KLM builds BB with DialogFlow

External Case study | Conversational AI

Share on facebook
Share on google
Share on twitter
Share on linkedin

Amsterdam-based KLM Royal Dutch Airlines is the oldest global airline still flying under its original name. KLM was founded in 1919. They serve more than 30 million passengers annually, they operate more than 200 aircraft, and fly to 163 destinations worldwide. Next to that, they’re also the third-largest private employer in the Netherlands. 

The average customer flies with the airline 1.4 times per year. As such a KLM customer might not take time to download the KLM’s mobile app to book a flight. For that customer, KLM wanted “a new entry point”. An entry point that provided opportunities for interactions using text or voice: conversational interactions. “A conversational experience allows for that personal approach. It brings warmth and personality to conversations with our customers,” says Ruben Klerks, KLM social media manager.

“For us, social media includes all messaging channels and assistive platforms like the Google Assistant,” says Martine van der Lee, KLM director of social media. Klerks adds, “We believe KLM should go to the customer, and be where they are.”



The airline began exploring ways of providing a conversational interface for customers in 2016. KLM decided to go for Dialogflow after testing a few alternative platforms. “We really love Dialogflow,” van der Lee says. “It has really strong natural language understanding (NLU) capabilities, which meant we were able to automate a large part of the conversation. And Dialogflow was very easy for our developers to use. We were able to build and ship the experience really quickly.”

The KLM Messenger bot

KLM’s first project was a booking bot for Facebook Messenger. The booking bot was introduced in September 2017. KLM dubbed it ‘BB,’ for Blue Bot (blue being their signature color). BB’s persona is female, friendly, helpful and professional. She is also a bit edgy, and occasionally even show a little touch of humor. “If you want to make a booking through Messenger, BB will ask you for your destination, when you want to fly, etc.,” van der Lee explains. “We’ll show you the options, and you can purchase, fill out your personal details, and get your booking confirmation, all right there on the conversational app.” By connecting BB with the airline’s CRM system, a human agent can quite easily take over if BB is unable to answer.

Several months later, the airline created another way for customers to interact with BB. In December 2017, KLM launched a packing service for the Google Assistant. “BB will guide you through everything you need to bring to your destination and for the length of your trip,” van der Lee says. “She asks all the right questions—such as if you need to arrange for a visa, or if you need to bring medicine—so travelers are prepared for their trip. Based on the weather forecast, she will check if you need to bring extra clothes or an umbrella.”

BB was developed within a few months, a cross-functional effort that involved members from marketing, IT, communications, copywriting, UX, engineering, and more. 


The KLM application on the Google Assistant


So far, the airline is happy with BB’s strong early performance. One of KLM’s insights is that they learned that customers love chatting with BB just to discover humorous easter-egg responses to different kinds of questions.

KLM plans to merge packing and the booking experiences. In this way customers can easily tackle the logistics of trip planning and focus on their vacation itineraries.

KLM’ll also continue to grow BB’s capabilities. “Our goal is to help travelers throughout the entire customer journey,” Klerks says. “We really see BB as an extension of the KLM service family.”

Our latest blogposts

Case studies

Conversational with Ticketmaster

Using Dialogflow Ticketmaster connects people with tickets and events faster through conversational applications The world’s top live-event ticketing company is Ticketmaster. Founded in 1976, Ticketmaster

Read More »
Case studies

Case study: KLM

KLM builds BB with DialogFlow External Case study | Conversational AI Share on facebook Facebook Share on google Google+ Share on twitter Twitter Share on

Read More »