\(Legacy\) Test topic and NLU model translations
Test a translated Virtual Agent topic and the localized NLU model to ensure that it works as expected in a conversation.
Before you begin
Note: An updated Assistant Designer Asset library user interface is available when you install ServiceNow Otto for Virtual Agent. This content assumes that you can see the list view. If ServiceNow Otto for Virtual Agent is not installed, you see the legacy UI and topics page. For more information, see Virtual Agent Designer legacy topics page.
Role required: virtual_agent_admin or admin
Procedure
-
Navigate to All > Conversational Interfaces > Assistant Designer.
-
Select the Asset library tab.
-
Set the discovery type toggle switch to NLU/keyword, followed by the NLU topic you want to test.
-
Under the Languages tab, select Manage languages.
-
In the Select NLU Model list, select the model group to test.
-
In the View language list, select a language.
-
In the Test column for an intent, select Test.
-
On the test window, run the conversation and review the results in the test tabs.
For more information about using the chat test window, see (Legacy) Testing NLU/Keyword topics.
The following image illustrates how you can test a French translation.
[Omitted image "lang-test-window.png"] Alt text: The test window displays the conversation in French. The fly-out panel displays the test phrase that was entered and the matching intent.
-
End the test by closing the window.
What to do next
Use the test results to modify the topic as needed. Continue testing as you adjust your topic and the NLU language mappings.
When the topic is ready, publish the topic to make it available to users. You can publish all or some of the NLU mappings. For more information about publishing a topic, see Publish a Virtual Agent topic.
Tip: You can view localization insights from the Manage languages page and the Virtual Agent Designer home page. Navigate to All > Conversational Interfaces > Virtual Agent > Designer, and then select Localization Insights from the Resources.
Parent Topic:(Legacy) Localize Virtual Agent topics that use NLU topic discovery
---
title: \(Legacy\) Test topic and NLU model translations
description: Test a translated Virtual Agent topic and the localized NLU model to ensure that it works as expected in a conversation.
locale: en-US
canonical_url: https://www.servicenow.com/docs/r/conversational-interfaces/test-nlu-language-model.html
release: brazil
topic_type: task
last_updated: "2026-09-10"
reading_time_minutes: 2
breadcrumb: [Localize NLU topics, Localizing NLU conversations, Localization options for NLU conversations, Build and deploy NLU conversations, \(Legacy\) Virtual Agent for NLU, Conversational Interfaces]
---
# \(Legacy\) Test topic and NLU model translations
Test a translated Virtual Agent topic and the localized NLU model to ensure that it works as expected in a conversation.
## Before you begin
**Note:** An updated Assistant Designer Asset library user interface is available when you install ServiceNow Otto for Virtual Agent. This content assumes that you can see the list view. If ServiceNow Otto for Virtual Agent is not installed, you see the legacy UI and topics page. For more information, see [Virtual Agent Designer legacy topics page](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/conversational-interfaces/vad-prev-topics-page.md).
Role required: virtual\_agent\_admin or admin
## Procedure
1. Navigate to **All** > **Conversational Interfaces** > **Assistant Designer**.
2. Select the **Asset library** tab.
3. Set the discovery type toggle switch to **NLU/keyword**, followed by the NLU topic you want to test.
4. Under the Languages tab, select **Manage languages**.
5. In the **Select NLU Model** list, select the model group to test.
6. In the **View language** list, select a language.
7. In the **Test** column for an intent, select **Test**.
8. On the test window, run the conversation and review the results in the test tabs.
For more information about using the chat test window, see [\(Legacy\) Testing NLU/Keyword topics](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/conversational-interfaces/va-designer-testing.md).
The following image illustrates how you can test a French translation.
\[Omitted image "lang-test-window.png"\] Alt text: The test window displays the conversation in French. The fly-out panel displays the test phrase that was entered and the matching intent.
9. End the test by closing the window.
## What to do next
Use the test results to modify the topic as needed. Continue testing as you adjust your topic and the NLU language mappings.
When the topic is ready, publish the topic to make it available to users. You can publish all or some of the NLU mappings. For more information about publishing a topic, see [Publish a Virtual Agent topic](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/conversational-interfaces/virtual-agent/publish-virtual-agent-topic.md).
**Tip:** You can view localization insights from the **Manage languages** page and the Virtual Agent Designer home page. Navigate to **All** > **Conversational Interfaces** > **Virtual Agent** > **Designer**, and then select **Localization Insights** from the Resources.
**Parent Topic:**[\(Legacy\) Localize Virtual Agent topics that use NLU topic discovery](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/brazil/markdown/conversational-interfaces/use-lf-translate-va-nlu.md)
| title | \(Legacy\) Test topic and NLU model translations |
| description | Test a translated Virtual Agent topic and the localized NLU model to ensure that it works as expected in a conversation. |
| locale | en-US |
| canonical_url | https://www.servicenow.com/docs/r/conversational-interfaces/test-nlu-language-model.html |
| release | brazil |
| topic_type | task |
| last_updated | 2026-09-10 |
| reading_time_minutes | 2 |
| breadcrumb | Localize NLU topicsLocalizing NLU conversationsLocalization options for NLU conversationsBuild and deploy NLU conversations\(Legacy\) Virtual Agent for NLUConversational Interfaces |