Add Mpower Agent Responses to Flows

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.. Flows A graphical representation of a conversation used to train an Mpower Agent. allow you to create a visual representation of the conversation between the contact The person interacting with an agent, IVR, or bot in your contact center. and your Mpower Agent, including how the Mpower Agent should respond to each intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. 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.

You can also configure Mpower Agent responses in stories Used to train an Mpower Agent for interaction handling based on intent and context. and rules Used to define an Mpower Agent's response to messages that don't change with context.. You do not need to create stories and rules in addition to flows. You can do one or the other.

The steps on this page describe how to add Mpower Agent responses to a flow. If you'd prefer to work with stories, rules, or fallback A plain text alternative sent when the destination doesn't support rich media. you can learn how to add Mpower Agent responses to those configurations.

Glossary

Concept	Definition	Example	What the Mpower Agent Does
Utterance	Anything a contact The person interacting with an agent, IVR, or bot in your contact center. says in an interaction The full conversation with an agent through a channel. For example, an interaction can be a voice call, email, chat, or social media conversation.. Sometimes called a message.	"I lost my password." "What is my balance?" "Are you a bot?"	The Mpower Agent uses Natural Language Understanding (NLU) to analyze each contact utterance to determine its meaning, or intent.
Intent	What the contact wants to communicate or accomplish. Every message the contact sends has an intent.	"I lost my password" has the intent of "reset password". "Hello" has the intent of "greeting".	The Mpower Agent analyzes a contact's message using NLU This process expands on Natural Language Processing (NLP) to make decisions or take action based on what it understands. to determine the intent. Once it knows that, it can respond with a message of its own. You configure the response you want your Mpower Agent to use for each intent.
Entity	A defined piece of information in a contact's message.	Person or product name, phone number, account number, location, and so on.	The Mpower Agent uses NLU to identify entities in a contact's message. Entities help the Mpower Agent understand what the contact's message means.
Slot	An entity extracted from a contact's message and saved for use in Mpower Agent responses. Similar to a variable.	Creating a slot for contact name lets the Mpower Agent use that name in responses during an interaction, making it more personal.	When configured to do so, the Mpower Agent extracts an entity from a contact message and saves it in a slot. You can have your Mpower Agent use this information later in the conversation.
Rule	Defines Mpower Agent responses to messages that don't change meaning with context.	Single-turn interactions with fixed responses: What are your hours? What is your address? Conversation building blocks: Greetings, good-byes, thank yous and transitions; simple yes/no questions; and acknowledgments. Mpower Agents come with default intents and rules for several of these, including greetings, handover The transfer of a contact from a virtual agent to a live agent. requests, and more. FAQs Insults and classic bot challenges	Rules are one of two ways you can configure how your Mpower Agent responds to an intent. Rules are useful for certain kinds of intents, but not all intents.
Story	Trains an Mpower Agent to handle an interaction based on message intent and conversational context.	In an interaction about a forgotten password, the Mpower Agent would respond to "How do I do that?" in one way. If the interaction were about creating a new account, the response would be quite different even though in both cases the contact is using the same words with the same intent—to get more information.	Stories are the second of two ways you can configure how your Mpower Agent responds to an intent. Stories teach the Mpower Agent how to use the context of the conversation to respond appropriately.
Mpower Agent Action	Anything an Mpower Agent says or does while handling an interaction.	In an interaction about a forgotten password, the Mpower Agent responds by sending the link to the password reset FAQ on the website. When a contact expresses frustration, such as "I don't understand! It's not working!!!" the Mpower Agent responds with "I'm sorry. Would you like me to transfer you to a human agent?" When the contact says yes, the Mpower Agent initiates the transfer.	Mpower Agent actions are the options you have when defining how you want your Mpower Agent to respond to each intent. They give you the flexibility to configure each response to achieve the outcome that meets the contact's needs.

Add an Mpower Agent Response

When adding an Mpower Agent response, you can use any of the available Mpower Agent actions What the bot can do on its turn in the conversation, such as send a message or fill a slot. that are supported for flows. Intent is an option in the list of Mpower Agent actions you can add to a flow. However, it is not an Mpower Agent action. Instead, it represents a contact message and introduces a new intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. to the flow A graphical representation of a conversation used to train an Mpower Agent..

You must create a flow before adding an Mpower Agent response to it. If you're working with 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. you can learn how to add Mpower Agent responses to those configurations.

In CXone Mpower, click the app selector and select Agent Builder.
Click the Mpower Agent you want to work with.
Click Dialogues in the left icon menu.
On the Flows tab, click the flow you want to work with.
On the flow canvas, locate the place where you want to add an Mpower Agent response.
Click the plus sign and select the Mpower Agent action you want.
Configure the action you selected:
- Message
- Rich Link
- Script
- Multimedia
- Cards
- Handover
- Tags
- Fill Slot
- Slot Condition
- Adaptive Cards
If you add a Message action, you can include buttons or quick replies. Configure them if you add any, and complete the new branch that each button or quick reply creates in the flow.
Continue adding Mpower Agent actions as needed to complete the Mpower Agent response. For example, in addition to a Message action, you might want to fill a slot and add a tag all in the same turn in the conversation.
To delete an Mpower Agent action from the flow, click the trash can .
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 a Message Action

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 action to a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. , you can learn how to add this option to those configurations.

When adding an Mpower Agent response to a flow, click Message in the Mpower Agent actions menu.
In the action that appears, enter the message text.
Add optional buttons or quick replies to the message. You can add more than one of each, but you cannot add both to one message. Each button or quick reply creates a new branch in the flow.
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.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 Mpower Agent actions What the bot can do on its turn in the conversation, such as send a message or fill a slot. menu allow you to create messages that have rich content. Rich content enhances the messages the Mpower Agent sends to the contact The person interacting with an agent, IVR, or bot in your contact center.. 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 flows A graphical representation of a conversation used to train an Mpower Agent. :

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.
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 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. you can learn how to add these options to those configurations.

Add an Adaptive Cards Action

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 an Adaptive Cards action to a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. you can learn how to add this option to those configurations.

When adding an Mpower Agent response to a flow, click Adaptive Cards in the Mpower Agent actions menu.
Select the Adaptive Card you want to use from the drop-down.
To view or modify the selected Adaptive Card, click preferences at the top right corner of the card.
Click rectangles with an arrow to override the default rich message fallback for this Mpower Agent action only.
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.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 a Fill Slot Action

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 a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. you can learn how to add this option to those configurations.

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.

When adding an response to a flow, Fill Slot in the Mpower Agentactions menu.
Select a slot from the drop-down of available slots. If the slot you want doesn't exist yet, you can create it from the Slots option in the right pane on the Dialogues > Stories page.
Enter a Value, or leave the field blank to allow the value to be reset. Slot variables are accepted.
Click the flow canvas to continue.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 a Slot Condition Action

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 a flow A graphical representation of a conversation used to train an Mpower Agent. only. If you're working with 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., you can learn how to add this option to those configurations.

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.

When adding an Mpower Agent response to a flow, click Slot Condition in the Mpower Agent actions menu.
Select a slot from the drop-down of available slots in your entities and intents. If the slot you want doesn't exist yet, you can create it from the Slots option in the right pane on the Dialogues > Stories page.
Enter a Value, or leave the field blank to allow the value to be reset. Slot variables are accepted.
Click the flow canvas to continue.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 a Handover Action

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 a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. you can learn how to add this option to those configurations.

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.

When adding an Mpower Agent response to a flow, click Handover in Mpower Agent actions menu.
For Into, select an agent queue from the drop-down of available queues.
Enter a note for the agent if you want to provide more context.
Click the flow canvas to continue.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 a Tag Action

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 a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. you can learn how to add this option to those configurations.

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.

When adding an Mpower Agent response to a flow, click Tags in the Mpower Agent actions menu.
Click Add Tag. If the tag you want doesn't exist yet, you can create it by clicking settings > Tags.
Click the name of a tag to add it. You can add multiple tags but must do so one at a time. Even if you add more than one tag, only one new branch opens in the flow.
Click the flow canvas to continue.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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 a Script Action

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 Scripts action to a flow A graphical representation of a conversation used to train an Mpower Agent.. If you're working with 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. you can learn how to add this option to those configurations.

When adding an Mpower Agent response to a flow, click Script in the Mpower Agent actions menu.
Click Select Script and select from the list of available scripts. If the script you want doesn't exist yet, you can create it on the Integrations > Scripts tab.
Click the checkmark to confirm the script you selected or click the trash can to start over.
Click preferences in the action bubble to open the Scripts page to view or modify the selected script.
To move this Mpower Agent action on the flow canvas, grab the stacked dots and drag the bubble to a new location.
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.