Guidance on Virtual Agent type (NLP vs LLM) for new implementation with Now Assist
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
3 weeks ago
The client has never used Virtual Agent in their instance before. They are now planning to start using it and have also purchased the Now Assist license.
In this scenario, should I develop an NLP-based Virtual Agent or an LLM-based Virtual Agent?
Currently, they would like to use only two topics:
Incident creation
Request creation
Please advise on the best approach to proceed.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
3 weeks ago
Hi @jay97
My first point for LLM is the primary benefit of having New Assist in place.For request creation, you need to have the Conversational Request plugin enabled.
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/atul_grover_lng [ Connect for 1-1 Session]
****************************************************************************************************************
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
3 weeks ago
I've been using "regular" (NLP-based) VA for a few years now but have only poked around LLM VA a little bit and it seems that LLM topic creation is (or at least can be) largely the same as before, so, to me, if you're paying for Now Assist, might as well just jump into the latest and greatest LLM topic paradigm to avoid potential future conversion troubles, even if you're not gonna make the most use out of LLM functionality.
Incident-creation can be super simple and straightforward, but I do think you'll probably be able to use the LLM functionality for request-creation from what I've gathered - and that one use case is probably more than enough to convince you.
(But see what others with more experience have to say before trusting me - I'm far from an expert on the LLM front!)
