Peki chatbots run on the MLNET algorithm and involve language recognition, verification and correction algorithms. It makes a guess with x% probability when it is suitable for which of the classes it is trained, and directs the incoming sentence to the relevant class, if any, or to the “default” flow. Classes are 100% created by the Peki Bot administrator.
You can define the response of the artificial intelligence as a static message, or you can direct it to the streams you will create using rich media plug-ins. The help desk on pek.io provides information on the capabilities of all rich media kinds.
Artificial intelligence can parse the words in an incoming phrase that you want to understand, so it can skip a question if it also includes information you want to learn about the flow. The parsing process helps artificial intelligence correctly grasp the specific request of the client and control the flow.
Bot History function. You can historically list all the bot correspondences on a user basis.
Thanks to the live chat interface, your agents can continue their conversation from the live chat interface on Peki without interrupting the correspondence, in the section you want the chatbot to transfer to the agent about the parts that are insufficient or not trained.
Peki has a store which involves integrations to 3rd party apps and also has access to ready-made bots. You can easily integrate your bot into any 3rd party application via this store.
You can access comprehensive reports on the use of the bot through the analytics tab, where you can access all the basic data about chatbot and live chat.
Making reservations for a hotel, an airline, a bus, etc. buying tickets, checking in, using an electronic ticket, sharing information with a travel assistant during the entire process, changing or canceling tickets, etc.
Bill payment, money transfer, fast payment, collection bots for social media shopping, statement inquiry thanks to secure login.
Opening a service case, after-sales support, frequently asked questions, and rapid response to inquiries are all examples of customer service and help desk functions.