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

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Assistant Designer user input controls

# Assistant Designer user input
controls {#ariaid-title1}

* Release version: Zurich
* 
* Updated March 12, 2026
* 
* ![](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 Assistant Designer user input controls

Assistant Designer provides a variety of user input controls that allow you to prompt and capture information from users during Virtual Agent conversations.
These input controls are essential for designing interactive and dynamic chatbots that can gather user responses efficiently and accurately.
Show full answer Show less  

## Common Properties

* **Input Variable:** Each input control stores the user response in a variable named based on the control's assigned name, formatted in lowercase with underscores. This variable is accessible within the same topic using getValue and getDisplayValue methods.

## Large Language Model (LLM) User Input Controls

For topics leveraging LLM Virtual Agent capabilities, the following user input controls are supported:

* Input Collector
* Text Input
* Static Choice List
* Dynamic Choice List
* Boolean Input
* Date Time Input
* Carousel Input

**Best Practice:** Avoid using more than five user input controls per LLM topic or Input Collector to prevent overwhelming the model and causing inaccurate responses.

## Natural Language Understanding (NLU) Properties

If NLU is enabled, input controls like Text, Static Choice, Dynamic Choice, Boolean, Date Time, and Carousel expose additional properties:

* **NLU Entity:** Links an input variable to an NLU entity from the topic's intent model, enabling slot filling where Virtual Agent extracts and stores recognized entity values from user utterances.
* **Enable NLU to Switch Topics:** Allows users to change topics mid-conversation by matching their input to other intents, even if the input control type does not typically accept free text.

## Additional Features

* **Default Value:** Input prompts can have preset values defined as strings or scripts, facilitating smoother user interactions.
* **Confirmation Messages:** Customizable bot responses that confirm the end of an input interaction, helping users verify their responses.

## Input Control Types and Uses

* **Input Collector:** Gathers multiple data points for use with ServiceNow Otto within LLM topics.
* **Text Input:** Prompts users to provide free text responses.
* **Static Choice:** Presents a predefined list of options, allowing a single selection.
* **Grouped Choice:** Displays multiple groups of predefined choices in one message.
* **Dynamic Choice:** Generates a choice list dynamically by querying tables or running scripts.
* **Boolean Input:** Offers a simple Yes/No prompt.
* **Date Time Input:** Enables selection of calendar dates and/or times.
* **File Picker:** Allows users to upload files or images, which display immediately in the Virtual Agent client.
* **Carousel:** Shows a horizontal series of labeled images from which users select one.
* **Secure Text:** Encrypts sensitive textual information, especially useful in LLM discovery topics.

## Practical Implications for ServiceNow Customers

By effectively using these input controls, ServiceNow customers can design more engaging, accurate, and context-aware Virtual Agent conversations. Leveraging NLU integration and LLM-specific controls enhances the bot's understanding and flexibility, enabling better user experience and efficient data collection. Properly configuring these controls with attention to input limits and confirmation prompts ensures reliability and clarity in user interactions.  
Use the collection of input controls provided by Assistant 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://www.servicenow.com/docs/7X_XT1wkiJlqIjGhcssimQ "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://www.servicenow.com/docs/UvxJFy7emVLY884mBVLg4w "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://www.servicenow.com/docs/oTWyZXZtMKTXQCBIoasClw "Use the Input Collector control to gather data for use by ServiceNow Otto in conversations that use large language model (LLM) topic discovery.")
* [Text input](https://www.servicenow.com/docs/SuODfdqQa9JzTTR4smkQ5w "The Text user input control in a Virtual Agent topic prompts the user for a text string.")
* [Static Choice list](https://www.servicenow.com/docs/OvK6b5MtkR0df38qGI64bw "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://www.servicenow.com/docs/NQdcRjTm3EQesmMSJoSuYg "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://www.servicenow.com/docs/lFdZ2wSTOLAU57oMLQTG1w "Use the Boolean user input control in a Virtual Agent topic to present a Yes/No prompt to the user.")
* [Date Time input](https://www.servicenow.com/docs/FBSsKUGDw29x3_N6vHJJhg "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://www.servicenow.com/docs/ejFDDvu_1w5RJBveMw75_g "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.
    * 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.
    {#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.

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.
* **[Input Collector user input control](https://www.servicenow.com/docs/oTWyZXZtMKTXQCBIoasClw)**   
  Use the Input Collector control to gather data for use by ServiceNow Otto in conversations that use large language model (LLM) topic discovery.
* **[Text user input control](https://www.servicenow.com/docs/SuODfdqQa9JzTTR4smkQ5w)**   
  The Text user input control in a Virtual Agent topic prompts the user for a text string.
* **[Static Choice user input control](https://www.servicenow.com/docs/OvK6b5MtkR0df38qGI64bw)**   
  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://www.servicenow.com/docs/hEi5gQhO5kkAWWlC96Ajgw)**   
  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://www.servicenow.com/docs/NQdcRjTm3EQesmMSJoSuYg)**   
  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://www.servicenow.com/docs/lFdZ2wSTOLAU57oMLQTG1w)**   
  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://www.servicenow.com/docs/FBSsKUGDw29x3_N6vHJJhg)**   
  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://www.servicenow.com/docs/gr6_9RD2bP0s0wsufKJUbQ)**   
  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://www.servicenow.com/docs/ejFDDvu_1w5RJBveMw75_g)**   
  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://www.servicenow.com/docs/xGs00P7jWuLA1Fdbfydy3w)**   
  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