---
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


---

# Creating a Virtual Agent topic

# Creating a Virtual Agent topic {#ariaid-title1}

* Release version: Australia
* 
* Updated March 12, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 minutes to read

Use Assistant Designer Asset library to create and modify Virtual Agent topics (conversations). Build your topic to meet a specific objective or goal, such as fulfilling a user's request or helping a user complete a task.

## Before you begin

Do the following:

* Review [Getting started with the Asset library in Assistant Designer](https://www.servicenow.com/docs/ZSHubJIiz1AbowMvQgaAog "The Assistant Designer Asset library includes a diagram tool for creating and managing assets, which are blueprints for conversations between a Virtual Agent and a user. You can design topics that help your users resolve common work issues or guide them through self-service tasks.").
* Configure Virtual Agent settings. For example, if you're creating large language model (LLM) topics, turn on ServiceNow Otto in Virtual Agent. For more information, see [Configuring assistants overview](https://www.servicenow.com/docs/Sc9j38ILtu~9qRO4WPWVZg "Use Assistant Designer to build and optimize large language model (LLM) assistants for your conversational needs. Assistant Designer is a centralized assistant administrator experience that allows you to create and manage both chat and voice assistants."). If you're creating Natural Language Understanding (NLU) topics, configure NLU settings. For more information, see [Configure Natural Language Understanding in Virtual Agent](https://www.servicenow.com/docs/OoXkuoaft1nBJxDPhF_3cQ "Configure Natural Language Understanding (NLU) in Virtual Agent to identify the NLU service provider for your instance. You can also specify the languages of NLU models used during conversation design, based on the languages supported by your NLU provider and the ServiceNow AI Platform.").
* Plan your conversation before you begin. For more information, see [Designing a Virtual Agent topic](https://www.servicenow.com/docs/bOAr4K9CGqCQHgIG2KNcKw "Walk through the design of an example Virtual Agent topic that enables users to view incidents they submitted. The example highlights various design controls that can be used to build the conversation flow.").
* Verify that you're in the appropriate application scope before you create or update a topic. For example, if you're creating ITSM topics, verify that you're in the ITSM Virtual Agent Conversations scope (and not the scope for the ITSM NLU Model for Virtual Agent Conversations). For details, see [Change the application scope for Virtual Agent Designer topics](https://www.servicenow.com/docs/YlJd1jIWeeVQBqean8bRPA "Set the application scope before you create or update a topic. For example, if you're creating ITSM topics, verify that you're in the ITSM Virtual Agent Conversations scope (and not the scope for the ITSM NLU (Natural Language Understanding) Model for Virtual Agent Conversations).").
{#create-virtual-agent-topic__ul_qkk_xjg_g3b}

Role required: virtual_agent_admin or admin

## About this task

The topic is in the Inactive state until you publish it. Publishing a topic changes the topic state to Active and automatically deploys the topic to your Virtual Agent clients.

The Large Language Model (LLM) topic type is faster and easier to set up compared to using Natural Language Understanding. You don't have to select NLU intents or train NLU models for your virtual agent. For more information, see [LLM topic discovery in Virtual Agent](https://www.servicenow.com/docs/4ZTKKoNkvTJqb_m0ZXG~5w "Large language models (LLMs) enable Virtual Agent to process user statements in plain language. Conversations that use LLMs can outperform those conversations that use Natural Language Understanding (NLU), with easier setup.").

When NLU is enabled, the Set up Natural Language Understanding (NLU) section is displayed in the Topic Properties page. You can use this section to specify the associated NLU model and intent for the topic. You can also optionally specify keywords that Virtual Agent can use as a fallback if NLU doesn't return a matching intent and topic. For more information, see [Natural Language Understanding (NLU) topic discovery in Virtual Agent](https://www.servicenow.com/docs/3dcuXDs2JnLVLW1Df~N7yw "Apply Natural Language Understanding (NLU) models that enable Virtual Agent to process user statements in automated conversations. An NLU model provides information that your virtual agent uses to determine what users want to do and to extract relevant values from their input. With NLU, Virtual Agent can offer a more natural and engaging conversational experience.").

## Procedure

1. Navigate to AllConversational InterfacesAssistant Designer.
2. Select the Asset library tab.
3. Set the topic discovery toggle switch to LLM or NLU/keyword depending on the type of topic you're creating.
4. Select the type of topic.  
   * For LLM topics:
     1. Select Create Asset.

     2. From the Create asset window, select Topic.

        <br />

        Important:  
        Selecting any of the other topics in the window will open the create flow in the respective application.
     {#create-virtual-agent-topic__ol_w3h_fwl_xfc}
   * For NLU/Keyword topics, select Create topic.

   {#create-virtual-agent-topic__ul_gzn_yvl_xfc}
5. On the form, fill in the fields.  
   For a description of the field values, see [Create a topic form](https://www.servicenow.com/docs/ZrgeiXz3GxkEl7kBYATDtA "The Create a topic form is used to set the properties for a new conversational topic for Virtual Agent.").
6. On the topic creation form, select Create.
7. On the Flow tab, build the conversation flow.  
   {#create-virtual-agent-topic__table_mmy_blm_hmb__entry__2}

   | Flow steps | Description |
   |-|-|
   | Add controls | To create the topic flow: 1. Select the controls for user inputs, bot responses, or utilities from the palette and drop them onto the canvas.When you add a control to the canvas, it becomes a node in the conversation flow. 2. For each node, complete the corresponding property sheet. In the topic header bar, select Save. The topic header bar displays a Saving in progress... message. The toast message Successfully saved your topic appears in the lower-right corner afterward for 4 seconds, and can be closed by selecting the X in the message. For details about each control and the corresponding properties that you define, see [User inputs](https://www.servicenow.com/docs/gfDlouC9E8VknQ33IKpE~Q "Use the collection of input controls provided by Assistant Designer to prompt and capture information from the user in a conversation."), [Bot responses](https://www.servicenow.com/docs/sv9owzV5tVgCKdfFVtvKxg "Assistant Designer offers various controls for displaying bot responses in a conversation. Because the bot responses occur in third-party platforms, the format for each output may vary."), and [Utilities](https://www.servicenow.com/docs/VFcFVN6Y_2YwTtftpaZAbg "You can control interactions within a topic by using utilities in Assistant Designer. These utilities perform various actions such as adding topic blocks (reusable components), running a script, or adding different conversation paths (branches) in a topic. Utilities are represented as nodes in a conversation flow but do not display anything to the user."). {#create-virtual-agent-topic__ol_b3l_3fm_3mb} As you add controls, watch for a yellow warning badge or a red error badge in the corner of the control. The number on the badge indicates the number of issues in that control, such as missing mandatory information in the property sheet. (Highlighting a badge or the "Incomplete" banner at the top of the property sheet details the items in need of correction.) |
   | Move a node | Select the node, drag it to the new location in the flow, and Select Save. |
   | Delete a node | Select the X in the upper right corner of the node. In the topic header bar, select Save. The topic header bar displays a Saving in progress... message. The toast message Successfully saved your topic appears in the lower-right corner afterward for 4 seconds, and can be closed by selecting the X in the message. Note: You can't delete a node that has a script variable used by subsequent JavaScript expressions in the flow. Also, you can delete a decision node only when it has a single branch. |
   [ ]

   {#create-virtual-agent-topic__table_mmy_blm_hmb}
8. Select Test in the header bar to test your topic in a chat window.  
   You can review test results in the adjoining tabs. For detailed information, see [Testing LLM topics](https://www.servicenow.com/docs/W9ige~Eqk2tnd2AdMk4cKw "Preview, test, and debug topics that use large language models (LLMs) in the Assistant Designer chat window.") and [Testing NLU/Keyword topics](https://www.servicenow.com/docs/rjsdmOKqEUk2wIcYC7hAdw "Use the chat test window to preview, test, and debug Natural Language Understanding (NLU)/Keyword topics.").

   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. For more information, see [Integrating Virtual Agent with 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.").
9. When you're finished with the topic, select Save in the topic header bar.  
   The topic is in the Inactive state until you publish it.  
   The topic header bar displays a Saving in progress... message. The toast message Successfully saved your topic appears in the lower-right corner afterward for four seconds, and can be closed by selecting the X in the message.
{#create-virtual-agent-topic__steps_ght_myq_1bb}

## What to do next

[Publish](https://www.servicenow.com/docs/LBVmSOsl0hXZiEDW~MBV8A "Deploy an inactive topic or an updated topic to save it and make it available to users on Virtual Agent clients.") the topic to deploy the topic to your Virtual Agent clients. The topic state changes to Active.

If you created a topic that might be frequently used in certain contexts (environments), consider promoting the topic as part of the [default or custom chat experience](https://www.servicenow.com/docs/R4waAGZguKdwl4f2r_Fndw "Create different chat experiences for your end users based on the context in which they initiate a conversation with Virtual Agent.").
* **[NLU model mapping in Virtual Agent Designer](https://www.servicenow.com/docs/GpyDoulyDruLh~u4R6MFYg)**   
  ServiceNow model groups help you to manage the localization of both topics and Natural Language Understanding (NLU) models more easily. You can map Virtual Agent topics to a new or existing model group directly from Virtual Agent.
* **[Topic mapping to a multilingual NLU model group](https://www.servicenow.com/docs/wAP0NMCi7dapSNmaBxXBPQ)**   
  When you map a topic to a multilingual model group in Virtual Agent Designer, the topic mappings for enabled languages are set up automatically.
* **[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.
* **[Add NLU to an existing keyword topic](https://www.servicenow.com/docs/Fq62DjnPQZPthdm7b3mYHQ)**   
  Create and map an NLU model group and intent for the topic from Assistant Designer Asset library.
* **[Add nodeless NLU entities as input variables to a topic](https://www.servicenow.com/docs/0czOtLjtxkSCTZbborBXlg)**   
  You can add nodeless NLU entities as input variables to a topic if NLU is enabled for Virtual Agent. These variables can be slot-filled from NLU service provider predictions or provided outside of the scope of the topic.
* **[Branch a Virtual Agent conversation with a Decision utility](https://www.servicenow.com/docs/KeyEX5LBB3ynYTm1iO3eYw)**   
  Your conversations may need to branch depending on end user input or choices. Use the Decision utility to branch the conversation when certain conditions are met.
* **[Insert a header card in a Static Choice or Dynamic Choice control](https://www.servicenow.com/docs/3dqZfXbC3E4H389nEL0QRw)**   
  When you create a Virtual Agent topic, you can include images and YouTube videos on Static Choice and Dynamic Choice user input controls.
* **[Change the application scope for Virtual Agent Designer topics](https://www.servicenow.com/docs/YlJd1jIWeeVQBqean8bRPA)**   
  Set the application scope before you create or update a topic. For example, if you're creating ITSM topics, verify that you're in the ITSM Virtual Agent Conversations scope (and not the scope for the ITSM NLU (Natural Language Understanding) Model for Virtual Agent Conversations).
* **[Define script variables for a topic](https://www.servicenow.com/docs/Jry1PMzY_Z7LublNb~eCCA)**   
  Use the Variables sidebar to define script variables for a topic. Script variables can store information that is not found in ServiceNow tables. This information can then be shared elsewhere in a topic.
* **[Create a small talk topic](https://www.servicenow.com/docs/hJdp7~FszIWa60kgOFwS6A)**   
  Build small talk topics that let Virtual Agent engage in casual conversation with users. A small talk topic provides a response to a casual question that users might ask during a conversation, such as the time or date. A small talk topic can occur anytime within a conversation session and can be unrelated to the original conversation intent.
* **[Control topic discovery and visibility](https://www.servicenow.com/docs/6ThTXKFSFnANkhRIcjIiAQ)**   
  Admins and topic authors can enable Virtual Agent to discover topics for use in chats, include a topic in the list users see, or both. The topics can be setup topics and small talk topics.
* **[Use system-derived entities in an NLU topic](https://www.servicenow.com/docs/7T7VSbILcHA50W7omuSHTw)**   
  Associate system-derived entities such as such as date, time, duration, or location with a node in a topic.

*[\>]: and then