In addition to its ability to interact with a human speaker, the chatbot implements an end-to-end process that identifies and extracts the information required by the user from back-end systems, supplying this information in real time within the context of a conversation carried out in natural language. The interaction between the user and the chatbot is immediate and does not require login procedures, resulting in a marked improvement of the service offered to the customer.
The bot can be accessed though a dedicated link or by scanning a QRcode, through which the user can automatically open the messaging application. The chatbot identifies the user and guides them towards the selection of a specific service through the use of an options menu.
This channel makes it possible to carry out different operations quickly and easily, such as allowing the user to consult their integrated utilities listing and spending, to request administrative and accounting information and to report issues and outages using geolocation tools, supported by images and descriptions of the specific problem.
Faced with such requests, the chatbot is able to locate and extract the necessary information from back-end systems, using a specific integration layer developed by Reply and incorporated within the bot. From an architectural point of view, the bot is designed on three different levels:
- an Api Layer that handles the conversation between the bot and the user’s chat application;
- a Core Layer that manages the access to machine learning algorithms;
- an Integration Layer that interacts with back-end systems and the company's CRM software using the OData protocol.