Events are triggered when specific actions occur during conversation with the Virtual Assistant  or when specific events are triggered on any active channels.

For example, when a user clicks the Get Started button to initiate a chat with your FB Messenger VA, it triggers the Facebook Welcome event. You can use this event to customize the welcome greeting such as personalizing it with the user’s first and last names, capturing additional information from users, and updating the back-end systems.

To generate the Get Started button, please use the following Curl code:

curl –location -g –request POST ‘https://graph.facebook.com/v2.6/me/messenger_profile?access_token={{page access token}}’
–header ‘Content-Type: application/json’
–header ‘Cookie: fr=0DjuarxRV9YWitxAN..BfXHzR…1.0.BfXHzR.’
–data-raw ‘{
“get_started”: {“payload”: “Facebook”}
}’

Note: You must provide access_token, the Page access token for the specific Facebook page in the curl to run the API.

To access Event Handlers, navigate to Build > Intelligence > Events.

Event Actions

Developers can define the VA should take when an event is triggered using one of the following options:

Run a Task

Select a Dialog task (Standard or Hidden) to be invoked when the event triggers. Once the event is triggered, the dialog starts executing. If it is interrupted because of other intent detections, the Hold and Resume settings come into play. During execution, if the selected Dialog is not published in the VA, the event is discarded.

In some cases, the Dialog may not be available to the user during a conversation for various reasons such as the task not yet being published, being suspended, or simply not having been assigned to the user. In such cases, the VA  shows an error message that the task is not currently available for execution. Developers can preempt such situations by testing the VA in Debug mode. The Debug Console shows full details about the error, including the reason why the task is not available.

Run a Script

Define a JavaScript to run when the event triggers. The script can make use of all applicable components such as session, context objects, variables, and functions. You can also fix the code using the Debug mode.

Show a Message

Define a simple or advanced message to the user when the event triggers. It supports all messaging formatting features available in the XO Platform, including multiple messages with channel override options.

Multilingual VA Behavior for Messages

• You can define language-specific messages;
• If a message is deleted from an Event for a specific language then it will be removed from all other languages of the VA;
• If a message is added for a language then the message would be added in all other languages using the same content;
• If a message is modified in a language, then the modifications will be applied for that language alone.

Learn more about message formatting and templates.

Event Types

Event Handlers are classified as Conversation Events, Intent Events, and Channel Events.

You can configure the following events to trigger responses:

Event Configuration

Conversation Events

Welcome / On Connect Event

Users can initiate VA conversations in varied ways, from a simple greeting to directly expressing an intent or asking an FAQ. To facilitate a scope for the developer to customize the response based on the user choice, the Welcome event comes with additional options when you choose Initiate Task or Show Message as the event configurations. For example, if the first user utterance maps to a task, should the VAexecute the event-based task or the user intent first?

Post ver9.0, you can use the isReturningUser parameter in the BotUserSession context object to identify returning users and send an appropriate welcome message (refer here for context object).

As a developer, you can define the VA’s priority when the user starts the conversation with a greeting, task, or FAQ from the options listed below:

End of Conversation

End of Conversation is triggered when the VA is not expected to send any message to the user or receive any message from the user.

A new flag indicating the reason for ending the task, added to the end of task event, will help decide the end of the conversation behavior. Client-side implementations of BotKits, RTM, and Webhook channels can use this reason for the task completion flag in the context to determine an appropriate course of action.

On triggering this event, the context will be updated with the following details:

• Reason for triggering event (see the table below)
• Name of the task that has just ended. If it’s an FAQ, then the task name will be set to ‘FAQ’

Task Execution Failure Event

• This event is available starting with the v6.40 release.
• By default, this event is always enabled with the Show Message option. This event cannot be disabled.
• This VA-level behavior can be overridden for specific tasks by defining task-specific failure events from the dialog task settings. Refer here for how.

Intent Events

Intent Not Available Event

When the VA cannot understand the user’s intent, this event determines the subsequent behavior. You can choose one of the following options:

• Show a standard message from the standard responses. Read here for details on standard responses.
• Automatically run a dialog task. You can use the dropdown to select the task you want to run.

Ambiguous Intents Identified Event

When the NLP engine identifies ambiguous intents from user utterances, by default, the virtual assistant displays a list of those intents during the conversation and requests the user to make a selection. This default behavior is ideal for most of the use cases. However, you can customize this behavior for specific use cases using the Ambiguous Intents Identified event. The event is triggered in the following scenarios:

• Two or more ‘definite’ intents are identified.
• Two or more ‘possible’ intents are identified and their scores lie within the defined proximity thresholds.
• Only low confidence intents are identified from the Knowledge Graph and no other intents are identified from other engines.

You can build custom business logic to analyze ambiguous intents, define appropriate conversation flow using a Dialog Task, and associate it with the Ambiguous Intents Identified event. By customizing the flow, you can avoid displaying ambiguous intents to the end user and redirect the conversation to the desired task. You can use the koreUtil.getAmbiguousIntents() function to retrieve the list of ambiguous intents and their confidence scores. For more information on the function, see koreUtil.getAmbiguousIntents().

Event Configuration

To configure the Ambiguous Intents Identified event follow these steps:

1. Go to Build → Intelligence → Events on the platform. By default, this event is disabled for all existing and new bots.
2. Click Configure to enable the event.
   
   If not enabled, the list of ambiguous intents is presented to the user during the conversation.
3. You can select the following options in the Configuration panel:
   • Present all the qualified intents to the end-user for disambiguation. This is the default selection in which the standard response related to the ambiguous intent(s) is presented. Learn more.
   • Automatically run a Dialog Task. This option lets you select a Dialog Task. Select this option if you want to build custom business logic to analyze the ambiguous intents, define appropriate conversation flow using a Dialog Task, and associate it with the Ambiguous Intents Identified event. Learn more.

   

4. Click the button Save & Enable to enable the event.

Interruption Management

When the event is enabled, the interruption behavior is handled as defined at the node level, dialog level, or bot level for ambiguous intents. The only exception is – when you select the Continue the current task and add new task to the follow-up task list option, the conversation continues as is with the current task, and any interrupting task will not be added to the follow-up list. For more information, see Interruptions Management.

Channel Events

Facebook & Telegram Welcome Events

This event triggers on receiving a Welcome Event from Facebook Messenger or Telegram. Once it is triggered, you can configure the Platform to perform the following actions:

• Initiate a Task: Select from the available Dialog Tasks to run once the event is triggered.
• Run a Script: You are shown a Javascript editor where you can add your script, which will run once the Facebook Welcome Event is triggered.
• Show a Message: This option lets you add VA responses to be sent to users once this event triggers.

Telephony Welcome Event

This event is triggered upon receiving a voice call to the Platform from any voice channel. This event will be triggered every time a user’s call reaches the Platform, and not just for the first time.

It provides the following two options:

• Initiate Task  – Select a task to be triggered from the drop-down list provided

• Voice Call Properties can be set as follows:
• Define at least one ‘Initial Prompts’
• Prompts for Timeout, and No Match can be defined
• Under Advanced Controls, settings for Timeout, No. of Retries, and Barge-in can be defined.
  See here for details.

IVR Impact

You may also use this event to define how and when the calls should be terminated for voice-based channels. The IVR implementation allows session/call closure only when the ‘end of conversation’ is completed. See more details here..

RCS Opt-In / Opt-Out Events

These events trigger when receiving opt-in or opt-out requests from users via the RCS channel. These events allow you to configure a response to be sent to the user as a follow-up for their action. 

Variable Namespaces

You can configure Variable Namespaces for Events by going to More Options > Manage Variable Namespaces at the top of the Events screen.

You can use the Manage Variable Namespaces to associate the Variable Namespaces to be used with the Event Handler. This option will be visible only when the Variable Namespace is enabled for the VA. For more information, see Managing Namespace.