Dialogflow - CX

Configuring Dialogflow CX

Configuring Dialogflow CX

The Talkative Configuration for your chatbot is very similar to configuring Dialogflow for any other service.

Custom events that need configuring

The interaction will start off by sending an interactionStart event. This will be the entry point of your chatbot.

For transferring

If you want to use transfers, you need to handle the failing of transfers as an event.

If your transfer fails due to businessHours, queueCap, or noUsers, you should set up an exception-based intent. A common use case is to provide an out-of-hours response if the chatbot transfers when business hours are closed. To create such an intent, you will need to create an intent with the following events:

interactionTransferFailed_businessHours

interactionTransferFailed_queueCap 

interactionTransferFailed_noUsers

Responding to basic user messages

Recognising the message.

The user messages are sent verbatim to Dialogflow and they can be recognised via the Training Phases.

Responding to the message

To respond to the message, simply fill in the Default Responses. One of those will be randomly selected as a response.

Sending multiple messages

To send multiple consecutive messages, simply create a second text response.

Message suggestions

To fill in message suggestions, send a custom payload as a response. The payload should look like:

{
  "talkative-engage": {
    "action": "suggestions",
    "suggestions": [
      "suggestion 1",
      "suggestion 2"
    ]
  }
}

Custom actions

Transferring

To transfer, you will need to create a custom Dialogflow Live Agent Handoff with the following content

{ 
    "talkative-engage": {    
         "to": "<queue_uuid>",    
         "action": "transfer"  
    } 
}

You will need the UUID to match one of your queues.

Emails

To allow the user to leave a message (that delivers as an email), you will need to send a custom response that contains: 

{ 
    "talkative-engage": {    
        "action": "email"  
     }
}

An email form will show to the customer in the widget. The data collection form will be the one set within the wait messages for that widget. 

Images

To make the chatbot send a message that contains an image, you will need to send a custom response that contains:

{
  "talkative-engage": {
    "action": "attach",
    "url": "https://i.imgur.com/AYlbbmX.gif"
  }
}

Ending

To end an interaction, you will need to send a custom response that contains:

{ 
    "talkative-engage": {    
        "action": "end"  
     }
}

Entities

Talkative automatically saves entities from Dialogflow into Interaction Data, allowing you to save key data points to your interaction record in Talkative. Both custom entities and standard system entities will be saved to Interaction Data. This happens automatically, no set up is needed.

For example, you might collect a customer's account number as part of a chatbot conversation, which can then be used to surface a CRM record when the chatbot hands off to a human agent. For more on Entities, please see Google documentation: 

https://cloud.google.com/dialogflow/cx/docs/concept/entity