Building a skill to log an Incident in ISM

Owned by sneha.tripathi
Last updated: May 25, 2021
3 min read

Luma Virtual Agent can integrate with external applications to retrieve data or perform actions in the target system. Using a web service, the Virtual Agent can integrate with an external application that can be used in Skills to perform user requests.

Let's look at an example to build a skill in Luma Virtual Agent that connects to an ITSM system such as Intelligent Service Management to create an incident for an issue.

The following are the key steps in configuring the skill:

  1. Define the Prompt/Attribute named 'Description' to accept details of the issue from the end-user:

    1. On Skill Builder--> Attribute tab, click on Create Attribute.

    2. Add attribute details such as Name and Data type.

    3. Set the prompt message to be displayed to the end-user, like “Enter issue details, “Enter Description. “

    4. Click Save.

  2. Define the Integration to ISM with the “Create Incident” operation.

    1. On the tenant menu, click on Integration.

    2. Create an Application with the integration type as REST.

    3. Add an instance to the ISM environment.

    4. Configure the ‘Create Incident’ Operation.

    5. Fetch the ticket number received as a response from the web service and save it in a local attribute TicketNumber.

  3. Build the skill

    1. On Skill Builder, click on the Create Skill.

    2. Add Skill details such as Name, Category, and Description.

    3. On the Invocation Type, select “User Phrase“ and add the Phrases that can be used to trigger the skill, such as “Log a ticket in ISM,” Create a ticket,” “Log incident,” etc.

    4. On Conversation Flow,

      1. Add Attribute “Description.”

      2. Add Web Service operation “Create Incident. “

      3. Add Information Message to be displayed to the end-user. Use the local attribute, (defined in Step 2) TicketNumber, to display the ticket number to the end-user in the information message. For example: “Incident @{local.TicketNumber} has been created in ISM. ”.

    5. Click Save to finish building the skill.

    6. The next step is to add permission to the skill. Click on Permission and the Users or Groups who should be able to execute the Skill.

  4. Run Build and Publish to make the skill available in Virtual Agent.

  5. Once the skill is Published, Go to the Test Widget to test the skill. Click on Debug Logs and execute the skill to view the runtime Skill execution logs.

Your skill is now ready to use. Go to Conversation History to view the list of conversations where the end-user requested the skill.

Below is the sample skill definition. Note that the integration details should be replaced with your organization-specific instance details.

Additional Resources:

Visit the below Wiki Documentation for more information on:

  1. Creating an Attribute on Create Global Attributes

  2. Configure a 3rd party Web service integration on REST Integrations Create Global Attributes

  3. Creating and Managing Skills is at Create Skills

  4. Using local attribute in skills on Use Variables in Skills

  5. Publishing Skill on Build and Publish

  6. Understanding Conversation logs on Conversation History.

CALL TO ACTION: Assignments

Now, refer to the above example and try creating the below skills:

  1. Build a Skill to create a Service Request in ISM. Create an attribute to accept the request details and configure an operation to Create a Service request in ISM. Use the Attribute and Operation in your skill and display the Service Request number received in a bot message.

  2. Build a Skill to view recent work logs for your ticket. Create an attribute to accept the ticket number, configure the operation, and pass the ticket number to the web service. Display the worklog received as the web service response. Configure a rule set to handle errors such as ticket not found, No worklog found, incorrect ticket number, etc.

  3. Build a Skill to connect to AccuWeather REST API to get current weather information of a city. Refer to the below link for details on the API:
    https://developer.accuweather.com/accuweather-forecast-api/apis