Exploring the Conversational Analytics dashboard in Platform Analytics experience

  • Release version: Washingtondc
  • Updated February 1, 2024
  • 3 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Exploring the Conversational Analytics Dashboard in Platform Analytics Experience

    The Conversational Analytics dashboard is designed to enhance the performance of Virtual Agent (VA) interactions by providing valuable insights into conversational data. This tool allows ServiceNow customers to refine topics and improve the deflection rate, ultimately leading to better user experiences. The dashboard retains conversational and analytics data for up to two years and offers real-time updates.

    Show full answer Show less

    Key Features

    • Underperforming Topics: Identify and investigate VA topics that are not performing well to facilitate improvements.
    • Conversation Details: Access metadata for each interaction, including user information, chat duration, conversation type, and channel.
    • Dashboard Tabs: The dashboard consists of various tabs such as Overview, Usage, Conversations, Users, Topics, and more, each providing specific insights into VA performance.
    • Advanced Filtering: Filter conversation details by conversation type, duration, user, and language for in-depth analysis.
    • NLU Prediction: Evaluate how well the Natural Language Understanding (NLU) model performs in interpreting user intents.
    • Issue Auto-Resolution: Review data on user issues that the Virtual Agent has resolved automatically.

    Key Outcomes

    By utilizing the Conversational Analytics dashboard, ServiceNow customers can expect to:

    • Enhance user engagement and reduce drop-off rates.
    • Gain insights into which topics are most and least utilized, enabling targeted improvements.
    • Monitor performance trends over specified date ranges to assess the effectiveness of VA interactions.
    • Utilize detailed conversation records to troubleshoot and optimize user experiences.

    Use Conversational Analytics dashboard to improve Virtual Agent (VA) interactions with users. The dashboard provides insights into conversational data, and helps you refine topics and improve the deflection rate of VA.

    Conversational Analytics dashboard

    Conversational Analytics dashboard provides insights into conversations so you can see how well Virtual Agent understood and resolved user issues. Virtual Agent keeps conversational data, that is, records of conversations with the users, and analytics data for up to two years. The dashboard contains indicators which, for example, reveal:
    • What percentage of users transfer from VA to a live agent
    • How to increase engagement rate and reduce user drop-offs
    • Whether the user reached the last node in a topic
    • Most and least used topics
    • Conversation details using advanced filters
    • How to optimize conversation design

    Virtual agent analytics overview tab

    Key features

    Underperforming topics

    See the underperforming VA topics to investigate and improve topic performance.

    Virtual Agent Underperforming topics section with visualizations for least used and incomplete topics.

    Conversation details

    Discover metadata about each VA interaction, including the user, chat duration, conversation type, and channel.

    Virtual Agent Analytics Dashboard conversation details tab.

    Overview

    The following sections provide a high-level overview of how to use each section of the dashboard from the top down.

    Date range of data displayed

    The Start date and End date fields at the top of the dashboard specify the data range of the data summarized on each page.

    Virtual Agent chat data ranges shown by start and end dates in year-month-day format.

    All data is continually pushed from Virtual Agent to the dashboard in real time, and retained for up to two years.

    For information about setting the date range, see Set the date range of the data.

    Certain data visualizations might not have data available for the start date and end date selected in the Start date and End date fields. In this case, the widget shows a start date and end date for the visualization based on the data availability within the selected date range.

    Getting detailed data

    The Overview tab contains key indicators to help you evaluate the performance of VA. You can view more details in the following ways:

    • Select a tab, for example, Usage.
    • Select an indicator, for example, Active VA users.

    Dashboard tabs
    Table 1. Dashboard tabs
    Tab Description
    Overview View the key indicators of the performance of VA.
    Now Assist in VA View key indicators to monitor the performance of Now Assist in Virtual Agent. This is visible only when Now Assist in Virtual Agent is enabled.
    Usage View VA conversation usage, for example, the language and conversation type.
    Conversations View conversation details and troubleshoot individual conversations. Advanced filtering enables you to filter the list of conversations by conversation type, duration, user, and language.
    Users View how your users are conversing with VA. Advanced filtering enables you to filter the list by user, channel, and last conversation.
    Topics View topic performance indicators. Some of the indicators are most and least used topics, topics corresponding to VA conversations that were transferred to a live agent, average length of conversations per topic, and topic blocks used.
    NLU Prediction View NLU performance indicators such as number of times the NLU prediction model accurately understood the intent of the user's conversation or auto-selected a topic. The indicator links to the NLU Workbench if your instance includes NLU.
    Custom Events View the number of custom chat events that you created using the Events page.
    Issue Auto-Resolution View details about the number of user issues intercepted by the auto-resolution service and resolved by the Virtual Agent.
    Virtual Agent performance

    This area of the dashboard contains key VA performance indicators that you can drill down into for more details.

    Virtual Agent analytics dashboard key performance indicators.

    The indicators show data trends, such as increase or decrease of the data values in the date range specified on the dashboard. Clicking on the info icon displays the description of the indicator.

    Certain trend visualizations on the dashboard such as the trends in intent and topic matching do not support viewing monthly, weekly, and daily data.