Virtual Agent Hub

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

The following image shows the main page of Virtual Agent Hub. Existing virtual agent configurations appear on the left side of the page.

A virtual agent is a software application that handles interactions with customers in place of a live human agent. They can be helpful in many kinds of situations, such as providing triage to determine the kind of information or help contacts need. 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 Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. (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 voice and chat virtual agent solutions and has all the desired features. Using the Virtual Agent Hub, he can:

Configure voice and chat virtual agents directly in Studio.
Test the connected virtual agents 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 Virtual Agent Hub with CXone, Classics, Inc. can lighten the workload for their agents. Self-service virtual agents can provide some of the more common answers to customers. This lets agents handle the more complex questions.

Supported Virtual Agents

CXone supports virtual agents on voice and digital channels A way for contacts to interact with agents or bots. A channel can be 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:

Virtual Agent Provider	Supports Voice *	Supports Digital Channels
Amazon Lex V1	Yes, utterance-based	Yes
Amazon Lex V2	Yes, utterance-based	Yes
Cognigy	Yes, SIP Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel	Yes
Enlighten Autopilot	Yes, SIP backchannel	Yes
Google Dialogflow CX	Yes, utterance-based	Yes
Google Dialogflow ES	Yes, utterance-based	Yes
IBM Watson Assistant	Yes, SIP backchannel	Yes
Microsoft Azure	Yes, utterance-based	Yes
Omilia	Yes, SIP backchannel	Yes
Salesforce Einstein	Yes, Voicebot Gateway and TTS-enabled	Yes
Custom Virtual Agent Integrations	Yes, utterance-based	Yes

* Learn more about the supported voice connection options.

CXoneBot Builder is another available virtual agent option. Using it, you can create your own virtual agents from scratch. Bot Builder is managed outside of Virtual Agent Hub.

Conversation Flow for Voice and Chat Channels

The beginning of the conversation is different for voice and text virtual agents:

For voice virtual agents, contacts The person interacting with an agent, IVR, or bot in your contact center. call a phone number and reach your organization. The contact may be connected directly to the virtual agent, or they might need to choose an option in an IVR Automated phone menu that allows callers to interact through voice commands, key inputs, or both, to obtain information, route an inbound voice call, or both. menu. Once the conversation with the virtual agent begins, 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 to 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. Transcription and speech synthesis can happen in CXone or, in some cases, in the provider's platform.
For text virtual agents, contacts start a conversation using a chat window. The location of the chat window varies depending on the specific channel A way for contacts to interact with agents or bots. A channel can be voice, email, chat, social media, and so on. you use. For example, it might be located on your website or the contact could start the conversation from the location of a third-party service, such as Apple Messages for Business. The contact's utterances are already in text format, so they don't need to be transcribed. They're passed on directly to the virtual agent.

After the conversation has started, the virtual agent analyzes the contact's utterances to understand the purpose or meaning behind what a person says. This is known as the contact's intent. When the intent is identified, the virtual agent sends an appropriate response to the contact.

Requests and responses are sent via Virtual Agent Hub and the script with each turn. This option allows for customization of the virtual agent's behavior from turn to turn. For voice virtual agents, this is the utterance-based method of connection. All text virtual agent providers use this method.

At the end of the conversation, the virtual agent sends a signal to the Studio script. It can signal that the conversation is complete, or that the contact needs to speak with a live agent. If the conversation is complete, the interaction ends. If a live agent is needed, the script makes the request. The contact is transferred to an agent when one is available.

Once the conversation is complete, post-interaction tasks can be performed, such as recording information in a CRM Third-party systems that manage such things as contacts, sales information, support details, and case histories..