---
sourceDocument: Australia Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/conversational-interfaces

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Enhanced handling of user inputs

# Enhanced natural language handling of user inputs in NLU topic discovery {#ariaid-title1}

* Release version: Australia
* 
* Updated March 12, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Give Virtual Agent the capability of recognizing natural variations on
<kbd class="ph userinput">yes</kbd> and <kbd class="ph userinput">no</kbd> from the user, such as
<kbd class="ph userinput">sure</kbd> or <kbd class="ph userinput">nope</kbd>. By defining a range of boolean
responses as affirmative or negative, Virtual Agent doesn't have to prompt the user
to restate their preference.
When Virtual Agent doesn't understand unexpected user input, it prompts the
user again for information that it can understand. Starting with the Tokyo
release, Virtual Agent can understand natural variations in boolean "yes/no"
responses, such as <kbd class="ph userinput">yep</kbd> or <kbd class="ph userinput">nah</kbd>.

## Natural language handling in ServiceNow
NLU {#natural-language-user-response-handling__section_opg_5s4_m5b}

The VA NLU Dispatches \[sys_cs_nlu_dispatch\] table stores the names of the model and intents
that handle utterance variations.

For ServiceNow®
NLU, the Setup Topics Model is already configured to handle boolean
user inputs in English. There are two records in the table, BOOLEAN_NO
and BOOLEAN_YES, which are mapped to the Negative
and Affirmative intents in the Setup Topics Model.

The Setup Topics Model and intents are read only, so if you need to modify the intents or add
additional intents in other languages, create a new model with new intents. You can update the
existing entries and add new ones to the table.

## Setting up natural language handling for third-party NLU providers {#natural-language-user-response-handling__section_y4f_zgp_m5b}

If you are using IBM Watson or Google Dialogflow for NLU topic discovery, add entries for the corresponding model and intents in the VA NLU Dispatches table, as described in [Configure enhanced natural language user input handling](https://www.servicenow.com/docs/6Heh3~kDlEiNY6KmJZ7AyA "Add enhanced natural language handling for boolean user responses to your Virtual Agent environment. If you're using additional languages or third-party NLU providers, specify the model and intents that define variations in yes/no utterances for your bot.").

## Changing the confidence threshold {#natural-language-user-response-handling__section_hcg_dgp_m5b}

The confidence threshold for boolean inputs is defined in the
com.glide.cs.dialog.boolean_threshold system property. The default value
is 0.9. For more information, see [Add a system property](https://www.servicenow.com/docs/access?context=t_AddAPropertyUsingSysPropsList&version=australia&pubname=australia-platform-administration&ft:locale=en-US).
* **[Configure enhanced natural language user input handling](https://www.servicenow.com/docs/6Heh3~kDlEiNY6KmJZ7AyA)**   
  Add enhanced natural language handling for boolean user responses to your Virtual Agent environment. If you're using additional languages or third-party NLU providers, specify the model and intents that define variations in yes/no utterances for your bot.