Building Conversation Flow

The Conversation Flow section allows you to build a conversation between the user and the bot. The conversation items represent the steps Luma VA should perform to complete a task. You can add the conversation items in the sequence of desired execution. Using the conversation items you can ask users for information, integrate with a third-party application, show search results, update KPIs or conditionally branch to a skill to exit the conversation.

Open

To build the skill conversation flow, add the conversation items in the desired sequence of execution. Luma Virtual Agent provides a wide range of Conversation Item that can be used to perform various actions during a conversation. Following are the conversation items available on the Skill builder:

Prompt User (Attribute)

Prompt User (Attribute) is used to fetch and retain information during a conversation between the bot and the user. The information can be gathered from user input, an integration (discussed later), or passed from other skills. This allows for building dynamic conversations and gathering data to execute the user's request. For more information on attributes, refer Create Global Attributes.

To prompt the user with a question or store a value, follow the below steps to use an Attribute Conversation Item.

• Select Prompt User (Attribute) from the conversation drop-down list. The construct is added to the conversation Flow.

• Now select the attribute in Select Attribute dropdown. You can search for the attribute, and the list is filtered based on the filter added. You can select an existing global attribute defined in the Attributes tab or click on 'Create Attribute' to add a new global attribute and use it in your skill. For further details refer to the Create Global Attributes article.

• Mark the attribute if the attribute value is mandatory for the skill execution.

• Add the default value to be assigned to the attribute if the user skips providing a response or the attribute.

All the predefined attribute configurations such as prompt message, Options, validations are applied to the skill. In case you want to make any changes specific to your skill, you can override the attribute.

Open

Attribute Override

While building the skill, Luma VA allows you to override the selected attribute. This means you can modify a few attribute details and continue using the same instead of creating a new attribute. While overriding an Attribute, the changes made are local to the skill and do not impact the original attribute.  The following details of the attribute can be overridden at skill level:

• Prompt type: No Prompt, Static User Prompt

• User prompt format: Text, Quick Replies, Cards, Image

• Validations

To override an attribute, follow the below steps:

1. On the Prompt User (Attribute) construct, click on the Attribute Name to open the View/Override Attribute window.

2. Click on the Override button. 

3. Update the required fields.

4. Click on Done to save the changes.

To revert overridden changes of the attribute, please follow the below steps:

1. Click on the selected Attribute Name to open the View/Override Attribute window.

2. Click on Override button. 

3. Click on Reset to Default button. All the fields will be reset to the values of the original attribute.

4. Click on Done to save the changes.

Invoke Integration

‘Invoke Integration’ connects Luma VA to external systems to perform actions to fulfill the user's request. For example, if the user interacts with the bot asking to create a ticket in ServiceNow, then an integration action is performed with ServiceNow to execute the skill. For more information on integration, refer to Integrations.

When added to the conversation flow, integration calls an external application to execute an action or retrieve information. To use Integration in your skill, follow the below steps.

1. Select the App Name from the drop-down list. This is a Connected App or external system that you previously created in the Integrations section of the Bot Builder interface. For more information on create 

   Ensure that the Connected App (web service) and the related operations are created first to display the values in the drop-down list.

2. Select the app Instance from the drop-down list. The instance is the environment you want to fulfill this request. For example, you may have a test instance or a production instance.

3. Select the Operation from the drop-down list. The operation is the web service call or method for the Connected App you want to use. You can choose to override the operation details by clicking the hyperlink at the operation name and clicking the override button on the operation page.  By overriding, you can set values in operation for this specific skill only.

4. The system displays the corresponding Integration Type based on the web service operation configuration.

Add Conditions- Rule Set

Add Conditions or Rule sets are used to add Condition checks to your skill. Use Rules, you can conditionally, prompt message to user, set or clear attributes, set KPIs or branch to another skill. This is often useful when a user asks for a generic request and through the conversation flow, you want to direct them to a more specific request (skill). For example, a user asks Luma for a new computer. Through a prompt you identify that the user requires a new laptop, then you can direct them to a laptop order skill. Likewise, you can branch to multiple skills and associate attributes according to the requirement. 

Add a Rule Set to a Conversation Flow when the Skill needs to evaluate a user's response and continue the Skill or branch to a different Skill. For more information on specifying the rule details, refer Rule Set Overview.

Invoke Automation Workflow 

Invoke Automation Workflow is used to add a published Automation Workflow Service to the Skills. Automation Workflows allow Administrators or Skill developers to automate tasks on remote services, servers, applications, and hardware. Add an Automation Workflow to the Conversation Flow when the Skill needs to execute one of the automated workflow services.

For example, we can enable an AD account using Automation Workflows which will be triggered when a skill related to it is executed by the end-user. For more information, refer Automation in Luma

Set/Transform Attributes

Set/Transform Attributes are used to transform and store information received from a user or an integration call. This allows the skill developers to convert the value and then use it in integration to execute a task, in a Ruleset to branch to another Skill, or in an Information Message to provide the user with information. For example, extracting user details like first, last, and organization names from an email address received as user input.   Using the conversation item, two actions can be performed:

Set attribute

Set Attributes helps to create local attributes and set the existing attributes with the values received from Integration calls. Set Attributes are available in Conversation items, Rule Sets, and Operation Inbound mapping. The 'Set Attribute' option allows the skills developer/administrators to assign value to a Global, Local, or Custom User Attribute. To set Inbound mapping, follow the below steps: 

1. Select Set/Transform Attributes from the Conversation Item list.

2. In Add Attribute, select Set Attribute.

3. To Set an attribute, add the below details.

   1. Scope: Represents the scope of the attribute to be used to hold the values

      1. Use Global to assign value to a Global attribute to be used in the skill. Though the attributes are available for other skills to use, the value is retained during the current skill execution.

      2. Use Local to create and set the value to a local attribute. These attributes are only valid and available during skill execution. The local variable value is retained between the prompts and is used to pass data between multiple integrations, user messages, or rules. If used after a bot response, the value in the Local attribute is lost.

      3. Use User Custom to assign value to a User Custom Attribute. The values of the User custom Attribute is retained across skills unless overwritten.

   2. Attribute: This is the name of the attribute

   3. Data Type: Represents the data type of the attribute.

   4. Expression Type and Expression: These represent the type (Value or JSON) and the location path of the value assigned to the attribute.

      1. Use Expression Type → Value to assign a value to the attribute. This could be a static value or value available in an attribute, e.g., @{response.body}, @{response.code}.

      2. Use Expression Type → JSONPath to assign a value from a JSON response such as $.data.TicketIdentifier, $.data.items[*].Priority.

      3. Use Expression Type → Indirect JSONPath to assign a value from a JSON type attribute such as @{local.items}→$.[*].TicketIdentifier.

      4. Use Expression Type → Xpath to assign a value from an XPath expression such as //AddResponse/Description.

Transform

Transform functions are used to transform the values and assign the transformed/formatted/customized value to a Global, Local, or Custom User Attribute. Luma Virtual Agent provides a range of Transformation functions to allow skill developers to convert the data as required such as Split, Trim, Substring, Replace, Custom Date-Time, and more.

To use the Transformation function use Transform and add details. Refer to Transformation functions for more information on how to use Transform functions.

Suggest Skills

Suggest Skills is used to display the list of skills to be suggested to the end-user at the end of skill execution so that the user is guided to relevant skills post the completion of the current skill. Using Suggest Skills, you can configure an exclusive list of Skills that should be recommended to the end-user once the skill is executed or reuse the configuration already configured for a System Skill/suggest Skill category. This ensures that the user is guided to relevant skills post the execution of the current skill. The display format can be Cards or Quick replies.

To set Suggest Skills:

1. Select Suggest Skills in the Conversation Item.

2. To configure a custom list of skill:

   1. Select Custom.

   2. Type in the Message you wish the user to view.

   3. Under Select skill, type in the skill name you want to display as a suggested skill.

   4. Next, choose the desired Display Format, Cards or Quick Replies.

   5. A minimum of one skill is to be selected.

3. To reuse configuration defined for a category:

   1. Select Suggest Skill Configuration.

   2. The suggest skills configured for the select category ate displayed to the user. For more information refer to Customize System Skills behavior.

Show Message

Show Message sends a message to the user. A Message does not require a response from the user. It is used to display a piece of information. This is used to let the user know the bot is performing a task or to communicate an update to the user. Typically Show Message is used to inform the updates during the conversation or to inform the user of the result of the integration call. The message could be a simple Text message, Quick Replies (a collection of options), Card, or Image.

Add a Message

To add Message to your skill, follow the below steps:

1. Select Show Message from the Conversation Item list.

2. Now select the message type:

   1. To send the text message, select Text. Provide the Message in the text box and press Enter. You can specify multiple text messages. However, only one random text message is displayed to the user.

   2. To display options, select Quick Replies.

      1. Provide the Message in the text box

      2. Select the button type. The following formats are supported:

         1. Text

         2. URL

      3. Add Button name or label.

      4. The system automatically uses the button label as the Payload. Payload indicates the value or action Luma takes if the button is selected. You can modify the Payload to meet your needs, which is used to pass any values for integration with other systems. For example, if you want to view the tickets by their priority (high, medium, and low), mention those values as the button labels shown below. If the priority is denoted as 1 for high, 2 for medium, and 3 for low in the corresponding system, then you can specify 1, 2, and 3 against the corresponding buttons as the payload.

   3. If you select Card, provide the prompt Message in the text box. Enter the Card Title, Card Subtitle, and Button details. The system automatically uses the button label as the Payload. You can modify the Payload to meet your needs, which is used to pass any values for integration with other systems. For example, you may want to view the list of pending tickets and take action to approve, reject, or request additional information from the user. You can provide the button labels as Approve, Reject, and Need Info. Similarly, the corresponding payload information can be specified as shown below. 

   4. If you select Image, provide the prompt Message in the text box. Enter the Image URL and Tooltip details. For example, you may want to view the map of the place u wish to visit. You can provide the corresponding Image URL.

3. The Quick reply and Card buttons trigger actions such as opening a URL, opening an article, or triggering a new skill.

Configure Interactive List or Quick Replies in Whatsapp via Infobip

For the Whatsapp channel (via Infobip), the Quick Replies are presented as Interactive lists. In case of more than three options in quick replies, the buttons are automatically converted into an interactive list. You can add additional information to these interactive lists. 

Infobip List Title: Add an exclusive title for the interactive lists. The title is displayed on only ‘Whatsapp (via infobip)’ channel in addition to the prompt message. The additional title is ignored for the other channels, and the prompt message is displayed to the end user.

Quick Replies Description: Add descriptions for each option in the Interactive List item displayed to the users. On Whatsapp (via infobip) channel, the additional information for each selectable option is displayed to the end user.  For the other channels,  the description text is ignored.

Formatting Messages

You can also format the bot messages using Smart Lookups. Type '@' to enable smart lookups and select the Format Category from the dropdown.  This standardizes the text format on all configured channels such as MS Teams, Slack, Whatsapp, Business Hangouts, and Web widgets.  

To format your text:

1. Type '@' 

2. Select Format(format) from the list. You can add a line break or add Bold, Italic styles to the required text.

3. Select the required format.

   1. For Bold and Italic formats, start by selecting Begin Character for Bold/Italics tags.

   2. Add the End tags at the end of the text to be formatted.

Capture Satisfaction Survey

Capture Satisfaction Survey prompts a custom Satisfaction survey to the end-user. Satisfaction Surveys are used to collect Feedback from the end user. Using Capture Satisfaction Survey, you can define a customized survey that is triggered after the execution of the skill. The survey configured in the conversation flow is specific to the skill. Here, you can define specific Survey questions and response options. A skill with a customized survey does not follow the system-level Feedback survey counter, and the survey is triggered every time the skill is executed.

To add a customized survey, follow the below steps:

1. Select Capture Satisfaction Survey from Conversation item.

2. Add the survey question specific to the skill in the Survey Prompt.

3. In Survey Rating Options section, add the response options. Add option Labels and Synonyms. 

4. Add a Validation Message. The message is triggered whenever an invalid response is received for the survey.

5. Add Post Feedback Message. The message is displayed after the survey response is received.

For more information, refer to Customer Feedback and Satisfaction Survey.

Capture Feedback

Capture Feedback prompts the end-user to provide feedback on skill execution. Feedback is used to request detailed feedback from the end user. Add ‘Capture Feedback’ to the conversation flow to prompt the user to provide feedback. The administrator uses the feedback response to improve user interaction with the Bot. Here you can configure a custom feedback question. This Feedback is specific to the skill and triggered upon completion of skill execution. Using Feedback, you can request detailed feedback from the end-user or provide specific options to provide Text feedback. You can also use the Quick Replies to trigger other skills automatically based on the user's feedback.

To add Feedback, follow the below steps:

1. Select Capture Feedback from the Conversation item.

2. Select the type of feedback in Feedback Prompt

   1. For Text type:

      1. Add the feedback question specific to the skill in the Message field.

   2. For Quick Replies:

      1. Add the response questions 

      2. You may add a follow-up action or skill in Payload to automatically trigger an action based on the feedback response selected by the end user.

3. In the Survey Rating Options section, add the response options. Add option Labels and Synonyms. 

4. Add a Validation Message. The message is triggered whenever an invalid response is received for the survey.

Set KPI

Skills in Luma can be configured to resolve an end-user issue and deflect a support request. This can be achieved through an automated service or by using existing Knowledge. KPIs in Luma are indicators of the value skills add to the organization. While creating skills, skill developers can use the 'Set KPI' conversation item to calculate or update Luma KPIs during skill execution. Here you can choose the KPI Metrics and the parameter based on the skill. Based on the configuration, KPIs are calculated during the conversation.

To set the KPI in a skill, do the following:

1. Add Set KPI to the Conversation flow.

2. Select the KPI(s) to be updated and the effort (in minutes) saved. You may update the following KPIs:

   1. Deflected Support Requests: The KPI indicates that the skill can deflect a support request. Specify the number of minutes that the skill can save as the user request is directly resolved and a support request is avoided

   2. Resolved with Knowledge: The KPI is linked to ‘Deflected Support Requests’. Mark 'Resolved with Knowledge' if the ticket is deflected by a Knowledge Article

   3. Actionable Support Requests:  Use the KPI to indicate that the skill creates a well-structured, actionable ticket. Specify the number of support minutes that can be saved by creating an actionable support request through Skill. The default value is set to 5 minutes.

   4. .Automated Resolutions: The KPI indicates that the skill resolves user issues using an automated service. Specify the number of support minutes that can be saved by the execution of the automated service, skill, or job by executing the Skill.

   5. Ineffective Best Response: This is a Luma Knowledge KPI. The KPI indicates that the Knowledge Articles returned in the result set are incorrect or irrelevant to the user’s request.

   6. Knowledge Gap: This is a Luma Knowledge KPI. The KPI indicates that Knowledge articles are unavailable for the user’s request and the phrase should be marked as a Gap in Luma Knowledge.

Search Knowledge

Search Knowledge is used to search for Knowledge Articles in the associated Luma Knowledge Tenant. Add Search Knowledge to your skill to search for Knowledge Article anywhere during skill execution. You can search for a specific article or with a phrase and metadata.

Search Knowledge construct eliminates the need to configure integration with the Luma Knowledge tenant. Luma VA and Luma Knowledge tenants are automatically associated with each other. 'Search Knowledge looks for articles directly in the associated Luma Knowledge system. The Knowledge articles in results can be accessed using the Knowledge Context variables. For more information, refer to Use Variables in Skills.

Follow the below steps to add Search Knowledge to your skill:

1. Add Search Knowledge to the Conversation flow.

2. Add a short description for the search.

3. There are two search methods:

   1. Metadata - To search for Knowledge Articles using a phrase. You could also supply additional context for the search by providing metadata,

   2. Article ID - To search for a specific Knowledge article using a Knowledge Article ID.

4. Now, based on the selected search method, provide the search filters:

   1. For the ‘Metadata’ Method, you may provide the following:

      1. Phrases: Provide the search phrase to search for Knowledge. By default, the user’s initial request (available in context variable @{conv.skillPhrase}) is assigned to the field. You could set the field to a static value or another attribute with a text value.

      2. Domain: Domain is the first level of categorization applicable to the Knowledge Artifact. In Luma Knowledge, all Knowledge Articles are categorized under domains and usually refer to the department or functional division the article is related to. For example, HR, IT, Network etc.

      3. Topics: Information on products, services, projects, or sub-teams related to the article. For example, Microsoft, Asset Management, etc.

      4. Subjects: Any specific target of information available in the article. For example, Office, Password, Account etc.

      5. Action: Action is the purpose of the Knowledge artifact. It indicates what action can be performed using the article. For example, Reset, Change, Create, Explain, Work, etc.

      6. Motivation: Motivation words that determine the intention of the user query. For example, how, when, where, etc.

Search Catalog

Search Catalog is used to search for Service Catalogs in the associated Luma Knowledge Tenant. Add Search Catalog to your skill to search for Catalog during skill execution. You can search for a specific catalog or with a phrase and keywords. The search Catalog construct eliminates the need to configure integration with the Luma Knowledge tenant. Luma VA and Luma Knowledge tenants are automatically associated with each other. ‘Search Catalog’ looks for catalogs directly in the associated Luma Knowledge system. The Catalogs in results can be accessed using the Catalog Context variables. For more information, refer to Use Variables in Skills.

Follow the below steps to add Search Catalog to your skill:

1. Add Search Catalog to the Conversation flow.

2. Add a short description for the search.

3. There are two search methods:

   1. Search Phrase or Keyword - To search for Service Catalogs using a phrase. You could also supply additional context for the search by providing keywords,

   2. Catalog ID - To search for specific Catalogs using a Catalog ID.

4. Now, based on the selected search method, provide the search filters:

   1. For the ‘Search Phrase or Keyword’ Method, you may provide the following:

      1. Search Phrases: Provide the search phrase to search for Catalog. By default, the user’s initial request (available in context variable @{conv.skillPhrase}) is assigned to the field. You could set the field to a static value or another attribute with a text value.

      2. Keyword: Any special code or identifier associated with the catalog can help Luma VA search the Service Catalog.

Display Knowledge

Display Knowledge is used to display Knowledge articles to the end-user. Add the construct to the skill’s conversation flow whenever you want the Knowledge to be displayed. Display Knowledge automatically uses the Knowledge Context variables to display the Articles. It automatically generates guided navigation with the identified categories in case an ambiguity is identified in the results.

Using 'Display Knowledge' you can specify when should the Knowledge articles, found during the initial search by Luma or custom search using 'Search Knowledge', be displayed. You can also define the number of articles and messages displayed to the user when presenting the Knowledge Articles.

Follow the below steps to add ‘Display Knowledge’ to your Skill:

1. Add Display Knowledge to the Conversation flow.

2. Add a short description.

3. If you wish to restrict the number of articles to be displayed,

   1. Select 'Limit number of Artifacts'.

   2. Add the 'Maximum Artifacts to be displayed'.

4. Next, customize the messages to be displayed with the Topic Navigation and the list of Knowledge Articles.

   1. The messages and the definition of the card with Knowledge Article details are part of the Presentation Template. For more details refer to Presentation Templates.

   2. You could use the default configuration or click on Customise to edit the messages.

   3. The customized messages are local to the skill; any changes to the presentation template do not update the change.

   4. Click on Discard to cancel any changes made to the presentation messages.

Display Catalog

Display Catalog is used to display Service Catalogs to the end-user. Add the construct to the skill’s conversation flow whenever you want the Catalog to be displayed. Display Catalog automatically uses the Catalog Context variables to display the Service Catalogs. It automatically generates guided navigation with the identified categories in case an ambiguity is identified in the results.

Using 'Display Catalogs,' you can specify when the Catalogs, found during the initial search by Luma or custom search using 'Search Catalog', should be displayed. You can also define the number of catalogs and messages displayed to the user when presenting the Service Catalogs.

Follow the below steps to add ‘Display Catalog’ to your Skill:

1. Add Display Catalog to the Conversation flow.

2. Add a short description.

3. If you wish to restrict the number of catalogs to be displayed,

   1. Select 'Limit number of Catalogs'.

   2. Add the 'Maximum Catalogs to be displayed'.

4. Next, customize the messages to be displayed with the Category Navigation and the list of Catalogs.

   1. The messages and the definition of the card with catalogs details are part of the Presentation Template. For more details refer to Presentation Templates.

   2. You could use the default configuration or click on Customise to edit the messages.

   3. The customized messages are local to the skill; any changes to the presentation template do not update the change.

   4. Click on Discard to cancel any changes made to the presentation messages.

Display Skill

Display Skill is used to display the skills to the end-user. Add the construct to the skill’s conversation flow whenever you want the Skills to be displayed. Display Skill automatically uses the Skill related Context variables to display the Skills. Using 'Display Skills,' you can specify when the Skills found during the initial search by Luma should be displayed. You can also define the messages displayed to the user when presenting the Skills.

Follow the below steps to add ‘Display Skills’ to your Skill:

1. Add Display Skill to the Conversation flow.

2. Add a short description of the step.

3. Next, customize the messages to be displayed with the list of Skills.

   1. The messages and the definition of the card with catalogs details are part of the Presentation Template. For more details refer to Presentation Templates.

   2. You could use the default configuration or click on Customise to edit the messages.

   3. The customized messages are local to the skill; any changes to the presentation template do not update the change.

   4. Click on Discard to cancel any changes made to the presentation messages.

Conversation Flow Restrictions

When building a conversation, keep in mind the following:

• A Conversation Flow cannot end with an Attribute. A Skill cannot be saved when an Attribute is the last item in the flow.

• All Conversation Items must have the required information populated.

• The suggested skills configured in the last skill (branched skill) are presented to the user.

• Suggest skill could be added only as the last step of the skill.