A ground breaking app, which offers live chat recommendations on where to eat, is hoping to change the way we dine out around the world.

Noisy tourists will be banned from Parisian cafes and restaurants.
Luka offers dinner recommendations based on profile of your taste.

Luka has started out modestly in San Francisco and the Bay Area of California but is hoping to expand its reach into Europe by the end of the year.

The apps uses artificial intelligence to find and then book the best places to eat using an informal chat interface.

Once you’ve signed up for an account, you simply ask Luka a question, based on your own particular tastes. For instance, if you were in the mood for pizza or pasta, you would simply ask: ‘Where is the nearest Italian restaurant?’

Or if you have no idea where you want to go, it will offer up a couple of suggestions and get feedback after you have eaten.

Over time, it will build up a profile of your tastes while scanning online reviews to ensure its recommendations are always up to date.

San Francisco welcomes cricket cooking. Image by Dave Glass / CC BY-SA 2.0

The app also sends digital cards for each restaurant with access to menus, hours of operation, contact details and the exact location.

It also remembers your preferences, handy for vegetarians or vegans, or people who have a particular aversion to certain types of food.

Eugenia Kuyda, one of the co-founders, told Lonely Planet: ‘In a nutshell we’re in San Francisco Bay Area now and are looking to expand to New York and more cities in US and Europe by the end of the year. We’re also going to be covering more topics, not just restaurants, and are launching tons of new functionality.

‘Our plan is going niche after niche – first restaurants, then something else. Being fully automatic allows us not only to scale fast, but also to create a system that learns from the users and can be part of group chats.’

The development team describe the app as a ‘cross between Yelp and Siri’, Apple’s famous personal assistant.

Where Luka differs from established websites is that it takes a lot of the hard work out of searching for a suitable restaurant.

It will only offer a few options, rather than asking users to trawl through endless restaurants … acting a bit like that friend you have who has eaten literally everywhere.

Explore related stories