- Google’s new flights use AI to find trips based on conversation requests
- It uses Gemini 2.5 to interpret descriptions of feelings and vague time frames to prepare offers
- Flight Agreements are rolled out in Beta all over the United States, Canada and India
Google uses Gemini AI to reinvent the travel agency experience and transform conversations into airline tickets. The new Flight Deals product, now in beta, adds AI -Chat to Google Flights users looking for a bargain or who are still trying to decide where and when they will travel.
Instead of fitting with drop -down menus for destination and departure time, you can simply write the type of turn you want to take and whatever else may be important to you when traveling. Instead of an airport code and a date, you can choose a season, the mood of the location and how you feel with very early flights. Gemini will then scan prices in real time from hundreds of airlines and provide up -to -date options tailored to your request.
This is not a substitute for traditional Google aircraft. The familiar grid of dates and slides is still alive and well. But Google thinks flights are perfect for the flexible (or just indecisive) travelers. Think of it as the one friend who is not only really good at finding travel conditions, but really loves to find them for friends.
For example, when I wrote “I want to go where I can see the Northern Lights in December for a week.” I had suggestions for Alaska, Iceland and Norway with some great deals across December. When I requested “a place with mountains and good food in the spring,” I saw flights from March to June to Denver, Munich, Auckland and more.
Flitting AI
The more relaxed your wording is, the more it has to work with. AI will try to match not only the location but the spirit of your request. Gemini 2.5 has been behind the curtain in lots of recent Google products, but this is one of the first times it is used in this way.
It also marks one of Google’s clearest features that does not yet bring AI into a very public, popular space that finds offers on flights. Aviation tickets are perfect for enticing people to try AI, as buying them is a common but not everyday experience, and expensive enough that people will make an effort to find a good deal without being so expensive that people would not trust AI to help them when it is still possible for the technology to fail.
Flight offers still learn and it may not always choose the perfect itinerary. But if it helps people discover that, for example, flights to Oaxaca in January are very cheap and the mole is life -changing, it’s a victory.
