Nowadays, customers want to get important information instantly and conveniently. Days of dialing your 0800 customer service phone numbers are slowly but surely coming to an end. That’s why banks and financial institutions these days try to improve customer experience by automating part of the communication. Main goals of banking chatbots are to facilitate two-way communication with customers and to remove the burden from the bank's customer support. The basic tasks such as account status, bank account details, questions about loans etc. are something that a bot can handle efficiently on its own, thus allowing the customer service agents to devote their time to complex issues. According to a report by Juniper Research for every query that a chatbot handles, banks save 4 minutes of an agent’s time.
Read further if you want to find out how to build and deploy a banking chatbot.
This use case will demonstrate how to define, design, build, and deploy a chatbot which can engage your customers and provide them with relevant information about their account status.
1. Login to the web interface and select Answers module.
2. Click the Create chatbot button and create a new chatbot. Mandatory fields to be able to create the bot are Bot name and Channel for which you should select WhatsApp.
Before you activate the bot, make sure you also configure the rest of settings, such as the Sender number, Language, Escape phrases, and Session Timeout.
3. If you have the intent training file prepared, import it. Otherwise, go to Intent tab and manually create necessary intents required for the dialogs.
4. Based on the bank's input and conversation design, create all required attributes. Attributes can help you with saving relevant information, e.g. user information, json files, locations, or similar.
5. If conversation design requires keywords, create keywords as well.
6. Once most of the intents, attributes, and keywords exist in the Answers platform, start with dialog design. Based on the conversation schema, use the necessary elements to build the dialogs starting with the selection of the intent.
7. You are able to use elements like Send text, Attribute, Call API,Conditions to create dialogs according to your design (and include authorization steps needed to confirm your clients identity).
8. After you finish designing the dialogs, use the Simulator tab to check how well your dialogs perform in simulations of real-life conversations.