Passengers per day


Messages handled


Saved per request


Of conversations automated


RATP is the operator of Paris’ public transportation systems. It manages and maintains a network of metro, tramway, bus, and RER train services.



Paris, France

Use cases

FAQs, lost objects, schedule information, itineraries, upcoming trains, alerts, and push notifications

Reinventing customer service with a virtual agent

In the past, RATP was manually answering each question and complaint coming from their website, Facebook Messenger, Twitter, and customer service phone line. Manually dealing with this significant volume of requests proved to be both time and cost-intensive. Moreover, their customers were often disappointed by how long it took to connect with a support agent.

With the help of Mindsay, RATP’s new virtual agent has reduced the load on the customer support team by providing commuters with instant answers to many of the most frequently asked questions. As the first line of support, the bot can resolve most level 1 customer support questions. This drastically reduces the number of requests that need to be handled by support agents. Furthermore, the bot gathers information from users during the conversation, providing the human agent with the information they need to solve the problem.

Drastic customer support savings

With more than 11 million daily commuters, managing a sizeable volume of daily requests is a costly proposition. This is especially true when the cost to resolve a single issue once reached more than €18. The high cost can mostly be attributed to the delays and manual processes that were needed to resolve each request.

The most notable improvement since implementing the Mindsay bot has been the reduction in the number of requests. With the bot learning every day, it is now handling 84% of conversations. This has allowed RATP to significantly reduce their agents’ workloads, freeing up time for them to focus on important or complex requests.

Customer wait times have also been cut down. One of the main causes of service delays was the lack of information agents had for each commuter’s request. Now, the virtual agent asks questions and uses the answers to provide agents with the information they need to quickly resolve the problem or answer the question.

With the help of Mindsay’s smart virtual assistant, RATP has significantly
improved its customer service and reduced costs.

Meeting new challenges

On Facebook Messenger, RATP’s chatbot is focused on another task: providing live transit information. The chatbot shares transit schedules and the arrival time of the next bus or metro train while also allowing users to create alerts. The option to set an alert for a specific metro or bus line is one of the most used features. A commuter can ask the bot to notify them if their metro or bus line is running on-time. Not only is it a useful feature for commuters, but it also proactively prevents hundreds of support requests.

Furthermore, RATP is now able to go one step further and send push messages if there are major transit disruptions like strikes, demonstrations, accidents, construction, or closures.

“We recommend Mindsay for their support, their perfect understanding of our needs, and their reactivity”

Patricia Delon
Marketing Director @RATP

More success stories

How Iberia offers a better passenger experience

How SNCF reduced the number of customer support tickets

Manage your support costs with Mindsay