---
sourceDocument: Yokohama Conversational Interfaces
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/yokohama/conversational-interfaces

 Release :

    - yokohama

ft:locale :

    - en-US

ft:publication_title :

    - Yokohama Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Virtual Agent Designer user input controls

# Virtual Agent Designer user input
controls {#ariaid-title1}

Release version: Yokohama  
Updated January 30, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 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 Virtual Agent Designer user input controls

Virtual Agent Designer provides a variety of user input controls to capture information during conversations.
These controls store user responses in input variables accessible throughout the same topic, facilitating dynamic interaction and data handling.
The controls support integration with Natural Language Understanding (NLU) models and Large Language Model (LLM) topics to enhance conversational intelligence and flexibility.
Show full answer Show less  

## Common Properties

* **Input Variable:** Each control stores user input in a variable named based on the control's assigned name (lowercase, underscores instead of spaces). This variable can be accessed with `getValue` and `getDisplayValue` methods.
* **NLU Entity:** When NLU is enabled, input controls like Text, Choice, Boolean, Date Time, and Carousel can be linked to NLU entities for slot filling, extracting recognized user input values automatically.
* **Enable NLU to Switch Topics:** Allows users to change the conversation topic by interpreting free-text input, enhancing flexibility in dialog flow.
* **Default Value:** Input prompts can have preset values defined as static strings or scripts.
* **Confirmation Messages:** Configurable bot messages that confirm user inputs at the end of node interactions.

## Input Controls for LLM Topics

Supported input controls when creating LLM Virtual Agent topics include:

* Input Collector: Gathers multiple user responses for use in LLM conversations.
* Text: Prompts for free-text input.
* Static Choice: Presents a predefined list for single selection.
* Dynamic Choice: Generates choices dynamically via table queries or scripts.
* Boolean: Provides Yes/No prompts.
* Date Time: Allows selection of calendar dates and/or times.
* Carousel: Displays a horizontal series of selectable labeled images.

**Note:** Limit the number of input controls to five per LLM topic or Input Collector to avoid overwhelming the LLM and causing inaccurate responses.

## Additional Input Controls

* **Grouped Choice:** Organizes multiple groups of choices in one message.
* **File Picker:** Enables users to upload files or images, which display immediately in the Virtual Agent client.
* **Secure Text:** Encrypts sensitive text input, suitable for LLM topics requiring data security.

## Practical Benefits for ServiceNow Customers

These input controls enable ServiceNow customers to build conversational agents that effectively capture and process diverse user inputs with flexibility and security. Integration with NLU models allows for intelligent entity recognition and smooth topic transitions, while LLM support lets you design sophisticated, dynamic dialogues. Proper use of input controls helps ensure accurate data collection, improved user experience, and enhanced automation within your Virtual Agent deployments.  
Use the collection of input controls provided by Virtual Agent Designer to prompt and capture
information from the user in a conversation.

## Common input control properties {#va-user-inputs__section_a4j_hsb_vcc}

In addition to [data pills and condition controls](https://servicenow-prod.fluidtopics.net/Snkx7CwL1lUPOyQ_Ex72XA "A Virtual Agent topic consists of a collection of controls within a topic flow. Use these controls to collect, process, and present information to your users. Controls can also read, create, and update records on your instance."), each input control has the following common properties:  

Input variable for the user response
:   Each control stores the user response in an input variable that is accessible from other controls within the same topic using the `getValue` and `getDisplayValue` methods. The variable
    name is based on the name that you assign to the input control. For example, if you assign the name <kbd class="ph userinput">First prompt</kbd> to an input control, the variable name is `first_prompt`. The
    variable name is lowercase, with an underscore character instead of a space. For more information on these methods, see [Virtual Agent scripts](https://servicenow-prod.fluidtopics.net/ke~GUHWgbfbG1gVpGBXv6A "Use ServiceNow Virtual Agent script methods and variables to write chat scripts, such as response, trigger, and flow scripts. Variables can also provide context for your live support topics and conversations.").
:
    Figure 1. The Variable name field is populated automatically

## Large Language Model (LLM) user input controls {#va-user-inputs__section_bn4_dy3_jcc}

The following user input controls are supported in LLM topics when you create an LLM Virtual Agent topic. LLM user inputs include the following.

* [Input Collector](https://servicenow-prod.fluidtopics.net/fQOc2pyDvp_lKSJW49DBMw "Use the Input Collector control to gather data for use by Now Assist in conversations that use large language model (LLM) topic discovery.")
* [Text input](https://servicenow-prod.fluidtopics.net/nFFAwDdJsnoHmzgubmBnww "The Text user input control in a Virtual Agent topic prompts the user for a text string.")
* [Static Choice list](https://servicenow-prod.fluidtopics.net/Elpm5lmY2MOaQiQqAFqUew "Use the Static Choice user input control in a Virtual Agent topic to list predefined choices available to the user. You can select only one item from a choice list.")
* [Dynamic Choice list](https://servicenow-prod.fluidtopics.net/x4Hn9qfVhrXzMo238dM6Ug "Use the Dynamic Choice user input control in a Virtual Agent topic to dynamically create a list of available choices for your users. Create these choices by querying a table or by using a script to dynamically create them.")
* [Boolean input](https://servicenow-prod.fluidtopics.net/_fU1PDSS5mneXWUElT5GQw "Use the Boolean user input control in a Virtual Agent topic to present a Yes/No prompt to the user.")
* [Date Time input](https://servicenow-prod.fluidtopics.net/slmJG0UiR36gTM_x7hwgSQ "Use the Date Time user input control in a Virtual Agent topic to enable the user to select a calendar date, time (hours and minutes), or both.")
* [Carousel input](https://servicenow-prod.fluidtopics.net/WikfoHc7PxhsL9grpymm0w "Use the Carousel user input control in a Virtual Agent topic to present a prompt and a horizontal series of labeled images. The user can select a single item from the carousel.")
{#va-user-inputs__ul_r2f_4y3_jcc}  
Note:  
Avoid placing more than five user input controls in a single LLM topic, or more than five in a single Input Collector. Excessive user input controls can overwhelm the LLM and may lead to inaccurate or unexpected responses.

## Natural Language Understanding (NLU) entity properties {#va-user-inputs__id_kxn_knb_vcc}

:   If NLU is enabled, the following properties are displayed in the property sheet for the Text, Static Choice, Dynamic Choice,
    Boolean, Date Time, and Carousel input controls. To view or enable these properties, go to the Advanced options section.

    * NLU entity: The entity that corresponds to the input variable for the control. You select the entity from the list of entities associated with the topic intent, as defined in the NLU model that you're using for the topic. When Virtual Agent recognizes the entity value in user utterances and if the value meets the entity prediction confidence threshold, then Virtual Agent extracts the value. The value is stored in the input variable for the node. This storing action is called slot filling. Slot filling recognizes when multiple values for the same NLU entity occur in a conversation. Users are prompted with a list to confirm which node value to select when multiple nodes are tied to the same NLU entity. This property is available only for NLU topic discovery.  
      Figure 2. NLU entity property ![Slide the NLU entity toggle to select an NLU topic when topic discovery is enabled.]()
    * Enable NLU to switch topics: Enables NLU prediction for the node. If enabled, users can enter text to answer questions, regardless of the type of input control being used. Virtual Agent uses this utterance to match another existing intent, letting the user switch topics. To enable this property on a node, navigate to Advanced optionsTopic switching.  
      Figure 3. Enable NLU to switch topics property ![Under Advanced options - Topic switching, slide the Enable NLU to switch topics toggle to switch topics property.]()
    {#va-user-inputs__ul_h3d_jwn_thb}

Default value
:   An input prompt can have a preset value that you define. This value can be either a string or a script that returns a string. This property is in the Advanced options section.
:
    Figure 4. Default value property

Confirmation messages
:   These bot response messages signal the end of the node interaction and ask the users to confirm their response. This property is in the Advanced options section.
:
    Figure 5. Confirmation messages properties
* **[Input Collector user input control](https://servicenow-prod.fluidtopics.net/fQOc2pyDvp_lKSJW49DBMw)**   
  Use the Input Collector control to gather data for use by Now Assist in conversations that use large language model (LLM) topic discovery.
* **[Text user input control](https://servicenow-prod.fluidtopics.net/nFFAwDdJsnoHmzgubmBnww)**   
  The Text user input control in a Virtual Agent topic prompts the user for a text string.
* **[Static Choice user input control](https://servicenow-prod.fluidtopics.net/Elpm5lmY2MOaQiQqAFqUew)**   
  Use the Static Choice user input control in a Virtual Agent topic to list predefined choices available to the user. You can select only one item from a choice list.
* **[Grouped Choice user input control](https://servicenow-prod.fluidtopics.net/TzvcClkF0ldVaOZcQAdhKQ)**   
  Use the Grouped Choice user input control in a Virtual Agent topic to list multiple groups of choices in one message.
* **[Dynamic Choice user input control](https://servicenow-prod.fluidtopics.net/x4Hn9qfVhrXzMo238dM6Ug)**   
  Use the Dynamic Choice user input control in a Virtual Agent topic to dynamically create a list of available choices for your users. Create these choices by querying a table or by using a script to dynamically create them.
* **[Boolean user input control](https://servicenow-prod.fluidtopics.net/_fU1PDSS5mneXWUElT5GQw)**   
  Use the Boolean user input control in a Virtual Agent topic to present a Yes/No prompt to the user.
* **[Date Time user input control](https://servicenow-prod.fluidtopics.net/slmJG0UiR36gTM_x7hwgSQ)**   
  Use the Date Time user input control in a Virtual Agent topic to enable the user to select a calendar date, time (hours and minutes), or both.
* **[File Picker user input control](https://servicenow-prod.fluidtopics.net/D60UEeCPVwDNOZFfzBmVMA)**   
  Use the File Picker user input control in a Virtual Agent topic to prompt a user to upload an image or any file type. After the user uploads an image file, the image appears immediately in the Virtual Agent client.
* **[Carousel user input control](https://servicenow-prod.fluidtopics.net/WikfoHc7PxhsL9grpymm0w)**   
  Use the Carousel user input control in a Virtual Agent topic to present a prompt and a horizontal series of labeled images. The user can select a single item from the carousel.
* **[Secure Text user input control](https://servicenow-prod.fluidtopics.net/4BKsVUw1Dokqopa3L9N0Pg)**   
  The Secure Text control provides a means to encrypt sensitive information provided as simple text or other formats. Use this control to encrypt sensitive information in topics that use large language model (LLM) discovery.

*[\>]: and then