The following scenarios outline some ideal use cases for Smart Conversations:
Your customer is unhappy, and the chatbot is unhelpful. Using Natural Language Understanding (NLU) the system receives negative sentiment analysis in real-time and, consequently, an alert is sent, or the customer is transferred, to an agent immediately. The customer gets help right away and gives 5 stars for the service they received. Learn more about NLU.
Your customer sends voice messages in WeChat. The system receives the transcript of the voice message, along with the sentiment result. The live agent’s responses provided to the customer, along with a record of the whole conversation, are stored as text, which makes it very easy to review and evaluate agent performance. Learn more about Transcription.
Your customer is reaching out on Facebook Messenger to get help from customer service. The agent needs to verify the customer’s ID in real-time. The chatbot asks the customer to send a picture of their driver’s license. Using IRIS the system receives the data extracted from the ID and matches it against the customer database. The next agent in queue responds to the customer and has all the customer information in front of them. The customer quickly gets the help they need. Learn more about IRIS.
Your customer can’t start their car in the middle of the night. They reach out to their car breakdown company using WhatsApp. The company has 24/7 support, but they have fewer experienced agents working at night. Using AskFrank the system receives the search results of previous conversations that match the same issue reported by this customer. The next available agent in the queue is presented with the resolution and can quickly help the customer. The customer is very satisfied. Learn more about AskFrank.