Plans supporting Eddy AI analytics
| Professional | Business | Enterprise |
|---|---|---|
Eddy AI assistive search analytics empowers you to understand and optimize the performance of AI search in your Knowledge base. The Eddy AI - Assistive Search analytics page provides information on the overall Eddy AI performance and search metrics, including unanswered searches of your knowledge base site. Also, you can visualize search analytics through charts and graphs for better understanding.
NOTE
To know more about the languages supported by Eddy AI, click here.
The Conversational Eddy AI related metrics are available only in KB site 2.0 projects.
Accessing Eddy AI search analytics
Navigate to Analytics () > Eddy AI in the Knowledge base portal.
The Eddy AI - Assistive Search page will appear.
You can view a comprehensive overview of article performance for the past week by default, but the filter allows you to select a different date range.
Using filters to customize data
By default, the data shows metrics for the last week. You can adjust this using filters:
Click the Date filter dropdown.
Select a predefined range (e.g., This month, Last month) or choose Custom to specify a date range.
Eddy AI search analytics page overview
NOTE
If multiple chatbots are deployed, the data from all chatbot instances will be merged and reflected in the results.
Similarly, if multiple knowledge base widgets are in use, data from all widget instances will be combined into the results.
You can view the following article performance metrics as tiles based on the filter applied:
Field | Description |
|---|---|
Total conversations | Total number of conversations in Eddy AI, where one or more Eddy queries count as a conversation. This metric will be available only for Knowledge base site 2.0 where Eddy AI is conversational. A single message is also counted as a conversation. |
Total queries | Total number of queries performed in Eddy AI. Queries are individual questions included in the conversation. |
Answered queries | Total number of queries that returned a result. |
Unanswered queries | Total number of queries that did not produce any results. |
Query analysis
You can interact with the graph to learn more information on query analysis:
Date-wise metrics: Hover over the graph to find the metrics on a specific date.
Date: The metrics are shown in month/date format. To view metrics of a different month, click the This month dropdown at the top right and make a selection of your choice.
All: Represents the comparison of answered queries, unanswered queries, and conversations in a single graph.
Answered (green line): Click to view the graph of queries that returned a result.
Unanswered (red line): Click to view the graph of queries that did not produce any result.
Conversations (violet line): Click to view the graph of conversations. It is available only for KB site 2.0 projects. Scroll down to the last section to export Conversations in CSV format.
Export image: To export the Query analysis as an image in .png format.
NOTE
Try to maintain the Unanswered searches as low as possible compared to the Answered searches to ensure your readers find the right content when they perform a Knowledge base site search. Unanswered searches typically occur when there is a lack of relevant information in the documentation, causing the Eddy AI to be unable to fetch data for specific search queries. Keeping your documentation up-to-date can help minimise such queries.
Conversation depth metrics
The conversation depth metrics display the graph illustrating the total number of queries per conversation alongside the total number of conversations. Conversation depth metrics are available only for KB site 2.0 projects.
Hover over each bar to see the exact number of conversations.
The graph tracks conversations ranging from 1 to 5 queries, with conversations exceeding 5 queries grouped under 6+.
Click the Export image () icon to export Conversation depth metrics as an image in .png format.
Feedback chart
The feedback charts display the data illustrating the total number of Likes and Dislikes, along with the percentage information. The total percentage of feedback is represented inside the color chart.
Click the Export image () icon to export the Feedback as an image in .png format.
Popular queries
This section showcases the top five popular search themes, along with their frequency counts for the selected month. Queries are grouped by keywords, highlighting the most popular topics of the month and the frequency of related questions asked by readers.
NOTE
The Popular queries metric is generated only if at least one month of data is available.
Unanswered queries
This section showcases the top five popular search themes, along with their frequency counts for the selected month. Each keyword represents a popular topic with unresolved searches.
NOTE
Post-processing occurs monthly, where 30 days of data is analyzed. The data is sent to OpenAI, which identifies the most common keywords and groups them into 10 primary topics. Any remaining data that does not fit into these categories is grouped under "Others." This helps to organize and highlight the most frequent topics efficiently. This is done for all the answered and unanswered queries.
Most referenced articles
This section lists the five most-referenced source articles for the selected month, along with how often each has shown as a source in Eddy AI search results.
Conversations
This section offers a detailed view of user interactions in a tabular form showing queries, response status, and feedback.
Search field: Enter a query to search for a specific conversation or query.
Conversations: The conversation will appear. By default, only the first question of each conversation is visible, with the other questions collapsed. Click on a desired query to open a pop-up that displays the entire conversation.
NOTE
If a conversation started last month and continues into this month, the conversation will be included in last month's analytics.
Query topic: Query topics are fetched from the list of popular queries. A minimum of 30 days of data is required to generate a query topic.
Response: Indicates the response status, such as answered () or unanswered queries ().
Feedback: Displays the feedback, such as likes or dislikes.
Filter: Filter by query topic, response status, feedback type, or application.
Response Status: Filter the response status by three options: All, Answered, or Unanswered.
Feedback: Filter the feedback types by four options: All, None, Liked, or Disliked. By default, All is selected.
Query type: Filters queries from previous months. This filter is unavailable for the current month.
Export: Export the data as a CSV file based on the applied filters.
FAQs
Why am I unable to filter the data on a weekly basis?
Popular queries and unanswered search keywords are derived from algorithmic grouping methods. These methods require sufficient data to categorize keywords based on the frequency of responses generated.
How do I resolve queries for which no response is generated?
To address queries that receive no responses, identify the relevant articles based on the keywords derived from unanswered search prompts raised by readers. Update the content of these articles accordingly.
How does Eddy AI conversation analytics fetch information if the conversation is in multiple languages?
If a conversation includes multiple languages, the conversation will be updated in the conversation table for each language used. However, specific metrics like total searches, answered queries, unanswered queries found, and feedback received will only be updated for the language in which they occurred.
How does Eddy AI conversation analytics fetch information if the conversation is in multiple workspaces?
If a conversation includes multiple workspaces, it will be updated in the conversation table for each workspace used. However, specific metrics such as total searches, answered queries, unanswered queries, and feedback will only be updated for the languages used within the respective workspace.
How are queries different from conversations?
Queries are individual questions included in the conversation. One or more queries contribute to a conversation.