AI agents
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
yesterday
OOB triage and categorize agent is giving in consistent response.
If run multiple times give different suggestions for category for same INC.
I understand AI agents are probabilistic. How to control this behavior?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
yesterday
My experience say AI deal or work on data, when your data will be increased it gets trained more and share good and accurate results. Also we need to understand it is still machine which needs human support. If still doubt, please log a case with now support team.
If my response proves useful, please indicate its helpfulness by selecting " Accept as Solution" and " Helpful." This action benefits both the community and me.
Regards
Dr. Atul G. - Learn N Grow Together
ServiceNow Techno - Functional Trainer
LinkedIn: https://www.linkedin.com/in/dratulgrover
YouTube: https://www.youtube.com/@LearnNGrowTogetherwithAtulG
Topmate: https://topmate.io/dratulgrover [ Connect for 1-1 Session]
****************************************************************************************************************
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
yesterday
Hi @Diksha Gautam K ,
In the lower instance, you can duplicate the agent and modify or update the prompt and check whether it resolves the issue. Again the output depends on the data available in your instance. AI Agents use GAF (Group Action Framework) to retrieve similar incidents, and based on that data, they predict the output.
Thanks!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
yesterday
I would suggest verifying that you are on the latest AI Agent app versions. Some of the earlier versions had real problems with inconsistencies in performance, but we've come a long way in the last year or so.
Most of the grouping/categorizing scenarios rely on Group Action Framework, which has improved significantly as well:
