An AI colleague for your restaurant: reservations that no longer slip
Reservations come in exactly when you can least deal with them: during service. Nova takes them via WhatsApp, checks availability, confirms immediately and sets group requests aside for you. No more missed messages at eleven at night, and no empty table because someone never got a reply.
Published on
The problem in this sector
Evenings + weekend WhatsApp explodes. Reservations missed, empty tables stay empty.
| Aspect | For this sector |
|---|---|
| Channels | WhatsApp · E-mail |
| Own knowledge | Menu, allergens, opening hours, link to your reservation system |
| Volume per day | 400 messages (80/hour) |
| Expected outcome | Reservation booked right away, even in the evening. No more missed WhatsApp bookings. |
That table is an example configuration, not a measured average. We do not yet have clients in production, so there are no field figures to show — and invented figures are worse than none. What it shows is the setup we would propose for this type of business, with the volumes that go with it.
Where the limit sits
One subject stays entirely out of reach here: allergens and dietary requirements. Not because the AI cannot look it up, but because a wrong answer there makes someone ill and the liability sits with you. Nova takes the question and passes it to the kitchen; it does not answer it. That is a deliberate limitation, not a shortcoming.
Concretely, these are the things Nova does not do on its own here:
- Answering questions about allergens, ingredients or dietary needs — those always go to the kitchen.
- Refusing a reservation or removing someone from the list when overbooked.
- Making commitments about a table, a room or a price for a group.
That limit does not live in a setting someone can flip by accident; it is established up front. That is the difference between a system you know the behaviour of and one you find out about afterwards.
The general rules on automated decision-making and transparency are set out in AI and the GDPR for SMEs and the AI Act for SMEs.
How it starts
It starts with a fifteen-minute intake call where we look at which work recurs in your case and lends itself to being taken over. We then analyse your existing communication from the past 90 days, so Nova learns your tone rather than a generic one. A shadow week follows in which it prepares drafts for you to review — only once that is right does it start sending on its own.
That shadow week is not a formality. It is the moment where it becomes visible which work the AI genuinely handles and which work should stay with a human — and that differs more per business than per sector.