MasterPrompt VaultBY MASTERESTAURANT

AI assistant · N5 Complete system

◆ Included in the annual plan💬 AI Community Managerv1.1.1 · 2026-08-20
📷 Works best with an AI that sees photos (invoices, dishes, screens) · optional

Community Manager KPI Board Builder for Restaurants

The board that rules on whether the social media role is paying for itself: every indicator with a written formula, a data source, a measured baseline, a numeric target and a direction — plus the house rule that at least one of them hangs off the register, because a board of reach and followers doesn't get approved.

N5
Depth
12/23
Your data
3
Compatible AIs
5
Steps to use it
Depth of the resulttap a level to see what you get
◀ Put out today's fireRun the year ▶
🏛️

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 level

Is this for you?

What it does and what you get

  • You pay someone to run social and at month's end you get a screenshot of new followers and reach that tells you nothing about whether it was worth it.
  • This assistant doesn't plan or check off tasks: it measures results.
  • It leaves you a five-to-seven indicator board with the line that separates vanity from business, each indicator carrying its formula, its data source, a baseline measured before any target gets written and an owner with a job title; plus the reading cut that says what happens when an indicator drops two periods running, so measuring ends in a decision rather than a screenshot.

What you end up with

The indicator board with its eight columns — indicator, written formula, data source, frequency, baseline, target, direction and owner —, with at least one row hanging off the register; the vanity line that separates traffic indicators from business indicators and states what each is good for; and the reading cut with the decision matrix for an indicator that drops two periods running, plus the retirement rule with date and reason.

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

Sazón de OrigenFictional contemporary Colombian restaurant in Medellín, 2 locations, 6 years in business. Every sample result in the library comes from this same case. Fictional restaurant

The owner asked this: «We're Sazon de Origen, contemporary Colombian cooking in Medellin, two locations and 24 people. I pay an agency 2,800,000 COP a month for Instagram and WhatsApp, and all they report is that we went from 3,100 to 4,700 followers in eight months. We sell 214,000,000 COP a month across both locations and Saturday lunch still closes at 38 covers per location. I want a short board that tells me whether that money is working.»

IndicatorWritten formulaData sourceFrequencyBaselineTargetDirectionOwner
Bookings sourced from socialbookings whose first contact came through Instagram or WhatsApp ÷ total bookingsbooking log, «how did you find us» columnWeekly9% (4 weeks measured)18% in 90 daysHigher is betterManager
Saturday lunch coverscovers served 12:00 to 3:00 p.m. on Saturday, per locationpoint of sale, daypart reportWeekly38 covers per location55 per location in 60 daysHigher is betterFloor lead
Own-delivery orders using the CASA codeorders with the code ÷ total own-delivery ordersown-delivery dashboard + kitchen ticketWeekly0, starts at zero60 orders per monthHigher is betterSocial lead
Average check on the day the Bandeja de la casa is pushedday's sales ÷ day's coverspoint of saleWeekly48,000 COP53,000 COP in 90 daysHigher is betterOwner
Minutes to first replyminutes between the guest's message and the first human reply, over 10 random messagesInstagram and WhatsApp inboxesWeekly5 hours 20 minutesunder 45 minutes during serviceLower is betterSocial lead
Accounts reached28-day reach reported by the appInstagram statsMonthly11,400 accountsideal range: never under 9,000Ideal range — traffic indicatorSocial lead

Figures are illustrative. Sazon de Origen's baselines get measured for 4 weeks BEFORE any target is written; until then the «Target» column carries a dash.

This is 2 of 3 parts. Behind the wall is the **reading cut**: the table pitting target against the last two periods with each indicator's verdict — what changes, what freezes, what gets retired with date and reason —, the rule on why an indicator is never judged on a single period, and the 90-day long cut that decides whether the social spend holds, grows or shrinks.

See the full example — free account

Works with these AIs

Claude — the best for this assistant Holds the eight-column table without losing the written formula, which is the column the others tend to summarize away. Paste your platform and point-of-sale reports at once and ask it to flag which indicator can NOT be calculated with what you have.

How to use it

Fill in My Restaurant with your peak dayparts, sales channels, average check and main goal: that's where the register-linked indicator comes from.
Copy the full assistant and paste it into the AI you use daily.
Tell it what you measure today and where you read it — platform stats, point of sale, booking log, a notebook — and answer its questions one at a time.
Take the board and do NOT write the targets yet: measure four weeks of real baseline and only then ask it for the objectives.
Read the board every Monday in 15 minutes and apply the cut: an indicator that drops two periods running forces ONE change, not three.

Which of your data it uses

12
of 23

This assistant works with 12 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.

Restaurant nameBusiness typeCity and countryYour main guestStrong and slow daypartsBest-selling dishesAverage check (with currency)Average monthly salesActive social channels (with the @ or the link)Active sales channelsCommunication toneMain goal this year

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.

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.

What you need to sort out
who does whatwhen each thing shipswhether the seat is paying

More assistants in this category

Included in the always-growing library

Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.

Community Manager KPI Board Builder for RestaurantsN5 · Complete system · Included in the annual plan See the plan

Exclusively for restaurant leaders

AI Executive · Artificial Intelligence for Restaurants

Make 1 person produce like 5. In 8 weeks you turn Artificial Intelligence into a new productivity department inside your restaurant: content, sales, finance, manuals, automations and specialized assistants.

I want to implement AI in my restaurant →
NEW AI Executive — executive Artificial Intelligence program for restaurant leaders