AI assistant · N5 Complete system
Profitability Plan Builder for Restaurants
Traces where your money leaks away — menu, purchasing, payroll, channels — and builds a 60-day plan to recover margin points, with a money target on each front.
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
- Selling well and earning little is the industry's silent disease: the dining room looks full, the bank account does not.
- Money leaks through drips nobody watches individually: unstandardized portions, a badly costed best seller, purchases from the usual supplier without quotes, overstaffed slow hours, platform commissions swallowing the margin.
- This assistant locates YOUR business's leaks, prices each one monthly, and organizes the repair into a 60-day plan where every action carries its money target.
What you end up with
A margin-leak map with an estimated monthly cost for each leak, the 60-day plan in table form (action, front, money target, owner, fortnight) and a prudent projection of recoverable margin points.
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 want to go from 8% to 14% operating margin in 12 months without raising menu prices. Where do I start?»
| Front | Leak detected | Estimated monthly cost | Supporting arithmetic | Confidence |
|---|---|---|---|---|
| Purchasing | Meat and poultry with no fixed-price agreement | 6,400,000 | 214 M × 34% food cost × 8.8% observed protein variation | Medium |
| Portion | 34 active dishes with no written gram weights | 4,300,000 | 2 food cost points on the 3 highest-volume references | Medium |
| Channel | Delivery platform commission on dining-room price | 5,100,000 | ~18% commission on the 13% of sales going through the platform | High |
| Labour | Location 2 shift outside lunch | 7,900,000 | 28% labour cost applied to low-occupancy hours | High |
| Price | Menu unreviewed for 11 months | 3,200,000 | Cost drift not passed on, over the 6 best-selling references | Low |
Estimated monthly leak: 26,900,000 COP, equal to 12.6 margin points on 214 M in sales. Figures estimated from the data provided; low-confidence ones get confirmed before acting.
| Fortnight | Front | Action | Cash target | Owner | How it is measured |
|---|---|---|---|---|---|
| 1 | Labour | Shrink location 2 to lunch and delivery | 7,900,000/mo | You | Hours paid outside lunch |
| 1 | Purchasing | 90-day fixed-price agreement on protein | 3,800,000/mo | Admin | Price per kilo on the invoice |
| 2 | Portion | Written gram weights and scale on the top 6 | 4,300,000/mo | Chef | Food cost of those 6 references |
| 3 | Channel | Differentiated platform pricing (+12%) | 2,600,000/mo | You | Margin per platform order |
| 4 | Price | Menu review on real costs, leaving the 6 anchor dishes untouched | 3,200,000/mo | You + chef | Weighted menu margin |
By day 60, with the high- and medium-confidence actions executed, operating margin should read between 11.5% and 12.4%, not 14%. Reaching 14% requires the full 12 months and two menu reviews.
By then food cost should sit between 31% and 32% (34% today) and labour cost between 25% and 26% (28% today). If at day 60 food cost has not dropped below 33%, the problem is not purchasing: it is portioning, and written gram weights are non-negotiable there.
Illustrative example generated with a fictional restaurant. Not a promise of results, not a client case.
This is 3 of 4 parts. Behind the wall: the **5 fronts with their 14 actions**, the execution order by dependency —what blocks what— and the supplier negotiation script.
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 Restaurant name, Business type and Active sales channels. 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.
v1.1.02026-08-13Body rewritten under the margin mandate: repair sequence in 6 numbered steps, five named output blocks, 8 business fields, named planning traps, five checks and figures with units. The version stays at 1.1.0 because the sample result was generated with 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.v1.0.02026-08-09Version inicial de la biblioteca viva.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
When something serious is happening in your restaurant — sales dropping, staff leaving, margin vanishing — thi…
N5 · Complete systemChoose at the top what you need from management today. In this one —deciding something big this week— it delib…
N5 · Complete systemOrganizes your restaurant's innovation as a system: an idea funnel, cheap pilots with a budget cap, and clear …
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.