AI assistant · N5 Complete system
Community Manager Job Description Builder for Restaurants
The job description that gets signed, not the task list that gets forgotten: what belongs to the community manager and what to the kitchen, the floor or the agency; what gets posted alone, what gets consulted, what never gets decided without the owner; and a trial-period review with a number at each date.
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
- Almost nobody fires a community manager for posting badly: they fire them because nobody ever wrote down where the job ended.
- With no boundary, the role inherits delivery, the register and inventory, and two months later the person leaves with nobody able to say whether it went well.
- This assistant drafts the document both sides sign: the accountable-and-consulted table, the three signature levels, deliverables with quantity and unit, the minimum profile with its interview red flags, and the 30, 60 and 90-day review with numeric criteria.
What you end up with
The role's boundary as an accountable-and-consulted table, with kitchen, floor and agency named; the three signature levels with their consultation deadline; deliverables by frequency with quantity, unit and review point; the minimum profile with four red flags and the question that exposes each; and the 30, 60 and 90-day trial review with an indicator and a numeric target at every date.
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, 24 people —18 in operations, 6 in admin— and an average check of 48,000 COP. I'm hiring my first permanent person for Instagram and WhatsApp, part-time, 1,400,000 COP a month. Last time they ended up taking delivery orders and closing the register, and after 2 months they left without me being able to say whether it had gone well. I want a paper we both sign and that lets me decide at 90 days.»
| Function | Accountable | Consulted | What does NOT belong here |
|---|---|---|---|
| Calendar and posting on Instagram | Community manager | Owner signs off on Mondays | Changing menu prices (28,000 to 72,000 COP) or the menu order |
| WhatsApp statuses and conversation | Community manager | Delivery lead when the message is an order complaint | Taking and dispatching the order: the delivery line belongs to operations |
| Photo and video of plated product | Community manager | Head cook, who says what's on today | Plating a Bandeja de la casa for the camera that differs from the served one |
| Google reviews for both locations and the delivery platform | Community manager drafts | Owner signs when the review mentions health or a charge | Offering money back or a free delivery |
| Paid media | The agency | Owner, with the month's budget (900,000 COP) | Moving the budget without a signature |
| Register, inventory and delivery routes | Operations (18 people) and admin (6) | — | None of this belongs to the role, and it's in writing |
That last row is what stops last year from repeating. The role can lend a hand on a packed Sunday, but it never shows up in the review and never justifies one post less: its 1,400,000 COP wage sits in the 28% labor cost, not in the operations budget.
Posts alone: the 4 approved posts of the week, stories of the day's lunch, answers about hours, both addresses and the menu's price range.
Consults first (committed reply within 2 hours during the 12:00 to 14:30 service, 24 hours outside it): one-star reviews, allergen questions, a delivery that arrived cold or incomplete, a pitch from a local creator.
Never decides without the owner: prices and promotions that touch the margin —with 34% food cost and 28% labor cost the prime cost stands at 62%, and a 2-for-1 on the 38,000 COP Bandeja de la casa eats the month—, any answer about hygiene or legal matters, and deals with the delivery platform or with agencies.
| Frequency | Deliverable | Quantity with unit | Where it's reviewed |
|---|---|---|---|
| Daily | Instagram and WhatsApp inbox | 0 pending at close; none waits over 24 hours | Screenshot in the team group |
| Daily | Stories of the plated lunch | 2 a day, shot before 11:40 a.m. | The account itself |
| Weekly | Posts from the approved calendar | 4 a week, each with its commercial objective written | Monday huddle, 20 minutes |
| Weekly | Reviews answered | Every new one, in under 48 hours | Google and platform dashboards |
| Monthly | Results readout | 1 page: Tuesday-to-Thursday evening covers, own-delivery orders and messages asking for a table | Owner meeting, first Monday |
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 part that decides hires: the **five-requirement minimum profile**, the **four interview red flags** with the question that exposes each and the answer that confirms it, and the **30, 60 and 90-day trial review** with its own-delivery order targets, the COP arithmetic explaining why it is measured that way, and exactly what happens when a date is missed.
See the full example — free accountWorks with these AIs
How to use it
Which of your data it uses
This assistant works with 13 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.
v1.1.12026-08-26Declares what it does NOT do. `motor/alcance.py` had flagged it as high risk —its title names a role, or its body promises to act on a system— and with no `limites_es`/`limites_en` the public page was promising by omission.v1.1.02026-08-20The instructions stop fitting any restaurant. The role's boundary is drawn against the declared team size — whatever is not the role's gets a named owner and, if nobody is left, that gets said before splitting a function between two; deliverables are counted only across the accounts and channels the house actually has open; and the 30, 60 and 90-day review is judged against the year's goal, so an indicator that fails to move it drops off the paper. The data used to sit in the header while the task described a generic seat.v1.0.02026-08-19Initial version. Born in the August 2026 marketing batch because the operating manual already said how the work gets done and there was still no paper saying whose it is. From today the role has a boundary, three signature levels and three dates with a number: hiring, delegating and reviewing stop being arguments from memory.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
The board that rules on whether the social media role is paying for itself: every indicator with a written for…
N5 · Complete systemA comment isn't answered for the person who wrote it: it's answered for the people reading. This writes the th…
N5 · Complete systemChoose at the top where the message lands: a direct message or a public comment. In this one —the direct messa…
Included in the always-growing library
Access to every published assistant, adapted to your AI and personalised with your restaurant's data, updates included.