Review and Improve Your Mpower Agent

This page provides information about reviewing conversation data in Agent Builder to improve the performance of your Mpower Agents A virtual agent created with CXone Mpower Agent Builder that can handle voice or chat interactions.. This is the fifth step in the Mpower Agent implementation process. It is also an ongoing maintenance job required to keep your Mpower Agent working optimally.

After you configure and begin to test the initial use cases for your Mpower Agent, Agent Builder will have data you can use to examine how effective the current configurations are. At first, the data come from test conversations with the Mpower Agent. Later on, after releasing the Mpower Agent to production, the data will include live conversations with contacts The person interacting with an agent, IVR, or bot in your contact center..

By reviewing this data, you can spot places where you can improve how your Mpower Agent performs. Its performance is indicated by how well it correctly predicts intents. If the Mpower Agent predicts the wrong intent, it's harder for contacts to achieve their goals.

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.

Review Conversation Data

You can review every conversation your Mpower Agent handles. This allows you to see first-hand how it responds, where it has difficulty, as well as the way contacts The person interacting with an agent, IVR, or bot in your contact center. interact with it and any issues they have. This information is valuable, as you can use it to improve the performance of your Mpower Agent by updating its intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish., rules Used to define an Mpower Agent's response to messages that don't change with context., and stories Used to train an Mpower Agent for interaction handling based on intent and context..

There following options in Agent Builder allow you to review conversation data:

Insights: Provides reporting and real-time, interactive analytics for your Mpower Agents:
NLU Inbox: Helps you manage your NLU This process expands on Natural Language Processing (NLP) to make decisions or take action based on what it understands. data to improve the quality of your Mpower Agent. It shows all new messages from contacts.
Query search: Use the search bar to narrow results in the NLU inbox or the Insights section.

Evaluate Intents

Evaluating and adjusting intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. can help you translate the contact's The person interacting with an agent, IVR, or bot in your contact center. challenges into solutions when you modify your Mpower Agent responses. While you can't cater to every user behavior, you can address common points of friction or frustration.

As you review conversations, evaluate intent data to see whether the intents are effective and efficient. Does the contact achieve their desired outcome easily? If not, determine if the intents are not specific enough, are too specific, or if the training data is inadequate:

Does the Mpower Agent reliably understand what the contact wants? If not, add more training examples to the intents where the Mpower Agent is unsure.
Are any of the intents actually similar enough that they're essentially the same? If so, consider combining them under a more general intent and using the examples to train your Mpower Agent to recognize the different scenarios.
Are contacts saying things that aren't covered by the existing intents? If so, consider adding more intents, or adding training data to your current intents.

Refine Your Mpower Agent Responses

Agent Builder has features that can help you to improve the performance of your Mpower Agent. Your first set of intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish., 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. might not have taken advantage of these features. As you work to improve how your Mpower Agent responds, the following features might be helpful:

Examine your responses to see if you could use different actions in Mpower Agent responses to make the response more slick, human-like, or user-friendly.
Consider whether any of the intents could be multi-intents. Multi-intents are useful when the contact combines two intents in one utterance What a contact says or types.. For example, when a contact says Thank you. Bye as a single message, they're combining a thank you intent and a goodbye intent.
Identify the unhappy paths Story that produces a wrong outcome for the intent. that correspond to the happy paths you already mapped out in your intents, if you haven't done so already. Plan how to handle them, then add stories or rules as needed, along with the necessary training examples.
Consider what entities or slots are required. Entities are pieces of information collected from a conversation. Slots are like variables and can hold the collected entities.
Determine if a form is needed to simplify the process of collecting information from the contact to fill slots. An Mpower Agent can follow a form to ask questions and gather information from the contact. You can also have the Mpower Agent display a form to the contact.
Configure additional options in your Mpower Agent responses, such as rich messaging, variations of Mpower Agent messages, Smart Typing, fallback, and safety nets.

Situations Where You Can Improve Your Mpower Agent

While reviewing, you can take actions to teach your Mpower Agent how to perform even better in future conversations. The following list describes situations that require improvement and what you can do:

Low intent classification confidence: If the intent classification is correct but your Mpower Agent has low confidence in its prediction, add more training data for the intent to make the Mpower Agent more confident. Training data includes intent examples and stories Used to train an Mpower Agent for interaction handling based on intent and context.. If the intent classification is not correct, change it.
Low Mpower Agent action prediction confidence: Review your training data and look for intents that are too similar. If you have intents that are too similar, combine them. Or add more training data to the existing intents to make your Mpower Agent more confident in what action it should take in this situation.
User frustration: This may include requests for transfer to a live agent (handover The transfer of a contact from a virtual agent to a live agent.), repeating what they already said previously, or insults. Add more training data about their issue, or adjust the NLU confidence threshold in fallback. This can tell your Mpower Agent to use handover sooner if it isn't confident how to help the user.
“Out_of_scope” intent or fallback behavior: This may include a user asking for something your Mpower Agent is not capable of, or your Mpower Agent using fallback too early. Check for and fix any misclassified intents to verify that your Mpower Agent didn't simply misunderstand the situation. Add a new story or rule Used to define an Mpower Agent's response to messages that don't change with context. to show your Mpower Agent what to do next time.

Fallback and Safety Nets

As you review and improve your Mpower Agent, you will start to identify places where contacts The person interacting with an agent, IVR, or bot in your contact center. are likely to get frustrated with your Mpower Agent. This is the time to add fallback and safety nets to it.

Fallback: This teaches your Mpower Agent what to do when it's not sure how to proceed. There are two kinds of fallback:
- NLU fallback:
- Action fallback:
Safety Net: A safety net allows you to configure what happens when there's another problem with the Mpower Agent or the systems it connects to. This could include things such as the Mpower Agent taking longer than normal to respond to the contact.

Additionally, this is a good time to make sure you have out-of-scope paths so your Mpower Agent can respond to contact messages that are outside its domain.