Join the #BuildWithBuildAgent Challenge! Get recognized, earn exclusive swag, and inspire the ServiceNow Community with what you can build using Build Agent.  Join the Challenge.

VA Expert feedback Loop & Irrelevant-utterances help needed

nttd-fcaballero
Tera Contributor

‎07-01-2025 12:45 PM

Hello everyone in the community! We need help with our NLU model. It's small, with only three intents initially. We have trained the model to detect these intents and it does this well. We have created a test set with many expressions that are irrelevant to the model so that in tests the bot falls back to Fallback; however, we haven't been able to use the tools to train the bot to dismiss irrelevant expressions because these tools don't allow us to select the model. I'm attaching some screenshots

NLU Model.png

Our NLU Model

 

NLU Model 2.png

Expert feedback does not allow us to select our model

 

What are we doing wrong? What's failing? Can you help us?

Thank you in advance!

  • 2,189 Views
10 REPLIES 10

Lynda1
Kilo Sage
In response to fabi0caballer0

‎08-04-2025 08:26 AM

The testing you have screen shots of, are not related to the EFL. It is using the phrases you have in that test document. It is literally testing the NLU Module. This activity can be done in any environment. 

You are expecting those test phrases to get into the EFL, that will never happen. The EFL uses phrase from actual chats to pick up the phrases.

NLU model testing you can do in any environment, That EFL work is done in production since that is where the EFL is picking up the phrases from actual chats. This runs every 30 days, that is why I made it a habit to work the EFL once a month, since the VA picks up from both the NLU and the EFL.

I feel like I typed in circles, I hope this makes sense!

0 Helpfuls