Add Mpower Agent Responses to Dialogues or Fallback

You can define how your Mpower Agent A virtual agent created with CXone Mpower Agent Builder that can handle voice or chat interactions. responds to contact utterances What a contact says or types.. Mpower Agent responses are configured in dialogues Mpower Agent stories, rules, and flows in Agent Builder.. During an interaction, when the Mpower Agent identifies a particular intent, it responds with the response that was configured for that intent. Responses consist of one or more Mpower Agent actions.

The steps on this page describe how to add Mpower Agent responses to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add Mpower Agent responses on the Add Mpower Agent Responses to Flows page.

Add an Mpower Agent Response

When you create a dialogue Mpower Agent stories, rules, and flows in Agent Builder. or fallback A plain text alternative sent when the destination doesn't support rich media., you can choose which actions the Mpower Agent will use when responding to contact utterances What a contact says or types.. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add an Mpower Agent response.

1. In CXone Mpower, click the app selector and select Agent Builder.

2. Click the Mpower Agent you want to work with.
3. Click Dialogues in the left icon menu.

4. On the Stories, Rules, or Fallback tab, click the dialogue you want to work with.

5. In the middle panel, hover your cursor over the + icon on the left. It changes to the robot icon and the Mpower Agent actions menu appears.

6. Click the Mpower Agent action you want to use. The action appears on the workspace in the dialogue you're working with.

   View image

   

7. Configure the action you selected:

   • Message

   • Multimedia, Cards, List Pickers, Rich Links, Buttons, Quick Replies

   • Fill Slot

   • Slot Conditions

   • Handover

   • Add Tags

   • Checkpoints

   • Forms

   • APIs integration actions

   • Script integration actions

8. Continue adding actions as needed to complete the Mpower Agent response.

9. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Message

The Message action allows you to define what your Mpower Agent says in response to the contact The person interacting with an agent, IVR, or bot in your contact center.. A message can include buttons or quick replies.

These steps describe how to add a message to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

1. When adding a Mpower Agent response, click Message in the Mpower Agent actions menu.

2. In the action that appears in the dialogue Mpower Agent stories, rules, and flows in Agent Builder., enter the message you want your Mpower Agent to send to the contact in the Type an Mpower Agent response field. In addition to adding plain text, you can:

   • Type a colon : to bring up an emoji picker.
   • Type a curly bracket { to bring up a list of existing slot variables. Select from the list or type the variable yourself. Enclose the name of the slot in curly brackets ( { } ).
   • Click Button or Quick Reply to add one to the message. Configure the button or quick reply. Details of the configuration appear next to it on the dialogue page. You can add more buttons or quick replies, but you cannot mix the types of rich content in one message.
3. Use the other options available for this action as needed: 

   • Click the clock to modify the amount of time the typing indicator displays before this action is sent as a message. If smart typing is enabled for this Mpower Agent, you can click Auto to override the default.

   • Click the crossed arrows to open a box where you can add variations to the existing message. The Mpower Agent will randomly select which variation to use in a conversation.

   • Click rectangles with an arrow to override the default rich message fallback for this Mpower Agent action only.

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

4. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Multimedia, Cards, List Picker, Rich Link, Buttons, Quick Replies

Some of the options on the General tab of the Mpower Agent actions menu allow you to create messages that have rich content. Rich content enhances the messages the Mpower Agent sends to the contact. They make it a more satisfying, versatile experience compared to plain text. You can learn more about rich messaging in Agent Builder, or you can learn how to add the following rich content to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. on the Add Rich Message Content help page:

• Multimedia: The Multimedia action lets you have your Mpower Agent send images, GIFs, videos, and so on to the contact.
• Cards: Cards combine images, structured text, and buttons into one message.
• List Picker: A list picker is a list of options the contact can choose from.
• Rich Link: Rich links are links that include a clickable image.
• Buttons: Buttons are an add-on to the Message action and can trigger an intent or open a URL.
• Quick Replies: Quick replies are a list of possible replies the contact can choose from. They're often used to help clarify or narrow down the intent.

If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add these options.

Adaptive Cards

Adaptive Cards are a platform-independent method of creating a variety of rich message content. They're currently only supported on digital Any channel, contact, or skill associated with Digital Experience. chat and Microsoft Teams channels Various voice and digital communication mediums that facilitate customer interactions in a contact center.. If a response that includes an Adaptive Card might be sent via another channel Various voice and digital communication mediums that facilitate customer interactions in a contact center., add rich message fallback A plain text alternative sent when the destination doesn't support rich media. to the response.

These steps describe how to add Adaptive Cards to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

1. When adding an Mpower Agent response, click Adaptive Cards in the Mpower Agent actions menu.
2. In the action that appears in the dialogue Mpower Agent stories, rules, and flows in Agent Builder., select an Adaptive Card from the drop-down list.
3. To modify the card or to view its properties, hover your cursor over the selected card and click Edit. The Adaptive Card designer opens in the pane on the right side of the page.

4. Click rectangles with an arrow to override the default rich message fallback for this Mpower Agent action only.

5. Use the other options available for this action as needed: 

   • Click the clock to modify the amount of time the typing indicator displays before this action is sent as a message. If smart typing is enabled for this Mpower Agent, you can click Auto to override the default.

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

6. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Fill Slot

The Fill Slot action allows you to choose a slot Entity extracted from contact's message and saved for use in bot responses. Similar to a variable. and specify a value to fill it with. You can use this action to fill a slot during the Mpower Agent's turn in the conversation.

These steps describe how to add a Fill Slot action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding an Mpower Agent response, click Fill Slot in the Mpower Agent actions menu.
2. In the action that appears in the dialogue Mpower Agent stories, rules, and flows in Agent Builder., select a Slot from the drop-down list. You can click Create Slot if the slot you need doesn't exist yet. If you create a slot, open the Slots panel on the right to configure it.
3. Enter the Value you want to fill the selected slot with.  You can: 
   • Enter a new value to fill the slot with.
   • Leave the field empty to reset the value of the slot.
   • Use the name of a slot as a variable by enclosing the slot name in curly brackets ( { } ).

4. Use the other options available for this action as needed: 

   • Click the clock to modify the amount of time the typing indicator displays before this action is sent as a message. If smart typing is enabled for this Mpower Agent, you can click Auto to override the default.

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

5. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Slot Condition

You can use the Slot Condition action to train your Mpower Agent to use different responses based on the value the slot holds. When you include this Mpower Agent action in an Mpower Agent response, the value of the specified slot becomes a condition that determines which path the Mpower Agent takes.

These steps describe how to add a Slot Condition action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding an Mpower Agent response, click Slot Condition in the Mpower Agent actions menu.

2. In the action that appears in the dialogue Mpower Agent stories, rules, and flows in Agent Builder., select a Slot from the drop-down list.
3. Enter the Value that must be matched to trigger the next action. You can use the name of a slot as a variable by enclosing the slot name in curly brackets ( { } ). If you want to reset the value of the slot, leave this field empty.

4. Use the other options available for this action as needed: 

   • Click the clock to modify the amount of time the typing indicator displays before this action is sent as a message. If smart typing is enabled for this Mpower Agent, you can click Auto to override the default.

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

5. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Handover

The Handover action allows you to have the preceding contact message trigger the handover The transfer of a contact from a virtual agent to a live agent. rule. This is an important Mpower Agent action to use in fallback and out-of-scope paths, but you can use it any time you want your Mpower Agent to hand a conversation off to a live agent. You can learn more about handover on the Mpower Agent Actions help page.

These steps describe how to add a Handover action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding an Mpower Agent response, click Handover in the Mpower Agent actions menu.
2. In the action that appears in the dialogue Mpower Agent stories, rules, and flows in Agent Builder., select a digital Any channel, contact, or skill associated with Digital Experience. routing queue from the Into drop-down list.
3. Enter a Note for Agent if you want to pass any information on to the live agent who handles the interaction. You can include slot variables in this field by enclosing the name of the slot in curly brackets ( { } ).
4. Use the other options available for this action as needed:

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

5. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Add Tag

The Tag action lets you add Agent Builder tags to an interaction. You can use tags when reviewing Mpower Agent data to identify patterns in conversations.

These steps describe how to add a Tag action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding a Mpower Agent response, click Add Tag in the Mpower Agent actions menu.
2. Click Add Tag in the Mpower Agent response workspace.
3. Select one or more tags from the drop-down list. You can search for tags by name.
4. To create a tag:
   1. Enter a tag name the search bar.
   2. Click the Create tag option that appears.
   3. Select the new tag to add it to the Mpower Agent response.
5. Click Add Tag to add more tags.
6. Use the other options available for this action as needed: 

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

7. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Checkpoint

A checkpoints links stories within the same story. This action is not available in rules or flows.

These steps describe how to add a Checkpoint action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. This option is not available for flows A graphical representation of a conversation used to train an Mpower Agent..

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding an Mpower Agent response, click Checkpoint in the Mpower Agent actions menu.
2. Click Story continues to in the Mpower Agent response workspace.
3. Select the story you want to link to. You can enter a keyword to search for a story.
4. Use the other options available for this action as needed: 

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

5. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Forms

Forms are a convenient way your Mpower Agent can gather information from the contact. They guide form-based conversations, where the Mpower Agent asks the contact questions, then completes the form with the responses. Form responses are stored in slots Entity extracted from contact's message and saved for use in bot responses. Similar to a variable..

These steps describe how to add a Forms action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. This option is not available for flows A graphical representation of a conversation used to train an Mpower Agent..

You must create a form before you can complete this task.

1. When adding an Mpower Agent response, click the Forms tab in the Mpower Agent actions menu.
2. Select Activate or Submit. You must add actions for both of these options to the Mpower Agent response.
3. Select the form you want to activate or submit.
4. Add another Forms action to the Mpower Agent response and click the Cancel option. This gives the contact the ability to cancel out of the form.

5. Use the other options available for this action as needed: 

   • Click the clock to modify the amount of time the typing indicator displays before this action is sent as a message. If smart typing is enabled for this Mpower Agent, you can click Auto to override the default.

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

6. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

API Actions

API actions are a customizable Mpower Agent action that allows you to include API integrations in the Mpower Agent configurations. They're an advanced option you can use to connect your Mpower Agent to other applications or platforms using API calls.

This option is only supported in stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. . It's not currently supported in flows A graphical representation of a conversation used to train an Mpower Agent..

This action instructs the Mpower Agent on what it needs to do. The contact does not see a message in the chat window when you include this action in a Mpower Agent response.

1. When adding an Mpower Agent response, click the APIs tab in the Mpower Agentactions menu.
2. Click the API action you want to add to the Mpower Agent response.
3. In the Save response into drop-down, select the slot where you want the response returned via the API call to be saved.
4. To view the configuration page for this API integration, click the configuration icon in the Mpower Agent response. When you are ready to return to the Mpower Agent response, click Dialogues in the left icon menu and navigate to the story, rule, or fallback you were working with.

5. Use the other options available for this action as needed: 

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

6. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.

Script Actions

The Scripts action allows you to choose a custom Mpower Agent action that you created as a script integration in Agent Builder. Depending on what the custom actions are designed to do, a message may or may not be sent to the contact.

These steps describe how to add a custom Mpower Agent action to stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., or fallback A plain text alternative sent when the destination doesn't support rich media. only. If you're working with a flow A graphical representation of a conversation used to train an Mpower Agent., you can learn how to add this option.

1. When adding a Mpower Agent response, click the Scripts tab in the Mpower Agent actions menu.
2. Click the custom Mpower Agent action you want to use in the Mpower Agent response.
3. To view the script of the custom Mpower Agent action you added, click the configuration icon in the Mpower Agent response. When you are ready to return to the Mpower Agent response, click Dialogues in the left icon menu and navigate to the story, rule, or fallback you were working with.
4. Specify a value for any editable variables the custom Mpower Agent action you added has:
   • For text type variables, enter a value in the field. This value overrides the default value, if the variable has one.
   • For select type variables, choose a value from the drop-down list. The values in the list are the ones assigned to the variable when it was created.

5. Use the other options available for this action as needed: 

   • Click and hold the six vertical dots to drag the action to a new place in the dialogue.

   • Click the trash can to remove the action from the dialogue.

6. When you're finished making changes, click Train and Stage to update your Mpower Agent model Version of a bot that has been trained and staged to test this change.