Introduction

wvx Copilot is a tool that enables intelligent analysis and response to customer inquiries across various communication channels. The 'wvx Copilot' component in Wolkvox Studio offers an advanced solution for managing these interactions using artificial intelligence.

In today's business environment, customer service is crucial for maintaining user satisfaction and loyalty. Wolkvox Studio, as part of the contact center service configuration software, provides tools to design customized interaction flows. The 'wvx Copilot' component, previously known as 'Mr. Wizard,' allows for the analysis of customer messages and the provision of automated responses based on prior training. This component is useful in various scenarios, such as:

• Chatbots: Interactions through WhatsApp, web, Facebook, Instagram, Telegram, and SMS.
• Voice (IVR): Transcription and analysis of voice messages.
• Interactions: Management of emails and social media interactions such as Facebook, Instagram, and Twitter.
• CRM Integrations and Webhooks: Automation of flows based on actions in CRM or external applications.

Configuration

The 'wvx Copilot' component in Wolkvox Studio is an advanced tool that enhances customer interaction management through artificial intelligence. Below is a detailed explanation of how it works and how to configure it:

• Domain Selection:
  • Field 'wolkvox copilot Domain': Here, you choose the wvx Copilot domain that has already been created and trained with PDF documents. This domain defines the context and knowledge that the AI will use to analyze messages.
• Question Configuration:
  • Field 'Question to wvx Copilot': In this field, you define the variable containing the customer's message to be analyzed. The variable can be $txt_query for chatbots, a voice-to-text transcription variable for IVR (e.g., obtained through the ASR component), or any other variable containing the message.
• Tests and Responses:
  • Button 'Test': Allows testing the component's response by typing a question in the 'Question to wvx Copilot' field. The response will appear in the 'Test Response' field.
  • Field 'Response Variable': Contains the name of the variable that will store the final response from wvx Copilot, which can be used in other components to display it to the customer.

Example of Using the 'wvx Copilot' Component Within a Flow in a ChatBot Routing Point

The main objective of this flow is to provide an efficient and automated customer service experience using the wvx Copilot component to respond to specific queries about financing, general questions, and sales. The flow is designed for ChatBot-type channels (WhatsApp, Web Chat, etc.), where customers can interact naturally and receive personalized responses based on their queries.

Below is a step-by-step description of how the flow is structured:

1. Start Component:
   1. The flow begins with the Start component, which is unique and mandatory in all routing points. This component marks the customer's entry point into the flow.
2. 'Reply Chat' Component:
   1. The Reply Chat component (also called Reply Chat) is configured with the message: "Welcome to wolkvox Cars. Type your query." This message is sent to the customer to initiate the interaction and prompt them to type their query.
3. 'Intents' Component:
   1. The next component is Intents, which is configured to detect three types of queries based on keywords:
      1. Financing: Keywords such as "finance," "credit," "loan," and "installments."
      2. General Question: Keywords such as "branches," "offices," "cities," "dealers," and "countries."
      3. Sales: Keywords such as "models," "cars," "vehicles," "motorcycles," "prices," and "buy."
   2. Depending on the detected intent, the flow splits into four possible routes:
4. Routes Based on Intents:
   1. Route 1: NO-MATCH
      1. If no intent is detected, the flow follows the NO-MATCH route, which returns the customer to the Reply Chat component to rephrase their query.
   2. Route 2: Financing
      1. If the financing intent is detected, the flow directs to a wvx Copilot component configured with the financing domain. This component analyzes the customer's message (captured in the $txt_query variable) and generates a response, which is stored in the $res_MrWizard variable. Then, a Reply Chat component shows the customer the response generated by wvx Copilot.
   3. Route 3: General Question
      1. If the general question intent is detected, the flow directs to a wvx Copilot component configured with the default domain. This component analyzes the customer's message (captured in the $txt_query variable) and generates a response, which is stored in the $res_MrWizard variable. Then, a Reply Chat component shows the customer the response generated by wvx Copilot.
   4. Route 4: Sales
      1. If the sales intent is detected, the flow directs to a wvx Copilot component configured with the sales domain. This component analyzes the customer's message (captured in the $txt_query variable) and generates a response, which is stored in the $res_MrWizard variable. Then, a Reply Chat component shows the customer the response generated by wvx Copilot.
5. End Component:
   1. The three routes (financing, general question, and sales) end in an End component, which is mandatory in all flows. This component marks the end of the interaction.

Note: This is a very basic example but ideal for understanding the possibilities of flows that include the wvx Copilot component. The possibilities are very broad depending on the objectives of the flows and the different options that the customer entering the flow may have. With Wolkvox Studio, you can design more complex and customized flows to adapt to the specific needs of your business.