Call Dialogflow CX Bot action

Prerequisites

Integrations > Integrations > View permission assigned to any user role

Use the Call Dialogflow CX Bot action to run self-service applications within a flow before or instead of routing a customer to an agent.

Notes:

This action is available in call, chat, and message flows.
To enable the Call Dialogflow CX Bot action in Architect, you must first obtain the Google Cloud Dialogflow CX integration from the Genesys AppFoundry. Then, configure it in Genesys Cloud and create a Google Cloud Dialogflow CX bot in the Google console.
You must have at least one active Google Cloud Dialogflow CX integration enabled. For more information, see About the Google Cloud Dialogflow CX integration.
Changes you make to a Google Cloud Dialogflow CX bot in the Google console can take a few minutes to appear in Architect.
To enable barge-in functionality for a Google Cloud Dialogflow bot, see Enable barge-in for Google Cloud Dialogflow bots.
Administrators can use any text-to-speech provider that is available in Architect flows for use with their installed bot integrations. For more information, see About text-to-speech (TTS) integrations.
For further assistance on configuring Google Cloud Dialogflow CX, see About the Google Cloud Dialogflow CX integration and Google Cloud Dialogflow FAQs.

Name

Description

Name field

Type a distinctive name for the action. The label you enter here becomes the action’s name displayed in the task sequence.

Dialogflow CX Agent

The specific Dialogflow CX bot, also called agent, that you want to use. This version is the agent bot that you create in the Google console.

Environment

Select the Google Cloud Dialogflow CX environment that you want the flow to use at runtime.

Note: A draft environment is always available for a Dialogflow CX agent. If you did not create any environments for the selected Dialogflow CX agent, then the only environment available is Draft. Otherwise, a list of published environments, in addition to Draft, appears.

Environments provide a way for a flow to select which version of a Google Cloud Dialogflow CX agent that Architect calls at flow runtime. For more information about using Google Cloud Dialogflow CX environments in Architect, see Use Google Cloud Dialogflow environments in Architect. For more information, see Versions and environments in the Google Cloud Dialogflow CX documentation.

Initial Event Name

The name of the Dialogflow agent event to trigger when the interaction begins.

Agent Input Text

The string variable text to send to the Dialogflow CX Agent.

Note: Typically, you only use this field when you chain bot actions together.

Session Parameters

The information that you can pass into and retrieve from the bot. Enter the name of the variable and a value to assign. You can add multiple variables, and you can reorder them.

Inputs

Inputs set a Google Cloud Dialogflow CX Session Parameter of the specified name with the value specified at the beginning of the Dialogflow CX session.

Key Name. This value represents the names of the Dialogflow CX Session Parameters. For more information, see Session Parameters in the Google Cloud Dialogflow CX documentation.
Value to Assign. The value specified at the beginning of the Dialogflow CX session.

Outputs

Use outputs to read the value of the specified Google Cloud Dialogflow CX session parameter and set the Architect variable to assign to that value.

Note: Key names are case-sensitive.

Key Name
Variable to Assign

Live Agent Handoff Metadata

Maps values returned from Google Cloud Dialogflow CX back to Architect variables. These values are derived from a “Live agent handoff” fulfillment payload that you specify in the Google Cloud Dialogflow CX agent. The Live agent handoff fulfillment payload must be a JSON object. The Key Names are the names of the keys in the JSON object. For more information, see Live agent handoff in the Google Cloud Dialogflow CX documentation.

Follow-up Response Timeout

The Google Cloud Dialogflow CX bot may retrieve follow-up information from the user. Here, enter the amount of time the bot waits for the user’s reply.

The default response timeout is 12 hours, and the minimum allowable value is 0 seconds. The system considers a NOT_SET or negative duration as immediate.

Note: The follow-up response timeout applies to each customer response. Each time the customer responds and then receives another prompt from the bot, the timeout resets.

For example, if the bot asks, “What is your preferred date,” it waits up to 12 hours for a customer response. If the customer responds with a date within the 12-hour time frame and the bot replies, “Thank you, do you have an alternate choice,” then the flow restarts the timeout. The flow waits another 12 hours for the response about an alternate date.

Failure Outputs

Select the variables that you want to assign to the failure data values returned by the Dialogflow bot.

Data value	Variable
errorType	FeatureNotEnabledError: The Call Dialogflow CX Bot action is not available for the organization. InternalServerError: An unexpected error occurred during the Call Dialogflow CX Bot action. Typically, the received response is in an invalid format. Contact Genesys Cloud Customer Care. NoInputError: The Call Dialogflow CX Bot action timed out without any user input. NoMatchError: The user input that the Dialogflow CX bot received did not match any grammar elements. NoResourceError: The Dialogflow CX bot response does not include accessible resources. Note: This error can also be caused by billing issues, for example, an expired credit card. VersionMismatchError: Received success from the Dialogflow bot, but a mismatch occurred. For example, the returned intent did not match any intents configured with the action. Reload the flow and republish it.
errorMessage	A non-localized message. This string variable can be empty or NOT_SET.

Note: To expand or collapse the list of variables, click the arrow next to Failure Outputs.

Configure intent and failure paths

Name	Description
Success path	The Google Cloud Dialogflow CX bot’s Draft dictates these paths.
Failure output path	This path indicates that an error occurred while running the action or there was a problem processing the results. Note: If the network experiences connectivity issues, the action automatically takes this failure path. Drag the appropriate action below the Failure path and direct the route you want the interaction to take. For example, a transfer action to send the caller to an agent for assistance.