AI assistant · N5 Complete system
Financial Presentation Builder for Restaurants
Your restaurant's numbers told for a decision: the story in three acts, one figure per slide with its source at the foot, the economics per table and per dish, and the concrete ask at the end — in a presentacion.html you project to the bank, the partner or the board without asking any program's permission.
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
- The owner who can run a restaurant can rarely present one: they walk into the bank with a twelve-tab spreadsheet, or to a partner with three figures from memory, and the decision gets postponed for lack of understanding.
- This assistant turns the restaurant's numbers into a presentation that decides, inside one file: the story in three acts — where we stand, what explains the result, what we ask —, a single leading figure per slide with its source written at the foot, the business economics brought down to table, dish and day, and the close with the concrete ask: how much, what for and when it comes back.
- The scenario simulator computes what would happen; THIS assistant tells what already happened and what is being asked, for an audience that decides in twenty minutes.
What you end up with
The 10-to-14-slide script in three acts — each with its leading figure, its source at the foot and its spoken line —, the presentacion.html file you project with the arrow keys, and the rehearsal routine with clock and the hard-question rule.
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 am asking the bank for a loan to remodel the Centro location. My sales and costs are current, but every time I present numbers the meeting tangles up. I need a presentation an analyst understands in twenty minutes.»
Written before the first slide: audience, credit analyst · decision sought, approval of the remodelling loan · real time, 20 min. With that line, act three gets built first and the other two are trimmed towards it.
| # | Act | Slide | Leading figure | Comparison | Source |
|---|---|---|---|---|---|
| 1 | Where we stand | The house in one slide | locations · years open · month's sales | against the same month last year | P&L + POS |
| 2 | Where we stand | The rhythm of sales | 12-month rolling sales | against the previous half | POS |
| 3 | Where we stand | What one table leaves | contribution margin per occupied seat | lunch against the slow evening | POS + recipes |
| 5 | What explains it | Cost under control | prime cost with its 12-month series | against the house target | P&L |
| 6 | What explains it | The full room and the empty one | table turnover in the full shift | against the slow shift | POS |
| 8 | What we ask | The ask | amount and term | — | proposal |
| 9 | What we ask | Where the payment comes from | the installment against the slowest month's cash flow | 12 months of flow | cash flow |
Rule visible on every slide: one big figure, its comparison beside it and its source at the foot. A slide with two protagonists splits in two.
Slide 3, complete: the big figure — what an occupied lunch seat leaves —; the comparison — against what it leaves on the slow evening —; and the line said out loud: «every lunch table already pays its share; the remodel buys seats in the shift that is running out of room».
SUPUESTO: occupancy in the remodelled shift is projected from the real occupancy measured in today's full shift, not from an industry benchmark percentage. If real occupancy afterwards came in lower, the installment stops being covered by lunch and has to lean on the evening: the slow scenario goes on the next slide, not in a footnote.
The weak figure, presented and not hidden: labor cost went up and appears in act two with its cause —two split shifts the new menu no longer needs— and its dated plan. The analyst was going to find it anyway; finding it explained is worth more than not seeing 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 are **the presentacion.html file with its presenter view** and **the clocked rehearsal routine**: the three passes with what each allows, the cutting rule and the reserve slides for the bank's three hard questions.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 10 of the 23 fields in «My Restaurant», among them Restaurant name, Business type 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 duel debt: it scored 67.2 out of 90.0. The `cifras` signal read ZERO, which in a financial-presentation card is the corpus's own irony: the body used the word «figure» eleven times and carried not ONE with its unit — every window was spelled out in words («twenty minutes», «twelve months», «three passes»). The meeting is now sized in 20 min or 45 min, the prime cost series runs 12 months, the script is reviewed within 7 days and the decision is counted at 30 days. `metodo` read 3 of 6 because the five criteria sat in one paragraph: the TASK is now six line-leading numbered steps injecting «ventas_mes», «food_cost», «costo_laboral», «ticket_promedio», «numero_sedes», «nombre_restaurante» and «meta_principal» into the working sections, because arraigo saw ZERO fields outside «YOUR RESTAURANT». `verificacion` read 2 of 5 and `lexico` 3 of 10: they are now five imperatives, and prime cost, food cost, labor cost, contribution margin, break-even, average ticket, covers, occupancy, table turnover, sales mix, sales channel and delivery are named — the vocabulary an analyst expects to hear from a restaurant. The SUPUESTO: line is added (recipe §0.1): the remodelling projection leans on the house's measured occupancy, not on a baked-in industry percentage. Lead-magnet kit regenerated against the new body.v1.0.02026-08-18Initial version. Born in batch 13, third published c17 assistant, with the full lead-magnet kit and a Sazón de Origen example. Its written boundary: the scenario simulator computes futures under declared assumptions; this one tells the present to the decision-maker — three acts, one sourced figure per slide, and the concrete ask at the close.More assistants in this category
Hand your P&L spreadsheet to the AI and receive the verdict in owner's language: where the profit went, which …
N5 · Complete systemHand over your spreadsheet —sales, costs, P&L or all three— and get a board of twelve charts where the money s…
N5 · Complete systemThe «what if» with numbers instead of gut: rent goes up, sales drop, prices rise, Sundays open — every scenari…
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
