Analyzing Your Bot

LLM and Generative AI Logs

The LLM and Gen AI Logs on the XO Platform provide detailed information about requests sent to LLMs and the corresponding responses. The logs include data on features accessing the LLMs, response generation time, payload details, tokens used, and more. It enables bot designers to track and compare usage across…

Task Execution Logs

The Task Execution Logs feature helps you gain in-depth insights into the task execution-related data and assess your virtual assistant’s performance in executing tasks. The Analyze > Task Execution Logs page shows information specific to task execution in the following sections: Failed Task: Indicates the number of unsuccessful tasks. API…

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…

Create Custom Dashboard Filters

Prior to the Version 10.0 release, you had to add filter conditions in the ‘Filter by’ clause for individual widgets within a dashboard. There was no provision to filter the records at a dashboard level. The platform now allows you to create custom filters that filter the data for all…

Feedback Analytics

Once you’ve created a Feedback Survey for your conversations based on a survey type (NPS, CSAT, or Like/Dislike), it’s important to constantly monitor and analyze the customer responses, feedback survey scores, and trends over a given period. Thus, knowing the survey type scores and the key metrics for respondents, responses,…

Conversation Insights

Once a virtual assistant is published, it is important to understand and analyze the performance. Kore.ai platform provides various dashboards and one of them being NLP Insights that captures details like Intent Found, Intent Not Found, Unhandled Utterances, etc. However, to categorize the utterances as True Positives (TP), True Negatives…

Virtual Assistant Health and Monitoring

The Health and Monitoring dashboard offers a goal-driven approach to improving the accuracy of the virtual assistant’s Natural Language Processing (NLP) model. The training data is analyzed along with the test coverage and test results of the test suites to provide insights into the NLP Model’s performance. This dashboard lets…

Dashboard Filters

The dashboard filters are used to filter and view the analytics data for virtual assistants (VAs) on the following dashboards in the ANALYZE section based on the user’s selection(s): Overview Dashboard Conversations Dashboard Users Dashboard Performance Dashboard NLP Insights Conversation Insights Conversations History Conversation Flows To understand the filter criteria…

How do I look at specific Conversations?

To look at a specific conversation on the Conversation History Dashboard, select the relevant filters from the filter selection panel and click on the conversation on the dashboard. Learn more.

What are Conversations and their Types?

Conversations include the voice call or chat communication between a virtual assistant and a customer to fulfill a specific task. They can be one of the following types: Interactive: Involves a two-way information (requests and responses) exchange between the virtual assistant and the customer. Non-interactive: Involves one-way information exchange from…
Menu