Virtual Agent Hub

Virtual Agent Hub allows you to manage the connections between CXone and your voice 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:

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 virtual agent solutions and has all the desired features. Using the Virtual Agent Hub, he can:

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 chat channelsClosed 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 agentClosed A software application that handles customer interactions in place of a live human agent. providers are: 

Virtual Agent Provider Supports Voice * Supports Chat
Amazon Lex V1 Yes, utterance-based No
Amazon Lex V2 Yes, utterance-based No
CXone SmartAssist Powered by Amelia Yes, SIPClosed Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel No
Enlighten Autopilot Yes, SIP backchannel No
Google Dialogflow CX Yes, utterance-based or SIP backchannel No
Google Dialogflow ES Yes, utterance-based No
IBM Watson Assistant Yes, SIP backchannel No
Microsoft Azure Yes, utterance-based No
Nuance Mix Yes, utterance-based No
Omilia Yes, SIP backchannel No
Custom Virtual Agent Integrations Yes, utterance-based or SIP backchannel No

* You can learn more about the supported voice options in the Voice Connection Options section on this page.

Conversation Flow for Voice Channels

To start an interaction with a voice virtual agent, contactsClosed 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 IVRClosed 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 utterancesClosed What a contact says or types. are transcribedClosed 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-speechClosed 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.

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. Depending on how the integration is set up, requests and responses are handled in one of two ways. They can be: 

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 is ended. 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 CRMClosed Third-party systems that manage such things as contacts, sales information, support details, and case histories..

Voice Connection Options

There are two ways to set up a connection between CXone and the voice virtual agent provider. In most cases, CXone supports only one of the options for each provider. The options are: 

  • Utterance-based communication: Routing and utteranceClosed What a contact says or types. processing happens in CXoneVirtual Agent Hub. You're able to control and customize each turn in the conversation. This is the option supported for most virtual agent providers.
  • SIP backchannel connection: This option uses backchannel audio connections and a signaling connection. The connections are configured in Virtual Agent Hub, but no other Virtual Agent Hub processing or routing is used. The signaling connection allows the virtual agent to communicate with CXone when the conversation is complete or needs to be escalated to a live agent.

The voice connection option supported for each virtual agent provider is described in the table at the top of this page. You can learn more about using SIP backchannel connections on the SIP BackChannel Connections page.