart from the single-location purchasing one is kept: the network, the location-against-location comparator, consolidated volume and the homologated master catalogue. Rises to 93.1.v1.0.02026-08-18Initial version. Born in batch 13, first published c32 assistant, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: a single location's purchasing board watches its own door; this one compares locations against each other and negotiates with the whole network's volume.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
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
