AI assistant · N5 Complete system
Team Results Board Builder for Restaurants
The board that hangs where the team sees it: who is ahead and at what, with indicators each person can move through their own work, its cut-off and the rule of how it is won —so it motivates instead of breeding resentment.
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
- Teams sell more when they see their name on the board — but a badly designed ranking rewards whoever gets the good table and punishes the slow shift, and the incentive kills the margin it meant to create.
- This assistant, pasted into an agent that creates files (Claude with Cowork or Claude Code), designs the competition with fair rules —metrics normalized per shift, not raw— and BUILDS the leaderboard: an HTML file where you paste the week's numbers and the board ranks, celebrates whoever climbs and shows each person how to catch the one ahead.
What you end up with
A working leaderboard.html file: the week's podium, a standings table with sales per shift worked, average ticket and suggestive selling per person, streak badges, and the game rules printed at the bottom with the costed prize and the weekly update routine with an owner.
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: «Build the leaderboard for my 8 servers. I have the POS close for the last 8 weeks.»
With no baseline there is no incremental, and with no incremental the prize comes out of the owner's pocket.
| Data | Where it comes from at Sazón de Origen | What for |
|---|---|---|
| Sales per server per shift | Daily POS close, 8 weeks | Normalize: points per shift, never per total |
| Personal average ticket | POS, average ticket per server | Measure how they sell, not what they were dealt |
| Suggested-sell placed | POS product report | The only one of the three the server fully controls |
| Shifts and consumption moment | Weekly schedule | Tuesday lunch is not Saturday night |
SUPUESTO: the average contribution margin of the menu as declared by the house is used. If the real one were 5 points lower, the prize stops paying for itself and has to be cut.
Week 32 · Podium: 🥇 Marcela (94 pts) · 🥈 Andrés (88) · 🥉 Paola (81).
| # | Server | Sales/shift | Avg. ticket | Suggested-sell | Points | Streak |
|---|---|---|---|---|---|---|
| 1 | Marcela | $612,000 | $48,900 | 34% | 94 | 🔥 3 weeks |
| 2 | Andrés | $588,000 | $51,200 | 29% | 88 | ▲ up 2 |
| 3 | Paola | $541,000 | $46,100 | 31% | 81 | = |
| … |
Below it, the prize of the month bar (180,000 COP) with the arithmetic in plain sight: it pays for itself with a 1.4% improvement over the baseline, and comes out of incremental margin — not the margin that already existed.
A note printed on the board itself: tips and covers served are not ranked here. That pits the team against the service and teaches people to turn tables fast instead of selling better.
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 **fair-play rules**: how the three metrics are weighted, normalization by shift and consumption moment, how sick leave is handled without damaging the table, and how streaks are calibrated so the last-placed keeps playing.
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 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.
v1.3.02026-08-27It was called «Constructor del Leaderboard del Equipo para Restaurantes». Diego's instruction, 2026-08-27: «this name is not understood, what is a lamina? if it is not understood it does not get used». A title that has to be translated does not get opened, and what does not get opened does not exist. The assistant's body does not change: what changes is the word it is searched and found by.v1.2.02026-08-25Body rewritten to pay down duelo debt: it scored 44.0 out of 90.0, the worst in the corpus. The method was written as a paragraph, so the `metodo` signal read ZERO on a method that was actually good; it is now six numbered steps that also inject «fields» into the TASK (required by arraigo). Deliverable pieces are named by block, five BEFORE YOU DELIVER checks are written out, and a SUPUESTO line is added so the AI declares its own benchmark instead of the house hard-coding one. Rises to 97.5.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 build files inside an agent.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
Pick the area above and whether you watch one location or the network, and the assistant builds THAT board: th…
N5 · Complete systemThe «sábana» —Latin American kitchen slang for the wide sheet where everything fits at once— is the master mea…
N5 · Complete systemThe PASS on one board: ticket times per dish against their standard, kitchen returns with fixed reasons, 86'd …
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.
