MasterPrompt VaultBY MASTERESTAURANT

AI assistant · N4 Executable plan

◆ Included in the annual plan⭐ Reviews, Reputation and Automated Messagingv1.1.1 · 2026-08-26

Positive Review Reply Builder for Restaurants

Writes the replies to four and five-star reviews: sorts them by what each one brings, hands out a long reply or a short line accordingly, and leaves every long reply with a quotable dish and a concrete ask aimed at a slot that still has chairs.

N4
Depth
7/23
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 ▶
🗺️

N4Executable plan

A plan with owners, deadlines and the metric you review. Not advice: an agenda someone can execute on Monday.

◆ This assistant 23 of the 164 published assistants are at this level

Is this for you?

What it does and what you get

  • A good review is the only sales piece a guest writes for free, and almost nobody answers it.
  • Answering all of them with the same sentence looks worse than not answering: forty identical replies on one screen teach the mould before the message.
  • This assistant separates the ones that bring something —a dish, a person, an hour— from the two-line ones, writes each differently, and puts into the long ones the noun a stranger can order and the ask that whoever wrote well will actually accept.
  • The negative review does not belong here: that one protects, this one cashes in.

What you end up with

Five chained blocks: the triage table with its discard rule, the replies written one by one in a long and a short version, the ask table with its slot and its review date, the bank of eight openings and eight closings, and the weekly routine with a cut-off hour.

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: "I have 31 four and five-star reviews from the last two months across Google and the delivery platform, and I have answered none of them. I do not want to send the same sentence forty times."

31 four and five-star reviews in 60 days: 19 on the Google map and 12 on the delivery platform. None answered. The queue is not ordered by date or by stars, but by what each review brings with it.

TypeHow manyWhat gets doneWhy
Names a dish, a person or a moment9Long reply of 55 to 70 words, signedIt brings raw material: something concrete to repeat in front of the reader
Four stars with a "but"5Long reply, first in the queueIt is the only place a stranger sees that somebody here listens
Two lines, no content, under 45 days12One 20-word line, no dish and no askSpending the good reply on "All very good" throws it away
Two lines, over 45 days5No replyAnswering two months late tells the reader that nobody here is watching

That is 14 long replies and 12 short lines. At six minutes for a long one and one for a short one, 96 minutes: an hour and a half of a Tuesday, not a project.

What was ruled out, and why. Three of the nine that name something are past 21 days, and the clock rule would send them to the short line. It gets broken here on purpose: what they bring —the server's name, a Sunday sancocho— still works today for whoever is comparing restaurants on the map, and the short line wastes it. They get the long reply, without pretending it happened yesterday.

Answering all 31 was ruled out too. Thirty-one replies in a row on the same screen, written on the same Tuesday, read like exactly what they would be: a batch. The two-line review with two months on it goes unanswered and nothing happens; last week's two-liner gets a line that differs from the one beside it.

This is 3 of 5 parts. Behind the wall sit the two pieces that make this repeat without turning back into a template. The bank: eight numbered openings with the exact situation each one fits and eight closings with their rule of use —four end in an ask with a day and a slot, two in the name of whoever signs, two by handing the word back to the kitchen— plus the three batch rules: no opening repeats within the month, no dish passes a third of the long replies (with 14 long ones, a cap of 4 per dish) and the split between signers goes by location, not by day. And the Tuesday routine, cut off at 10:30 a.m.: pull the list, triage, four-star ones first, the repetition check read out loud, and the two figures of the month's last Tuesday.

See the full example — free account

Works with these AIs

Claude — the best for this assistant The best fit here: it holds fourteen replies in a row without falling into the mould and takes the instruction not to reuse an opening already spent.

How to use it

Gather last month's four and five-star reviews with date, platform and the text copied as written, not summarised.
Copy the assistant into your preferred AI along with your business details and tell it which slots are slow: that is where the ask lands.
Answer the queue in the order it gives you and leave unanswered the ones it marks, which is a decision too.
Read every reply before it goes out: the assistant drafts, and you paste it with your own account on each platform.
Log date, channel and ask for each one, and at 30 days count how many came back.

Which of your data it uses

7
of 23

This assistant works with 7 of the 23 fields in «My Restaurant», among them Restaurant name, City and country and Best-selling dishes. 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 nameCity and countryBest-selling dishesStrong and slow daypartsActive sales channelsCommunication toneAverage check (with currency)

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.

Which review came in
negativepositive

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.

Positive Review Reply Builder for RestaurantsN4 · Executable plan · 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