A conversation between the end-user and the Virtual Agent starts when the bot understands the user request and completes when the request is fulfilled. In Luma Virtual Agent, any request to be fulfilled by the bot must be defined in a logical entity, called Skill. A Skill in Luma Virtual Agent is an enabled conversation between Bot and User which can answer a common query or interface with 3rd party systems to fulfill the user request. When Designing a conversation or skill, you define the user’s intention, information required to process the user request, and actions that resolve the user’s request.
Luma VA understands the user’s request with the help of inherent Natural Language Processing capabilities. Administrators use Serviceaide’s Luma Virtual Agent Bot Builder Application to design and create these conversations.
How to build a Skill in Luma Virtual Agent?
A skill in Luma Virtual agent contains phrases that indicate how the end-users may request for the skill, dialogs between the user and virtual agent to collect the information required to process the request and actions to be performed by the bot. These components together provide the back and forth conversation between the bot and the user to fulfill the end-user request.
Following are the basic building block of a Skill in Luma:
Invocation Type is the method using which end users can invoke or trigger the Skill.
Conversation Flow is used to build the Conversation flow between the user and your bot. Here we structure the conversation by adding the following conversation items,
Attributes are used to gather and hold information received from the end-user, which can be later used to action the user's request.
Integrations are the connectivity mechanisms to the external systems and associated web service operations. These enable the bot to fetch information or execute an action in the 3rd party application.
Information Message is the bot response displayed to the end-user during the conversation.
Conditions-Ruleset is used to evaluate a user's response to determine the next steps such as continue the Skill, branch to a different Skill, or terminate the skill.
Transformations are used to transform the data using the system-defined functions
Suggest skills are used to configure an exclusive list of Skills that should be recommended to the end-user once the skill is executed.
Permission to grant access to skill to individual users and groups so that correct people can execute the skill
Build and Publish is used to train the bot on conversations and Skills designed in Bot Builder. It ensures that Virtual Agent understands the user intent and processes the services as requested.
For more information on building blocks of Skill, refer to Create and Manage Skill.