Configuring the live chat dialog nodes in IBM Watson Assistant Skills

includes an enhanced live chat experience for administrators, users, and Live Chat support agents. During a live chat, BMC Helix Virtual Agent displays the topics that are configured in Live Chat. After users select a topic, BMC Helix Virtual Agent routes the conversation to an appropriate support queue in Live Chat. This autorouting ensures that the users’ questions are routed to the most appropriate support agent for that topic, and the turnaround time is faster.

Task 1: To configure the LiveAgentChat – Login node

Log in to your IBM Cloud account.
Navigate to the IBM Watson Assistant Skill that is configured with BMC Helix Virtual Agent, and take the backup of the skill.
Click Dialogs > select the node that is configured for live chat.
For example, LiveAgentChat node.
Rename the live chat node from LiveAgentChat to LiveAgentChat – Login.

In the JSON editor, you should see the following text:
Important: The messages in blue text are the default messages. You can modify the messages to suit your business requirements.
{
  "context": {
    "summary": "<?input.text?>"
  },
  "output": {
    "text": {
      "values": [
        ""
      ],
      "selection_policy": "sequential"
    },
    "action": {
      "inputMap": {
        "chatId": "$chatId",
        "inputText": "$Summary",
        "responseByStatus": {
          "LIVE_CHAT_CONNECTION_ERROR": "Sorry, I could not connect to a live agent. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_SUCCESS": "Please wait while I connect you to a Live Agent. From here on responses to you will be from a system generated message or from a Live Agent.",
          "LIVE_CHAT_TOPIC_SELECTION_KEY": "Please select the topic you need a support agent to address. If none of the listed topics accurately describe what you need, please state your need.",
          "LIVE_CHAT_MAXIMUM_CONNECTION_ERROR": "Sorry, there are currently no live agents available. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_AGENT_OFF_HOURS": "Sorry, but the Live Chat desk is currently closed. To help resolve your issue you can type start over and rephrase your question, or I can create a Service Desk Request. Which one would you like?"
        }
      },
      "outputMap": {
        "result": "${actionResult.output.text}",
        "sys_options": "${actionResult.output.optionsText}",
        "virtualChatTopics": "${actionResult.output.optionsText}"
      },
      "actionTypeName": "virtualChatLogin",
      "waitForActionExecution": true
    }
  }
}
Save and close the JSON editor.

Task 2: To create a LiveAgentChat - No Topics node

In the LiveAgentChat - No Topics node, in the JSON editor, replace the existing text with the following text:
Important: The messages in blue text are the default messages. You can modify the messages to suit your business requirements.
{
  "output": {
    "text": {
      "values": [
        "${actionResult.output}"
      ],
      "selection_policy": "sequential"
    },
    "action": {
      "inputMap": {
        "chatId": "$chatId",
        "inputText": "",
        "responseByStatus": {
          "LIVE_CHAT_CONNECTION_ERROR": "Sorry, I could not connect to a live agent. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_SUCCESS": "Please wait while I connect you to a Live Agent. From here on responses to you will be from a system generated message or from a Live Agent.",
          "LIVE_CHAT_MAXIMUM_CONNECTION_ERROR": "Sorry, there are currently no live agents available. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_AGENT_OFF_HOURS": "Sorry, but the Live Chat desk is currently closed. To help resolve your issue you can type start over and rephrase your question, or I can create a Service Desk Request. Which one would you like?"
        }
      },
      "outputMap": {
        "result": "${actionResult.output}"
      },
      "actionTypeName": "connectToLiveAgentWithResponses"
    }
  }
}
Save and close the JSON editor.

Task 3: To create a LiveAgentChat - Display Topics node

Navigate to the LiveAgentChat – Login node.
Create a child node and name it as “LiveAgentChat - Display Topics”.
Specify the following condition for If bot recognizes setting:
$result != "" and $virtualChatTopics .contains('label') == true
See the following screen capture:
Open the JSON editor for Then respond with setting.
Replace the existing text with the following text:
{
  "context": {
    "sys_options": "$virtualChatTopics"
  },
  "output": {
    "text": {
      "values": [
        "$result"
      ],
      "selection_policy": "sequential"
    }
  }
}
Save and close the JSON editor.

Task 4: To create a LiveAgentChat - Topic Selection node

Navigate to the LiveAgentChat - Display Topics node.
Create a child node and name it as “LiveAgentChat – Topic Selection”.
Important
You must create the LiveAgentChat - Topic Selection node as a child of LiveAgentChat - Display Topics node only.
See the following image:
Specify the following condition for If bot recognizes setting:
$virtualChatTopics .contains('label') == true
Open the JSON editor for Then respond with setting and replace the existing text with the following text:
Important:  The messages in blue text are the default messages. You can modify the messages to suit your business requirements.
{
  "context": {
    "summary": "<?input.text?>"
  },
  "output": {
    "text": {
      "values": [
        "${actionResult.output}"
      ],
      "selection_policy": "sequential"
    },
    "action": {
      "inputMap": {
        "chatId": "$chatId",
        "inputText": "<?input.text?>",
        "responseByStatus": {
          "LIVE_CHAT_CONNECTION_ERROR": "Sorry, I could not connect to a live agent. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_SUCCESS": "Please wait while I connect you to a Live Agent. From here on responses to you will be from a system generated message or from a Live Agent.",
          "LIVE_CHAT_MAXIMUM_CONNECTION_ERROR": "Sorry, there are currently no live agents available. To help resolve your issue you can type 'start over' and rephrase your question, or I can create a service desk request where someone will follow up with you. Which one would you like?",
          "LIVE_CHAT_CONNECTION_AGENT_OFF_HOURS": "Sorry, but the Live Chat desk is currently closed. To help resolve your issue you can type start over and rephrase your question, or I can create a Service Desk Request. Which one would you like?"
        }
      },
      "outputMap": {
        "result": "${actionResult.output}"
      },
      "actionTypeName": "connectToLiveAgentWithResponses"
    }
  }
}
Save and close the JSON editor.

Task 5: To create a LiveAgentChat - Error node

Navigate to the LiveAgentChat – Login node.
Create a child node and name it as LiveAgentChat - Error.
Specify the following condition for the If bot recognizes setting:true
Open the JSON editor for the Then respond with setting.
Replace the existing text with the following text:
{
  "output": {
    "text": {
      "values": [
        "$result"
      ],
      "selection_policy": "sequential"
    }
  }
}
Save and close the JSON editor.

Post configuration tasks

After you manually update the Live AgentChat - Login dialog nodes in the IBM Watson Skill, you can configure BMC Helix Chatbot for enabling live chat. Once configured, you can verify that the topics, that are configured in Live Chat, are displayed in the chatbot conversation.