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 · Last updated 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 |
| Deployment | Nova Air |
| Expected outcome | A reservation over WhatsApp or email goes straight into the integration, including at the moment nobody is near the phone. |
How far your sector has come
Hospitality applies AI least often of all sectors, alongside transport and construction, at 6 to 7 percent — against 54 percent in information and communication. That makes sense: in hospitality the work is on the floor, not behind a screen. Which is exactly why it stands out when reservations are confirmed within a minute while the rest of the street replies the next morning.
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.
An allergen question is not an ordinary question
Taking, moving, confirming and reminding bookings is ordinary work for an assistant. Allergens are not. There the information duty from Regulation (EU) No 1169/2011 applies, and the subject touches food safety.
The workable line is: relay word for word what the kitchen recorded, and hand the conversation over the moment someone asks whether they can safely eat something. The difference between 'does this contain nuts' and 'can I eat this' is the difference between passing on information and giving advice.
An allergy note is also health data. It belongs to that one booking, not in a guest profile that lasts for years. And a note about a no-show is a judgement about a person; an AI does not write that down.
The whole story, from age checks to what happens to booking data, sits in AI and guest contact in hospitality.
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.
What we need from you
This differs per sector, so it sits here rather than in a generic checklist:
- Your reservation system and capacity per time slot, including what you keep free for walk-ins.
- From what group size a request goes to you instead of being confirmed automatically.
- Your current opening hours and closing days — the most frequent question and the fastest to go stale.
How a project runs — intake, analysis of your existing communication and a shadow week in which nothing is sent yet — is set out on the approach page.