Skip to end of metadata
Go to start of metadata

You are viewing an old version of this content. View the current version.

Compare with Current View Version History

« Previous Version 3 Next »

Consultants work on the functional configuration of Kbot. They set up its appearance, add and modify messages, and train the bot. Also they are responsible for the natural language processing (NLP), machine learning, etc.

Working with intents

Chatbot consultants manage intents. Intents are primary logical units of conversations. The main idea of a conversation processing is extracting an intent and delivering a corresponding response to a user. Such response might include information or an action.

Let’s take a look at some use cases.

Create and test intents

  • See the process of creating a new intent.

  • Learn how the bot detects intents.

  • Configure a simple response.

  • Learn how to create test sentences and link them to the intent.

  • Run tests and verify results.

Working with tickets

Kbot can connect to various trouble ticketing systems. Consultants can work with tickets with the help of another Kbot tool called Workflow.

The Workflow is a dialog model that allows users to run through a dialog using the predefined scheme.

Let’s take a look at some use cases. The following ticket-related tutorials are presented from the simplest to the most difficult.

Properties basics

When you work with tickets, it is necessary to collect various properties. The process of collecting properties is called Slot Filling. For example, to create a ticket the chatbot requires additional information, such as the ticket’s title, description, priority, etc.

Watch a short video displaying the properties that the chatbot requires to create a ticket.

Create an incident ticket

View the process of Slot Filling using several intent properties. As a result, the chatbot creates a ticket with the collected information.

  • Learn how to work with properties.

  • Learn about utility nodes — special blocks designed specifically to be reused in Workflows.

  • See the process of creating a ticket that uses properties information.

Create an incident ticket (sample 3)

Slot filling by collecting the pieces of information required for creating a ticket through a conversation workflow.

Difficulty: 2

Create an incident ticket (4)

Slot filling by collecting the pieces of information required for creating a ticket through a conversation workflow.

Difficulty: 3

Ticket categorization

Usage of a sub-worklow. The ticket Categorization workflow is called by the Incident or Request intents. It leverages Machine Learning for the automatic classification of the incident or request.

ServiceNow Cart Management

Learn how to:

  • Add or remove elements in a cart.

  • Create a request for this cart.

  • No labels