AI assistant · N5 Complete system
FAQ Answer Builder for Restaurants
The bank of the twenty or thirty questions that repeat every day, each with ONE written canonical answer —the one the server says, the one that goes in the message and the one you publish—, with its hard fact, its owner and its review date. It doesn't send itself: a person says it, and that's why it risks no account.
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 schedule changed in July and by October the written message still showed the old hour, because that hour lived in five places and nobody knew which.
- That is what this piece fixes, and it is an operations problem, not a writing one: one answer per question, the hard fact behind it, the name of whoever really knows it, and the date it must be looked at again.
- It also does the two things almost nobody does: harvest the questions from message history and from the door —not from what the owner imagines— and give every answer an expiry date, because a canonical answer with no date rots quietly and keeps circulating.
What you end up with
The canonical bank as a table, 20 to 30 rows sorted by frequency, with the question in the customer's words, its single answer, the hard fact behind it, who knows it and when it gets reviewed; the per-channel versions with each maximum length and the fact untouched; and the maintenance sheet with owner, last review, next date and the trigger that expires a row early.
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: «We're Sazon de Origen, contemporary Colombian cooking in Medellín: two locations, 6 years, 24 people, a 48.000 COP average check and a menu between 28.000 and 72.000 COP. Between Instagram and WhatsApp people ask me the same things all day —hours, parking, whether we reach Envigado, whether anything is gluten-free— and everyone answers differently. In July we moved Sunday closing to 4:00 p. m. and three Sundays later the WhatsApp auto-reply still said 6:00 p. m. I sell in the dining room, through my own delivery and one delivery platform, and I'm after taking operating margin from 8% to 14% without raising menu prices.»
| Question, in the customer's words | Canonical answer | Hard fact behind it | Who knows it | Reviewed |
|---|---|---|---|---|
| «what time do you open?» | «Tuesday to Saturday 12:00 to 9:00 p. m. Sunday 12:00 to 4:00 p. m. Closed Mondays.» | Signed schedule for both locations | Location manager | Every 30 days · and the day it changes |
| «is there parking?» | «In Laureles yes, 8 own spaces. At the other location no, but there is public parking 60 metres away.» | Spaces counted, not estimated | Location manager | Every 90 days |
| «do you deliver to Envigado?» | «Our own delivery reaches Laureles, Estadio and Belén. Envigado only through the delivery platform.» | Current coverage map | Delivery lead | Every 30 days |
| «do you have anything gluten-free?» | «Yes: the Trucha al ajillo is made without flour. The kitchen is not gluten-free: it is shared with every other dish.» | Standardized recipe card for the trout, confirmed in the kitchen | Head cook | Every 30 days · and with every menu change |
| «how much is the Bandeja de la casa?» | «38.000 COP.» | Current menu price, inside the 28.000 to 72.000 COP range | The owner | Every 90 days |
| «is it enough for two?» | «The Bandeja de la casa is served at 520 g: enough for one hungry person, or two sharing with a starter.» | Portion weight on the recipe card | Head cook | Every 90 days |
| «how do I book?» | «By WhatsApp, up to 8 people and 3 hours ahead. From 9 people up the location manager confirms by phone.» | Booking policy for both locations | Location manager | Every 90 days |
| «can I bring my dog?» | «Yes, on the Laureles terrace. The Poblado location is indoors and doesn't take them.» | House rules per location | Location manager | Every 90 days |
| «what payment methods do you take?» | «Cash, card and transfer. On our own delivery, cash on arrival too.» | What the register accepts today, not in 2024 | Register | Every 30 days |
Sorted by frequency over 4 weeks of history: hours and delivery coverage take close to half of everything that lands. Figures are illustrative: yours come from counting your own messages, not from an internet average.
| Where it's used | Maximum length | How the opening-hours row reads |
|---|---|---|
| WhatsApp, quick reply | 2 lines | «Tue–Sat 12:00–9:00 p. m. · Sun 12:00–4:00 p. m. · Closed Mon. Shall I hold a table?» |
| Instagram, public comment | 1 line | «We're open until 9:00 p. m. today, see you here!» |
| Instagram, direct message | 3 lines plus the menu link | Full hours for both locations + address + link |
| Profile card and digital menu | 1 fixed line | Full hours, no decoration |
| Delivery platform | The dashboard's hours field | Edited in the dashboard the same day, not next week |
| Dining room, what the server says | 1 sentence | «On Sundays we close at 4:00, so the kitchen takes the last order at 3:30 p. m.» |
Six places, one fact. The day Sunday moved to 4:00 p. m. what failed wasn't the wording: what failed was that nobody held the list of the six places. That list is this table, and that's why it sits glued to the bank instead of in the manager's head.
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 sits **the maintenance sheet**: the six critical rows with their owner, last review, next date and the trigger that expires them early —the holiday, the menu change, the neighbourhood that opens—; plus the COP arithmetic for what three Sundays announcing an hour that no longer existed actually cost, and the rule that blocks publishing any answer with no owner and no date.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 14 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.
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.
v2.0.12026-08-27It now declares the «See photos» capability, so the AI selector warns before you open the prompt in one that lacks it, instead of letting you find out mid-task.v1.0.02026-08-20Initial version. Born because the messaging family already had plenty of answerers —the library, the comments, the direct messages, the flows— and none of them had anywhere to take the fact from: opening hours lived in five templates and changing one meant lying in the other four. It brings the canonical bank with a single answer per question, harvested from history and from the door, with its hard fact, its owner and its review date, so that changing something means changing it in one place.v2.0.02026-08-27It stops being an AUTOMATION and becomes a SCRIPT. Diego's call: the useful piece is what gets answered —in which words, with which fact, and what is NOT promised—; automating the sending is what risks getting the account shut down. It moves home to Service Scripts and Protocols, where what somebody says lives.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.
