Docs

Answer from Documents (Beta)

The Answer from Documents feature helps answer end-user queries from unstructured PDF documents without the need to extract individual FAQs and train them. This feature leverages a Large Language Model (LLM) and Generative AI models from OpenAI or Azure OpenAI integration to generate answers by processing uploaded documents and user…

Knowledge AI

The XO Platform’s Knowledge AI lets you use FAQs and unstructured documents to improve intent identification for user queries. This feature includes two modules – Knowledge Graph (Ontology-based and Few-Shot) and Answer from Documents. Knowledge Graph The Knowledge Graph (KG) lets you turn static FAQ text into an intelligent, personalized…

Manage Data Tables and Views in Admin Console

The Kore.ai XO Platform now allows an administrator to view all data tables and views in the workspace. An administrator can also change the ownership of the data tables and views. View Data Tables and Change Ownership As an administrator you can view all data tables in the workspace. To…

Data Tables and Views

Introduction The Kore.ai XO Platform allows virtual assistant designers to view and manage the data mappings for tables and views using the Service Node in the data service. This helps improve the virtual assistant’s performance by ensuring the correct values are mapped and used when viewing or updating details in…

Flow Health

Introduction The Flow Health dashboard summarizes how well the flows of Virtual Assistant (VA) are performing and shows the coverage of intents and transitions in the bot definition. The Flow Health dashboard displays the overall pass or fail percentage of test cases with options to view the transitions coverage. The…

Glossary

The following list provides definitions of commonly used terms in conversation testing. Dynamic Text Marking The dynamic text annotation feature allows you to annotate a section of the text. During test execution, the annotated portion of the text is ignored by the platform for text assertion. To know more, see…

Test Case Execution Summary

The Test Case Execution Summary allows you to view the test case results, identify the failed test cases, and resolve the flow of the virtual assistant. It gives complete details of the overall test results and the defects found. The following sections explain the options available on the Conversation Testing…

Test Case Assertion

A test case assertion is a statement specifying a condition that must be satisfied for a test case to be considered successful. In the context of conversational systems, test case assertions can be used to validate various aspects of the conversation, such as the correctness of the response to a…

Test Editor

You can use the Test Editor to view the test cases and their metadata. This section explains the steps to access the test editor and use the available options: On the Conversation Testing page, click on any Test Suite to go to the Test Editor. In the Test Editor, the…

Create a Test Suite

A Test Suite contains a collection of test cases grouped to simulate a specific conversation between the user and the bot and used anytime for test execution. You can know the execution status and determine and analyze the results in a test suite. In Conversation testing, you can create the…