Automated Feedback Summarization for Knowledge Articles #203
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
✅ Valid PR for ActionPack Thank you for your contribution. This PR complies with the CONTRIBUTING.md. |
…finition_74773827c368721051c35ffdd4013164.xml
…finition_85035c3bc320321051c35ffdd40131a4.xml
|
✅ Valid PR for ActionPack Thank you for your contribution. This PR complies with the CONTRIBUTING.md. |
Rampriya-S
approved these changes
Oct 19, 2025
Contributor
Rampriya-S
left a comment
Rampriya-S
left a comment
There was a problem hiding this comment.
Approved. This custom Flow Designer action is getting the Knowledge Article and collecting feedback for automated summarization. Thank you for your contribution!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In a Knowledge Management system, maintaining the quality and relevance of knowledge articles is essential. End-users often provide feedback in the form of ratings and comments on articles they read. However, manually reviewing this feedback across a large number of articles is time-consuming and inefficient.
This use case implements an automated process using ServiceNow Flow Designer and scripting to collect, aggregate, and summarize feedback for each Knowledge Article. The summarized feedback is intended for use by Knowledge Managers or Editors to assess article quality, identify content gaps, and prioritize updates or improvements.
Tables Involved:
kb_knowledge – Stores knowledge articles.
kb_feedback – Stores user feedback (ratings and comments) on articles.
Input:
Name
Type
Description
articleSysId
String
Sys_id of the knowledge article to review
Outputs:
Name
Type
Description
summary
String
Text summary of feedback
averageRating
Number
Average rating (0–5 scale)
totalFeedback
Number
Total number of feedback entries
Working Logic (in brief):
Validate Input: Ensure articleSysId is provided.
Aggregate Feedback:
Use GlideAggregate to count total feedback and average rating.
Collect Comments:
Query non-null comments from kb_feedback.
Generate Summary:
Format rating and comments into a readable report.
Return Outputs: Pass the summary, average rating, and total count to Flow.
Example Summary Output:
Feedback Summary: