AI assistant · N3 Analysis with a verdict
Sales Mix Analyzer for Restaurants
Reads your sales mix like a consultant would: concentration per dish, popularity index by category, daypart and channel differences, and the bias promotions inject into the numbers.
N3Analysis with a verdict
Crosses YOUR numbers and takes a stand, with a table, units and currency. Not options: a recommendation you can defend.
◆ This assistant 24 of the 164 published assistants are at this levelIs this for you?
What it does and what you get
- Your POS report tells you what sold; it does not tell you what it means.
- This assistant turns that listing into a mix diagnosis: how much revenue your top 10 dishes concentrate, which items are genuinely popular within their own category, what shifts between lunch and dinner or dine-in and delivery, and where a promotion is inflating a number you believe is organic.
What you end up with
A mix diagnosis with a concentration table, per-dish popularity index within its category, daypart and channel comparison, and a list of signals that call for a decision.
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: «Here are this month's sales by dish, daypart and channel. What is the mix telling me?»
| Rank | Dish | Units | Revenue | Cumulative % |
|---|---|---|---|---|
| 1 | House platter | 620 | 44,640,000 | 20.9% |
| 2 | Three-meat sancocho | 480 | 28,800,000 | 34.3% |
| 3 | Ajiaco | 355 | 17,750,000 | 42.6% |
| 4 | Grandmother's dessert | 240 | 6,720,000 | 45.8% |
| 5 | Garlic trout | 210 | 13,860,000 | 52.3% |
| 6 | House rice | 190 | 8,740,000 | 56.4% |
6 of 34 references make 56% of revenue. The other 28 split 44%, averaging 3.3 M each. Figures in COP.
- The platter concentrates 21% of revenue: a strength and a risk. What happens to your month if your meat supplier raises 15%?
- The ajiaco ranks 3rd in units and 5th in revenue: priced low for its demand. Are you giving away the dish most people ask for out of habit?
- 13% of sales go through the platform and contribute 7% of margin: every point that channel grows costs you margin. Is it growth or expensive volume?
- Sunday makes 22% of weekly sales with 14% of open hours: why is the Sunday menu identical to Tuesday's?
- 17 references sell under 40 units a month: each one costs inventory, waste and kitchen time. Which survive a menu review?
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: the **popularity-by-category** table with the index for all 34 references, and the daypart comparison against the same month last year.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 8 of the 23 fields in «My Restaurant», among them Cuisine or concept, Dish descriptions (paste your menu) 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.
v1.1.32026-08-26TASK now uses the restaurant's data instead of naming it only in the header. `motor/arraigo.py` had it below the house minimum: it named the client's data in YOUR RESTAURANT and then worked without it. The method was not touched -it was well written-: what changes is that the work is now done AGAINST the restaurant's figures.v1.1.22026-08-14Spelling: Spanish accents restored in the prose. No field marker, link or meaning changed.v1.1.12026-08-14Spelling fix: año/años with ñ in the Spanish text (markers untouched).v1.1.02026-08-13Body expanded under the margin mandate: 6 numbered steps, 5 named output blocks, 8 business fields, named traps, verification checklist and figures with units. Version kept because the published sample result is tied to it.v1.1.02026-08-12Card expanded as a lead magnet (doc 11): who it is for, a sample result with the fictional restaurant Sazon de Origen, recommended AIs and a measured depth level. The assistant body did not change.More assistants in this category
Builds the complete menu engineering matrix for your menu: every dish classified by cash contribution margin a…
N3 · Analysis with a verdictDesigns your menu's complete pricing policy: ladder per category, endings consistent with your positioning, a …
N4 · Executable planNames your new dishes and rescues the ones nobody orders: twelve candidates, four verifiable discard criteria …
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
