Virtual Agent Hub

CXone Virtual Agent Hub allows you to manage the connections between CXone and the virtual agent providers you use in one place. When you add a virtual agent to Virtual Agent Hub, you provide the information CXone needs to communicate with the bot provider. This is one step in the process of integrating your virtual agents into CXone.

CXone supports virtual agents on voice and chat channels A way for contacts and agents to interact, such as voice, email, chat, social media, and so on.. The supported virtual agent A software application that handles customer interactions in place of a live human agent. providers are:

A virtual agent is a software application that handles interactions with customers in place of a live human agent. Many virtual agents can provide nearly human-level comprehension and interactions. Virtual agents use various technologies to provide these human-like interactions, such as:

Artificial intelligence (AI).
Natural language processing Also called NLP, this process understands human speech or text and responds with human-like language. (NLP).
Text-to-speech State that allows an agent to complete work requirements after finishing an interaction (TTS).
Speech-to-text Also called STT, this process converts spoken language to text. (STT, also called transcription).

Classics Inc., has decided that they would like to add self-service options to their contact center. They want to reduce the burden on their agents. Self-service options mean contacts can get answers to common questions without agent interaction. This will reduce the load of calls that their agents handle, so they will be free to focus on the complex cases.

The implementation manager, Ichabod Crane, looks at all of the natural language solutions that CXone supports. He decides to use Google Dialogflow ES. Google Dialogflow ES offers voicebot and chatbot solutions and has all the desired features. Using the CXone Virtual Agent Hub, he can:

Configure voicebots and chatbots directly in Studio.
Test the connected bots within the configuration window.
Set the language for his international contact centers.
Enable TTS Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. output.

By using CXone Virtual Agent Hub with CXone, Classics, Inc. can lighten the workload for their agents. Self-service bots can provide some of the more common answers to customers. This lets agents handle the more complex questions.

Conversation Flow for Voice and Chat Channels

During an interaction, the Studio action used in the script acts like a bridge between CXone and the virtual agent. It passes replies back and forth between the script and the bot. For voice interactions, the contact's utterances What a contact says or types. are transcribed Also called STT, this process converts spoken language to text. into text so the virtual agent can analyze them. The virtual agent's responses are converted into synthesized speech using a text-to-speech Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. service before being sent to the contact.

The virtual agent analyzes the contact's utterances to understand the intent for each one. Intents are the purpose or meaning behind what a person says. When the intent is identified, the virtual agent sends a response to the contact. The script passes it to the contact. When the conversation is complete, or if at any point the contact needs a live agent, Amelia lets the virtual agent action know. The Studio script continues, transferring the contact to a live agent if needed.

The conversation flow has some slight differences depending on the virtual agent A software application that handles customer interactions in place of a live human agent. Studio action Performs a process within a Studio script, such as collecting customer data, playing a message or music, or routing a contact to an agent. you use. There are two types of virtual agent Studio actions. Conversation actions handle very simple virtual agents and exchange actions handle complex virtual agents. The differences in conversation flow are found in the role the action plays in the conversation:

For simple virtual agents that use a conversation action, the action interacts directly with the virtual agent. It passively monitors the conversation, but doesn't handle any part of it.
When you use an exchange action, you can customize the bot's behavior from turn to turn. This gives you great control over the conversation.

Conversation and exchange actions both support chat and voice channels A way for contacts and agents to interact, such as voice, email, chat, social media, and so on..

Integration of Virtual Agent Bots

Integrating a virtual agent bot A software application that handles customer interactions in place of a live human agent. with CXone involves the following tasks:

Set up, configure, and test your bot with the virtual agent provider.
Create at least one Studio script with a virtual agent action.
Add and configure an app for your bot in Virtual Agent Hub, and link the app to the Studio action used in your script.
Test the connection and communication between CXone and the virtual agent.

Every virtual agent has unique requirements and configuration needs. The online help for each supported virtual agent bot provides information about the integration process that's specific to that provider:

Virtual Agent Hub Studio Actions

There are four virtual agent Studio actions. They connect CXone and your virtual agent. The virtual agent you use might work best with a specific action.

The virtual agent actions are:

VoiceBot Exchange and TextBot Exchange—Use these actions for complex bots or for when you need to customize the bot's behavior from turn to turn. Your script must include at least two instances of the action.
Voicebot Conversation and Textbot Conversation—Use these actions only for very simple bots. They don't allow for customization of the bot's behavior from turn to turn.

Virtual Agent Hub Version Control

Periodically, Virtual Agent Hub receives updates that are controlled through numbered versions. Upgrades of this kind are not applied automatically. You must manually select the new version for each of your virtual agent apps in Virtual Agent Hub. This gives you control over what version you're using and when you upgrade. This is important because some versions require you to update and test your scripts before moving to a new version.

If you have more than one virtual agent, you can choose the version for each one. Additionally, if you ever need to, you can revert one of your virtual agents to a prior version.

Some numbered versions are limited to certain virtual agent providers. Not all virtual agents have the option for every integration version. The following integration versions are available:

Version 1.0.0: This is the first version of Virtual Agent Hub. All virtual agent providers have this version.
Version 2.0.0: This version updated the schemas used with some virtual agents. It's only available for Google Dialogflow ES and CX.
Version 3.0.0: This version introduced StandardBot, which standardizes how CXone communicates with virtual agent providers. You can create template scripts that will work with any supported virtual agent provider. Additionally, the StandardBot tools allow you to test the communication between CXone and your virtual agent. This version is available for all providers.

You can check the integration version you're currently using on the Properties page of the app for your virtual agent in Virtual Agent Hub. The Integration Version field shows the version the app is currently using.

Use care when changing versions. The changes made from version to version can affect many aspects of your integration, including scripts, settings, schemas, and more. Changing to the wrong version without testing the upgrade first can result in your virtual agent not working as expected. This could result in your contact center's ability to handle contacts through that channel being disrupted.