Loading...
Loading...
Loading...
Previous suggested step: Knowledge optimizer overview
Next suggested step: Optimize your knowledge base content
In the knowledge optimizer dashboard, you can view and analyze performance and high-level operational metrics for a selected knowledge base V2 or knowledge fabric configuration. You can also filter these results by specifying a date range or a configured touchpoint.
You can view these metrics for knowledge bases:
For answered and unanswered queries, you can see the application in which the query appears:
The All Queries tile displays a pie chart of the percentage of answered and unanswered queries. Hover over a section in the chart and see the value and category, answered or unanswered, that make up 100% of all queries.
The Answered Queries tile displays the total number of queries that the bot answered and the application from which the conversation occurred. To see the percentage of answered queries for a particular application, as indicated by the color-coded labels, hover over a section in the chart.
The Unanswered Queries tile displays the total number of queries that the bot did not answer and the application from which the conversation occurred. To see the percentage of unanswered queries for a particular application, as indicated by the color-coded labels, hover over a section in the chart.
From this tile, you can optimize your knowledge base.
This tile shows the top queries, up to 20, that were not answered during bot conversations and the number of times in which each unanswered query appeared in a conversation.
This tile shows the top queries, up to 20, that were answered during bot conversations and the number of times in which each answered query appeared in a conversation.
This tile shows the top articles, up to 50, used in the knowledge base within the specified time frame. The tile also displays the number of times each article was used in bot conversations, the last modified date, and the percentage of positive or negative feedback, including positive and negative feedback counts.
Click an article to open the Article View and see the article details, feedback analytics, number of views, and other queries that this article answered.
You can view these metrics for knowledge configurations:
The Total interactions tile shows the total number of voice and digital interactions in which the selected touchpoints generated answers from knowledge fabric content during the selected date range. This metric provides administrators with a baseline volume of answer generation activity, helping them understand the overall scale of usage before drilling into feedback trends or specific query issues.
The Total feedback tile shows the the total number of feedback submissions, both positive and negative, that touchpoints received on generated answers within the selected date range. This metric helps administrators gauge how actively users are engaging with the feedback mechanism, providing context for interpreting feedback scores and identifying whether enough feedback volume exists to draw reliable conclusions about content performance.
The count of answer generation queries, up to 50, that received negative feedback, indicating instances where the generated answer did not adequately address the query. This metric allows administrators to pinpoint specific problem areas, review query details such as generated answers, sources, and touchpoints, and identify knowledge gaps or content issues that need attention.
Click a query to open the Query details panel and see more query details such as queried date, suggestion, whether copied by agent or not, whether context search was enabled, and the conversation ID. It also shows the generated answer and sources that were used to generate the answer.
Get user feedback about articles.