Teach Your Mpower Agent to Have Conversations

This page describes the essential tasks required to build an Mpower Agent A virtual agent created with CXone Mpower Agent Builder that can handle voice or chat interactions. in Agent Builder. This is the third step in the Mpower Agent implementation process.

Teaching Your Mpower Agent to Have Conversations

You don't need to script each possible variation of a conversation. Mpower Agents A virtual agent created with CXone Mpower Agent Builder that can handle voice or chat interactions. use conversational AI technologies, which allow them to understand contacts' The person interacting with an agent, IVR, or bot in your contact center. meaning and respond appropriately without being scripted. However, you do need to teach your Mpower Agent how to handle conversations with contacts. You do this by creating conversation templates using 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. in Agent Builder.

Rules and stories, also known as dialogues, teach the Mpower Agent how to respond to the contact utterance What a contact says or types. by utterance. Each dialogue focuses on a specific, small part of the conversation. They generally consist of a contact utterance, the corresponding intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish., and the Mpower Agent response.

You may need more than one dialogue for a given intent. There might be some situations where you want your Mpower Agent to respond differently to the same intent based on certain criteria. You can teach the Mpower Agent how to tell the difference by creating multiple dialogues, each their own unique response and the criteria that define when the Mpower Agent should give that response.

How Dialogues Teach the Mpower Agent

During an interaction with a contact The person interacting with an agent, IVR, or bot in your contact center., an Mpower Agent analyzes the contact's utterance What a contact says or types. and identifies the intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. If the intent only has one configured dialogue Mpower Agent stories, rules, and flows in Agent Builder., the Mpower Agent responds according to that dialogue's configured response. If there are several dialogues for the intent, the Mpower Agent analyzes the conversation to detect clues for which version of the dialogue it should use.

The following diagram shows the logic an Mpower Agent uses when responding to a contact: 

Mpower Agent Responses

Mpower Agent responses can be as simple or as complex as you want to make them. Mpower Agents can: 

• Reply with information or questions.
• Display images, GIFs, videos, or links to web pages. They can include buttons or lists that the contact can interact with.
• "Choose" which action to take using conditions. You can configure multiple possible responses based on what the contact says.
• Follow a form to collect information from the contact.
• Escalate the interaction to a live agent.

Mpower Agent responses are built in dialogues Mpower Agent stories, rules, and flows in Agent Builder. and consist of one or more of the available Mpower Agent actions. Mpower Agent actions perform a specific function. Some Mpower Agent actions send content to the contact The person interacting with an agent, IVR, or bot in your contact center. , such as a message or a list of options to choose from. Other Mpower Agent actions perform tasks that are invisible to the contact, such as calling an API or pulling data from or storing data in a third-party application.

Agent Builder has a set of default Mpower Agent actions that you can choose from, but you can also create custom Mpower Agent actions. Custom Mpower Agent actions can make API calls or be designed with custom JavaScript.

Skill Store

Mpower Agent skills allow you to group Mpower Agent configurations and training data according to what your Mpower Agent can do. You can use them to filter training data, which makes it easier to focus more specifically each task your Mpower Agent can accomplish.

Mpower Agent skills are also used to distribute pre-made abilities to Agent Builder users via the Agent Builder Skill Store. The Skill Store provides integrations with various CXone Mpower features and products.

For example, if you want to use your Expert knowledge base with your Mpower Agent, you can add the Autopilot Knowledge Mpower Agent skill to your Mpower Agent. This adds all the necessary rules, stories, intents, entities, slots, scripts, and so on to your bot.

You can design Mpower Agent skills that others might want to use and submit them for approval to be added to the Skill Store. CXone Mpower reviews them and will add them to the Skill Store if they're approved. This makes them available for other Agent Builder users to add to their Mpower Agents.

Train Your Mpower Agent

Training your Mpower Agent helps it learn from the configurations you've made. The better the quality of the training, the better your Mpower Agent can correctly predict intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. Training happens in the following ways:

• When you add training data to an Mpower Agent: Training data are the examples you add to intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish.. If you add lots of high-quality examples, your Mpower Agent can more effectively build associations between words, phrases, and intents.
• When you create stories and rules: 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. teach an Mpower Agent how to respond to an intent. If the intent has enough high-quality training data, the Mpower Agent learns to recognize different ways contacts The person interacting with an agent, IVR, or bot in your contact center. express the same intent.
• When you create stories to teach an Mpower Agent about intent variations: For general intents with variations that impact how the Mpower Agent responds, you use stories to teach the Mpower Agent to differentiate between the variations. This helps your Mpower Agent learn to navigate the nuances of contacts' requests and respond correctly.

You can test how well-trained your Mpower Agent is by chatting with it in Agent Builder. By chatting with your Mpower Agent, you can see where it has problems and make corrections immediately.

Part of the ongoing training process is working with your Mpower Agent to make it smarter. The smarter your Mpower Agent is, the more effective it is at predicting intents and choosing the correct response. You can make your Mpower Agent smarter by reviewing conversation data and making changes to your Mpower Agent in response to problems found in the conversation data. You can review and improve your Mpower Agent.

Training Data

Intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. examples train your Mpower Agent on the various ways a contact might express an intent. The more examples of an intent you have, the more variations of that intent your Mpower Agent will be able to correctly identify. Use real-world conversation data to test and train your Mpower Agent. Always opt for quality data over quantity for best results. This helps ensure that the Mpower Agent is well-prepared to handle conversations with real contacts.

You can review your intents to see which ones need more training examples. Each intent has a number next to it that indicates the number of examples it has. Intents with 14 or fewer examples need more, if possible.

Train and Stage Option

When you are ready to test changes you've made to your Mpower Agent, you can click Train and Stage. This adds the changes to the Mpower Agent model Version of a bot that has been trained and staged so you can test them. Additional training through conversations may be required to refine how your Mpower Agent understands the configuration.

If you are making improvements to an Mpower Agent that's been deployed to production, Train and Stage creates a new Mpower Agent model Version of a bot that has been trained and staged and deploys that model to stage. If you want your improvements to be reflected in production, you need to manually deploy this new model. This ensures no Mpower Agent model enters production without your explicit consent.

You can use the health monitor to track the progress of trainings initiated with Train and Stage.

Train Your Mpower Agent with Stories and Rules

Stories allow you to teach your Mpower Agent how to respond to messages Anything a contact says in a bot interaction, whether question or statement, written or spoken. in the context of 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.. You can create stories from scratch or convert actual conversations into stories. Rules teach your Mpower Agent to respond to messages whose meaning doesn't rely on context.

Sometimes you may need to create multiple stories for a single intent. This is useful when there you want your Mpower Agent to respond differently depending on small differences in the intent. For example, if an Mpower Agent can check account balances, you might want it to respond differently depending on the type of account the contact The person interacting with an agent, IVR, or bot in your contact center. wants to check.

Stories and rules may need periodic updates and revisions. For example, if, after reviewing conversation data you discover that one of your stories is causing the Mpower Agent to be confused and predict the wrong intent, you can address the problem by changing the story. In some cases, you might need to change the intent as well as the story.

Training Data Best Practices

When planning your approach to gathering training data and training your Mpower Agent, keep the following best practices in mind: 

• Always opt for quality over quantity. It's okay to start with a small data set and build it over time as you gather more high-quality examples.
• Use examples from real-world conversations. This ensures that the data you use is realistic. It comes from utterances What a contact says or types. real contacts have made.
• Don't use tools that auto-generate data and claim to train your Mpower Agent faster. They often produce examples that don't reflect what contacts really say. They also can result in an Mpower Agent that loses its ability to generalize. Over time, the Mpower Agent reaches a point where it only recognizes phrases it's seen before.
• Do not use the same training data for more than one intent. If you re-use training data, your Mpower Agent won't be able to reliably determine the intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. in live interactions with contacts.
• Remain flexible and willing to adjust intents and stories over time. As you review conversation data, you may discover that what you thought was two separate intents are really shades of a more general intent. Or you may find that an intent is too broad and you need to break it down into more specific intents.
• Add new training examples only if they will help.
  • Do not add new training examples that are very similar to existing examples. If the Mpower Agent correctly predicts the intent with a high confidence for one utterance, it doesn't help the Mpower Agent to add more examples that are very similar.
  • Do add more training examples of utterances the Mpower Agent has previously predicted incorrectly or with low confidence.

Create Responses to Train Your Mpower Agent

Configure Mpower Agent responses with the following process: 

1. Create an intent.
2. Create a rule or story for the intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. you created to define how your Mpower Agent responds to that intent. Which one you create depends on the intent. Refer to the plan you made earlier in the Mpower Agent implementation process. The high-level process of creating 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. is:

   1. Stories and rules begin with something the contact The person interacting with an agent, IVR, or bot in your contact center. might say related to the intent. For example, for an intent called check_balance, the contact might say "Can you tell me my account balance?"

   2. After you enter an example of what the contact might say, your Mpower Agent attempts to predict the intent of the example. It displays the closest match, along with how confident it is in its prediction. It displays its confidence as a percentage.
   3. Confirm the intent prediction or choose the correct intent, then confirm it. If the confidence level seems low, add more training examples to the intent. Remember that the confidence level needs to be above the threshold you've set for NLU fallback A plain text alternative sent when the destination doesn't support rich media..

   4. Now you can add the Mpower Agent response using any of the available Mpower Agent actions.

      View image

      

   5. Add another contact utterance, if the real-world conversation examples for this intent show that contacts tend to follow up the response (from an agent or an Mpower Agent) with the same type of question or statement. Not every story will have followup utterances.

   6. Continue the conversion in the story or rule, following the real-world examples you collected. Add as much back-and-forth interaction as you need to teach the Mpower Agent how conversations about the intent should go.

      However, stories and rules should not be complete conversations. When the next statement in the conversation would necessarily start a new intent, it's time to stop and create a new story. Alternatively, consider breaking stories into smaller substories. You can link them using checkpoints.

   7. Create multiple stories for the same intent if there are variations of how the conversation might go, based on the contact's unique situation and needs. This trains the Mpower Agent to tell the difference between variations of a single intent.

      • Don't include variations of the conversation flow in the same story. This could confuse the Mpower Agent.

      • If there are variations to the way a contact might phrase a message, or similar messages that all mean essentially the same thing, you can add them as examples of the intent.

      • Think in terms of happy Story that produces the correct outcome for the intent. and unhappy paths Story that produces a wrong outcome for the intent.. Each intent can have more than one happy path and more than one unhappy path.

3. If the intent, rule, or story requires them, create entities, slots, or forms.

   • Create entities Keyword or phrase defined in your company profile in Interaction Analytics. Related to an entity type. Can include variants. only for information you need the Mpower Agent to extract from the conversation.

   • Create slots Entity extracted from contact's message and saved for use in bot responses. Similar to a variable. for data you need to save or use during the conversation. Agent Builder automatically creates slots when you create an entity.
   • Consider using a form in a story or rule if you need to collect more than a couple pieces of information from the contact.

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.

5. Chat with your Mpower Agent to test it. Based on the results of your conversation with the bot, you might need to make adjustments to the story or rule you created. You might also need to add or change the training data for the intent you're working with. When testing the Mpower Agent, try using lots of variations of the intent you're testing. Repeat the training and testing steps as often as necessary until you're happy with the performance of your Mpower Agent.