Google Dialogflow CX

Google Dialogflow CXis a third-party virtual agent bot platform. CXone supports using Google Dialogflow CXwith voice and CXone chat channels. CXone supports utterance-based features with Google Dialogflow CX. Features that require audio streaming are not supported.

Virtual agent bots interpret what your contacts say or type and respond appropriately. They do this using technologies such as:

Virtual agents are flexible and can provide a range of functions to suit the needs of your organization. For example, you can design your virtual agent to handle a few simple tasks or to serve as a complex interactive digital agent.

Dialogflow ES and CX are public offerings and you can purchase them directly through NICE CXone. However, the public version does not have full telephony features or native connections between Dialogflow and Google Contact Center AI Agent Assist. These features are available when purchasing through NICE CXone partners.

Comparison of Google Dialogflow CX and ES

CXone supports Google Dialogflow ES and CX. The two versions are similar, but have some key differences.

Dialogflow ES is suitable for small, simple bots. It simulates nonlinear conversation paths using a flat structure of intents and context as a guide. This approach doesn't support large or complex bots. You can pass contexts using the customPayload property of the Virtual Agent Hub Studio action used in your scripts. These bots use context data to determine the contact's intents.

Dialogflow CX supports complex, nonlinear conversational flow suitable for large, complex bots. It allows intentsClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish to be reused and doesn't require context information. You can pass customPayload data, but you don't need to include context information.

Conversation Flow for Voice and Chat Bots

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 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 into 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.

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 Closed A software application that handles customer interactions in place of a live human agent. Studio actionClosed 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 channelsClosed A way for contacts and agents to interact, such as voice, email, chat, social media, and so on..

Prerequisites

To use Google Dialogflow CX virtual agent botsClosed A software application that handles customer interactions in place of a live human agent. with CXone, you need:

Components of an Integration

The integration of Google Dialogflow CX into CXone involves the following components: 

Custom Scripting Guidelines

Before integrating a virtual agentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish, you need to know: 

  • Which script you want to add a virtual agent to.
  • The virtual agent Studio actionsClosed Performs a process within a Studio script, such as collecting customer data, playing a message or music, or routing a contact to an agent. that connect the bot to CXone. There are separate actions for voicebots and chatbots.

  • Where the Studio actions must be placed in your script flow.
  • The configuration requirements specific to the virtual agent you're using.
  • How to complete the script after adding the virtual agent action. You may need to: 
    • Add initialization snippets as needed to the script using Snippet actions.  You can do this to customize your bot.
    • Re-configure the action connectors to ensure proper contact flow and correct any potential errors.
    • Use the OnReturnControlToScript branch to handle hanging up or ending the interaction. If you use the Default branch to handle hanging up or ending an interaction, your script may not work as intended.
    • Complete any additional scripting and test the script.

Ensure that all parameters in the virtual agent actions you add to your script are configured to pass the correct data. The online help pages for the actions cover how to configure each parameter.

Additionally, ensure that you completely configure your virtual agent on the provider side. Verify that it's configured with all possible default messages. For example, error messages or messages indicating an intent has been fulfilled.

If you need assistance with scripting in Studio, contact your CXone Account Representative, see the Scripting Reference Material sections of the online help, or visit the NICE CXone Community site.

Supported Actions for Voicebots

To integrate a Google Dialogflow CX voicebot into a script, you can use the Voicebot Exchange or Voicebot Conversation actions. Voicebot Exchange is the preferred action for use with Google Dialogflow CX.

Voicebot Exchange Action

This action is for complex bots or for when you need to customize the bot's behavior from turn to turn.

Voicebot Exchange monitors the conversation between the contact and the bot turn by turn. It sends each utteranceClosed What a contact says or types. to the bot. The bot analyzes the utterance for intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish and context and determines the response to give. The action returns the bot's response to the contact. When the conversation is complete, the action continues the script.

Voicebot Exchange is the preferred action for use with voice bots. If you want to configure barge in or no input, additional scripting is required. If you're using a SIPClosed Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel connection, you must use the Voicebot Conversation action.

Voicebot Conversation Action

This action is only for use with very simple bots or when you are using a SIPClosed Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel connection. Voicebot Conversation does not allow the Studio script to customize the bot's behavior from turn to turn.

Voicebot Conversation interacts directly with the bot and passively monitors the conversation in real time. The bot analyzes the conversation for intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish and context from a constant audio stream. It then returns appropriate responses to the contact. When the bot indicates the conversation is over, the action continues the Studio script. The action passes along any relevant information for screenpops, agent routing, and so on.

This action is not recommended for use with unless you're using it with a SIP backchannel connection.

Supported Actions for Chatbots

When integrating a Google Dialogflow CX chatbot into a script, you can use the Textbot Exchange or Textbot Conversation actions.

Textbot Exchange is the preferred action for use with Dialogflow CX chatbots. Textbot Conversation is not recommended for use with Dialogflow CX.

Textbot Exchange Action

This action is for complex bots or for when you need to customize the bot's behavior from turn to turn.

TextBot Exchange monitors the conversation between the contact and the botClosed A software application that handles customer interactions in place of a live human agent. turn by turn. It sends each utteranceClosed What a contact says or types. to the bot. The bot analyzes the utterance for intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish and context and determines which response to give. TextBot Exchange returns the bot's response to the contact. When the conversation is complete, the action continues the script.

Textbot Exchange is the preferred action for use with Google Dialogflow CX chatbots.

Textbot Conversation Action

This action is only for use with very simple bots. It does not allow for customization of the bot's behavior from turn to turn.

Textbot Conversation interacts directly with the bot and passively monitors the conversation in real time. The bot analyzes the conversation for intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish and context. It returns appropriate responses to the contact. When bot indicates that the conversation is over, the action continues the Studio script. The action passes along relevant information for screenpops, agent routing, and so on.

Textbot Conversation is not recommended for use with Google Dialogflow CX chatbots.