AI assistant · N5 Complete system
AI P&L Spreadsheet Analyzer for Restaurants
Hand your P&L spreadsheet to the AI and receive the verdict in owner's language: where the profit went, which line got out of control, and a monthly reading file ready to rerun.
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 P&L arrives from the accountant in a language that is not the owner's, and the decision gets postponed another month.
- This assistant, pasted into an agent that can read and create files (Claude with Cowork or Claude Code), takes your income-statement spreadsheet as it arrives, audits it (duplicated lines, months that don't reconcile, mixed costs), translates it into the house structure —sales, cost of sales, prime cost, operating expenses, profit— and delivers the verdict with the three lines that took the most profit versus last month.
- It closes by building you a monthly reading file so the P&L stops being a document and becomes a decision routine.
What you end up with
Three pieces: the spreadsheet audit with each finding and its cell; the month's verdict —the P&L translated into the house structure, the 3 lines that took the most profit versus last month in your currency, prime-cost and break-even traffic lights, and the 5 decisions with owner and deadline—; and the lectura_pyg.html file ready to rerun the reading every month.
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 June and July P&Ls for my two locations. Tell me what changed and where to look first.»
No line gets discussed before its total reconciles. Four of them did not.
| Finding | Sheet and cell | Severity | Proposed fix | Who confirms |
|---|---|---|---|---|
| Norte's rent is charged to both locations in July | P&L!C18 and D18 | 🔴 | Leave it on Norte only; July's total drops 4.2 M | Accountant |
| «Other expenses» holds 9.2% of sales with no breakdown at all | P&L!row 41 | 🔴 | Split into 4 lines before the next reading | Manager |
| July delivery came in net of commission and June gross: sales are not comparable | P&L!C6 vs D6 | 🟡 | Redo July gross and move the commission to channel cost | Manager |
| Depreciation appears in neither month | absent | 🟡 | Confirm whether it is kept on another sheet | Accountant |
| Line | June | July | Change in money | Change in % | Traffic light |
|---|---|---|---|---|---|
| Sales | 148.2 M | 141.6 M | −6.6 M | −4.5% | 🟡 |
| Cost of sales | 46.1 M | 47.9 M | +1.8 M | +2.7 pts of sales | 🔴 |
| Payroll | 34.7 M | 32.7 M | −2.0 M | −0.3 pts of sales | 🟢 |
| Prime cost | 54.5% | 56.9% | — | +2.4 pts | 🔴 |
| Operating profit | 11.3 M | 4.1 M | −7.2 M | −4.7 pts | 🔴 |
The 3 thief lines, in money: Centro's cost of sales (−2.9 M, and the file shows purchases flat: that is inventory or waste, not price); double-charged rent (−4.2 M, a recording error, fixed before deciding anything); reclassified delivery commission (−0.9 M, not a new loss — sales that were never yours).
July's break-even, recalculated with the contribution margin from the file itself: 132.4 M a month, that is 4.4 M a day, about 94 covers a day at the 46,900 average ticket the file yields.
SUPUESTO: prime cost is compared against the ceiling this house declared on its own card, not against a sector average. If this house's real ceiling were 3 points higher, July would stop being red and turn amber, and the first decision would change line.
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 decisions template and the three questions for your accountant** —each backed by its cell— plus the lectura_pyg.html file with its NEXT MONTH zone.
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, Business type and Number of locations. 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.
v1.2.02026-08-25Body rewritten to pay down duelo debt: it scored 49.6 out of 90.0. The `metodo` signal read ZERO —the three deliverables were written as one running paragraph, without a single step at the start of a line— with `verificacion` at 1 and `cifras` at 1. The TASK is now six numbered steps that inject «fields» (required by arraigo), the OUTPUT FORMAT names its pieces by block with their columns, and BEFORE YOU DELIVER carries five checks on things that can actually go wrong. Reading against sector averages is removed and the SUPUESTO line added. Dating it today wakes alcance: the title says «with AI» and the card declared no limits; `limites_es` and `limites_en` are written.v1.1.02026-08-14Card expanded as a lead magnet (doc 11): who it is for, a sample result with the fictional restaurant Sazón de Origen and recommended AIs with an honest note on agent delivery. The assistant body did not change.v1.0.02026-08-14Born in the TOOLS line (Diego's 2026-08-14 commission): assistants that read and build files inside an agent.More assistants in this category
Hand over your spreadsheet —sales, costs, P&L or all three— and get a board of twelve charts where the money s…
N5 · Complete systemYour restaurant's numbers told for a decision: the story in three acts, one figure per slide with its source a…
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.