Use Forms

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.

Create a New Form

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.
In the right pane, click Forms and then click New Form.
Enter a name for your new form and press Enter.
Under Requested Slots, click Add Slot.
Select the Slot from the drop-down, then enter the Question the Mpower Agent should ask the customer to get the correct information. For example, if your Slot is Name, your Question could be What is your name?
View image
Repeat the previous two steps for any additional slots you want to add to the form.

Activate a Form

You need to include a form in a story Used to train an Mpower Agent for interaction handling based on intent and context. or rule Used to define an Mpower Agent's response to messages that don't change with context. to describe when the Mpower Agent should run the form. When the story or rule is triggered, the form will activate and the Mpower Agent will start to ask the questions.

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.
Add a new story or rule. In this example, the name could be Address Change.
Enter the message a customer may send. In this example, it could be I need to change my address.
The Mpower Agent attempts to assign an intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. If the intent is correct, click Confirm. Otherwise, select the correct intent from the list. If the intent you need does not exist, type an intent name into the search field and click Create intent. This creates a new intent based on this message. You can add more examples to the intent later.
In the Mpower Agent response, click the drop-down to select a form.
View image

Submit a Form

A form is automatically submitted once all required slots are filled. However, your Mpower Agent will continue to listen for the next user message rather than automatically acknowledge that the form was submitted. This can leave the customer wondering whether their submission was successful. For a better customer experience, you can use a rule Used to define an Mpower Agent's response to messages that don't change with context. or story Used to train an Mpower Agent for interaction handling based on intent and context. to define what the Mpower Agent should do after a form is submitted.

Any slots collected from the customer can be used as variables to show that the Mpower Agent has collected the data. To use a variable, enclose the name of the entity Keyword or phrase defined in your company profile in Interaction Analytics. Related to an entity type. Can include variants. in curly brackets.

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.
Add a new story or rule. In this example, the name could be Submit Address Change.
Click Add condition, then click Active Form. Click the drop-down to select a form. This ensures that the rule only runs if the specified form is active.
In the Mpower Agent response, click the drop-down to select a form.
Add a message from your Mpower Agent letting the customer know their submission was successful.
View image

Cancel a Form

A contact The person interacting with an agent, IVR, or bot in your contact center. may change their mind in the middle of filling out a form and decide not to complete it. This can turn into a delicate situation with a contact, so defining a way for your Mpower Agent to handle this gracefully is a good idea.

Akela's Mpower Agent was receiving some requests to stop the address change process. The Mpower Agent wasn't sure how to handle this, so it would handover to an agent, leaving customers frustrated. Akela decided to create a rule her Mpower Agent could follow to cancel the address change form after it had been activated.

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.
Click the Rules tab.
Click New rule.
Enter a name for the rule. In this example, the name could be Cancel Address Change.
Click Add condition, then click Active Form. Click the drop-down to select a form. This ensures that the rule only runs if the specified form is active.
Enter the message a customer may send. In this example, it could be Nevermind.
The Mpower Agent attempts to assign an intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. If the intent is correct, click Confirm. Otherwise, select the correct intent from the list. If the intent you need does not exist, type an intent name into the search field and click Create intent. This creates a new intent based on this message. You can add more examples to the intent later.
Add a message from your Mpower Agent letting the customer know their request was cancelled.
View image

Interruptions

Once an Mpower Agent starts asking form questions, it will keep doing so until all the slots in the form are filled and is not able to process other things. Contacts The person interacting with an agent, IVR, or bot in your contact center. don't always answer all of a form's questions from start to finish. They may ask questions, change their mind, or otherwise change the subject in the middle of the form. These are called interruptions. To handle situations like this, you can write rules Used to define an Mpower Agent's response to messages that don't change with context. or stories Used to train an Mpower Agent for interaction handling based on intent and context. that include common interruptions.

An interruption with a recognized intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. triggers one of the following behaviors:

If the recognized intent is in a rule Used to define an Mpower Agent's response to messages that don't change with context., the Mpower Agent responds to an interrupted message based on the rule design. The Mpower Agent then returns to the form loop.
If the recognized intent is in a story Used to train an Mpower Agent for interaction handling based on intent and context., the Mpower Agent response may vary based on the story design. Once the intent is fulfilled, the Mpower Agent returns to the form loop.
If the recognized intent has low confidence, the Mpower Agent responds with the NLU fallback phrase, then continues in the form loop.

A common use for forms is agent escalation. The Mpower Agent will gather information to pass on to the live agent to simplify the process once the agent is connected. Many times, a contact will ask why the Mpower Agent needs their information. This is considered an interruption. The Mpower Agent adjusts to the new intent long enough to answer the question, then returns to the form loop. This is shown in the following example image.