--- 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 --- # Testing NLU/Keyword topics # Testing NLU/Keyword topics {#ariaid-title1} * Release version: Australia * * Updated March 12, 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Testing NLU/Keyword topics This content explains how ServiceNow customers can effectively test and debug Natural Language Understanding (NLU) and Keyword topics within Virtual Agent using the chat test window in Assistant Designer. It details how to preview conversations across different channels, validate topics, and analyze test results to ensure accurate intent matching and entity recognition. Show full answer Show less ## Testing Environment and Options * The default test window is the web (Service Portal) chat client, but you can also test topics in integrated third-party messaging apps such as ServiceNow Otto panel, Microsoft Teams, or Slack if configured. * Testing is initiated by selecting the Test option in the topic header or by testing active topics from the home page. * Validation badges indicate missing or incomplete information in the topic flow, and a Validation Issues tab lists detailed problems to correct before proceeding. ## Chat Test Window Features When testing a topic, the chat test window includes several useful tabs for analysis: * **Analysis:** Displays intent matching results, prediction scores, entity recognition, and slot-filling based on test phrases entered. * **Variables:** Shows all variables involved in the conversation (input, script, live agent, and slot-filled variables) along with their current values. * **Context:** Allows specifying context variables to simulate different chat scenarios influencing topic intent or routing, such as selecting a specific portal name. * **Logs:** Provides processing and error messages, useful for debugging custom scripts within Virtual Agent flows. ## Using Topic Discovery and Active Topic Testing The Include Topic Discovery option is enabled by default when testing individual topics, automatically generating intent predictions from test phrases. When testing active (published) topics, topic discovery is also enabled but test case creation is disabled. ## Improving NLU Models Customers can refine utterances and entities in Virtual Agent Designer based on Analyze tab feedback, retrain the NLU model, and retest until achieving satisfactory intent prediction accuracy. Once finalized, both topic and model can be published together. ## Next Steps and Automation * After testing, use insights from the chat test window to fine-tune conversations and improve intent matching. * Train and test NLU models conveniently within Assistant Designer without switching interfaces. * Leverage the ServiceNow Automated Test Framework via Assistant Designer to create and run automated tests, ensuring topic flows continue to function correctly after updates. Use the chat test window to preview, test, and debug Natural Language Understanding (NLU)/Keyword topics. As you work on a topic in Assistant Designer, you can run your conversation in a chat test window. The default test window is the web (Service Portal) chat client. If you're using the [Virtual Agent integrations with third-party messaging apps](https://www.servicenow.com/docs/eYn0beX_CQLOgHdD3uqHuA "Enable users to run Virtual Agent bot conversations in supported third-party messaging apps. Use the Conversational Integration apps for Slack, Microsoft Teams, and Workplace that are available from the ServiceNow Store to configure these messaging apps on your ServiceNow instance."), elements in your conversation might appear differently in third-party messaging applications. Test your conversations in any third-party applications where you want to deploy Virtual Agent. If the ServiceNow Otto panel, Microsoft Teams application, or Slack application is configured for your environment, preview options for those channels are displayed in the Test button list. Select Preview in Otto panel or Preview in Microsoft Teams in the list to test your topic in those environments. ## Testing your NLU/Keyword topic in the chat test window {#va-designer-testing__section_fq4_tmj_1mb} Figure 1. Example NLU/Keyword test options To run your topic in the chat test window, select the Test option in the topic header bar. Alternatively, you can test active (published) topics by selecting Test active topics while viewing NLU topics on the home page. Note: If your topic is missing any necessary information, an incomplete badge appears in the corner of the flow diagram pane. A yellow or red warning badge also appears next to each node. The incomplete badge lists the total number of issues, while the local warning badges show how many are found in each node. Selecting Test when there are issues present opens a Validation Issues tab on the sidebar, which counts up and details all the issues needing correction. These details include a full description and a hyperlink to each incomplete node. The chat test window opens in the chat widget and displays adjoining tabs that provide details about your topic as you test it. You can use these tabs: * Analysis - The results for intent matching and entity recognition appear based on what you entered in the conversation. * Variables - List of all the variables used in the conversation, such as input and live agent variables. * Context - Options for specifying the context (using context variables) in which a topic is run. * Logs - A list of the processing performed. {#va-designer-testing__ul_kmv_gmf_nzb} Figure 2. Example Natural Language Understanding (NLU) chat test window and test tabs By default, the Include Topic Discovery option is enabled. This option automatically performs topic discovery and generates prediction results for NLU topics using test phrases that you enter in the test window. The conversation begins with the Virtual Agent greeting and the button for the menu of available topics. If you're using the Test Active Topics option or sub-options from the home page, topic discovery is enabled, so it's not listed as an option. Testing active topics behaves the same as testing from a topic except that test cases can't be created. ## Analyze test phrases tab {#va-designer-testing__section_gnc_cvz_hmb} For NLU enabled topics, the Analyze test phrases tab provides an analysis of the possible intents that match the test phrase (utterance) that you entered in the chat test window. The tab lists the prediction results, which include matched intents and their prediction scores, along with any entity recognition and slot-filling results. The top match is listed first. The predicted intents depend on the prediction confidence threshold set in the NLU service. Figure 3. Example Analyze test phrases tab for NLU/Keyword topics If an utterance doesn't match a current intent, you can add or change utterances in Virtual Agent Designer. For more information, see [Modify NLU utterances and entities for a Virtual Agent topic](https://www.servicenow.com/docs/cnkJMk25Etci63gaBlFXJw "View, test, and modify NLU utterances for a Virtual Agent topic on the NLU Intent tab in Assistant Designer Asset library."). Make changes, train the model again, and then retest until you're satisfied with the results. When the topic is ready, you can publish both the topic and the model from Virtual Agent Designer. ## Variables tab {#va-designer-testing__section_v2p_bxw_hmb} The Variables tab displays a list of all the variables used in the conversation and the associated values captured as the conversation progresses, so that you can follow along. A conversation can have these variable types: * Input variables * Script variables * Live agent variables * Variables passed between a calling topic and topic block * "Nodeless" NLU entities declared as a slot-filled variable for the topic {#va-designer-testing__ul_dz5_vyw_hmb}The list is separated into sections by type of variable. The following example shows the Input variables section. Notice that for the static list control, both the display label and value are captured for the selected choice. Figure 4. Example list of input variables The following example shows the Input variables section for the grouped list control. This variable information appears similar to the static list control, but the variables are separated by each group of the grouped choice. Figure 5. Example list of grouped choice variables ## Context tab {#va-designer-testing__section_dqn_b4r_lpb} Use the Context tab to specify a different context for the chat. Choose a context variable from the list. These variables contain contextual information that can be used to determine topic intent or control how chats are routed to live agents. For example, you could select portal from the list of variables and enter the portal name IT Express. The Context tab is unavailable when creating test cases. For more information about defining context variables, see [Configure context variables for storing chat-related information](https://www.servicenow.com/docs/kGrAEmnoX4R6E0RV3rTFKw "Specify chat context variables, also called Live Agent chat variables, for storing chat-related information, such as pre-chat survey responses. These variables contain contextual information that can be used to determine topic intent or control how chats are routed to live agents. You can also define variables to capture contextual information passed in Virtual Agent topic scripts to share with live agents."). For more information about live agent variables that are included with Virtual Agent, see [Live agent chat context variables](https://www.servicenow.com/docs/auUlE1RZ6SBuydgrKzjiag "Use chat context variables to pass certain information from the topic to share with a live agent or to control how bot conversations are routed to live agents. Virtual Agent includes some default variables, and you can define new ones."). Figure 6. Example Context tab ## Logs tab {#va-designer-testing__section_uxp_kz1_3mb} The Logs tab displays the processing and error messages that are recorded while running your conversation. If you're using scripts in Virtual Agent Designer, use `gs.log`, `gs.print`, and `gs.warn` statements in your scripts to output information in this log. Figure 7. Example Logs tab ## Next steps {#va-designer-testing__section_amq_xpr_2mb} When you're done testing your topic, close the test chat window. If needed, you can use the test information to fine-tune your conversation. For example, if the results on the Analyze test phrases tab return multiple possible matches for your utterance, you could update the utterances for your intent and NLU model on the NLU Intent tab for your topic. * **[Train and test your NLU model in Assistant Designer Asset library](https://www.servicenow.com/docs/3ITr4ectfRv3ifwNfNhfiA)** Use the NLU Intent tab to train and try a Natural Language Understanding (NLU) model that is mapped to a topic without leaving Assistant Designer Asset library. * **[Automated testing for Virtual Agent topics that use NLU topic discovery](https://www.servicenow.com/docs/WV2noAcdBtLy5lo19K5JkQ)** Automated testing for your Virtual Agent topic flows uses the ServiceNow Automated Test Framework product through Assistant Designer. You can create and run automated tests through the Automated Test Framework to confirm that your topic flow works after making a change.