Input Collector user input control

  • Release version: Yokohama
  • Updated January 30, 2025
  • 2 minutes to read
    • Summarize
    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 Input Collector user input control

    The Input Collector control is designed to gather user input data for Now Assist conversations that utilize large language model (LLM) topic discovery in ServiceNow. It enables effective collection and management of multiple user inputs to enhance conversational interactions driven by LLMs.

    Show full answer Show less

    Key Features

    • LLM Exclusive: The Input Collector is available only for topics using LLM discovery.
    • Input Capacity: It can hold up to 5 LLM user inputs (excluding other Input Collectors). To collect more inputs, multiple Input Collector nodes can be chained, or the system property com.glide.cs.vainputcollectormaxnodes can be adjusted.
    • Flexible Node Management: Nodes within an Input Collector can be reordered on the canvas by dragging or in the table view using up/down arrows. Nodes can also be added, removed, or moved between Input Collectors via drag-and-drop on the canvas.
    • Flow Action Properties: Each node supports configuration properties including:
      • Node Name: Identifier for the node in the topic flow.
      • Advanced Instructions for LLM: Custom instructions such as data formats, restrictions, or default values can be set using plain language, scripts, or conditions with the data pill picker.
      • Confirmation Message: Optionally displays a summary of collected inputs at conversation end, allowing users to confirm or revise their responses. This feature is enabled by default.
      • Conditional Display and Skipping: Nodes can be conditionally shown or allowed to be skipped based on no-code conditions or scripts.

    Channel Support

    The Input Collector control supports various communication channels with differences in LLM and NLU/keyword support:

    Channel LLM Support NLU/Keyword Support Constraints
    Web UINot supportedSupportedNone
    Mobile UINot supportedSupportedNone
    Now Assist panelNot supportedSupportedNone
    Microsoft TeamsSupportedSupportedNone
    SlackNot supportedNot supportedNot applicable
    WorkplaceNot supportedNot supportedNot applicable
    Facebook MessengerNot supportedNot supportedNot applicable
    SMS TwilioSupportedNot supportedNot applicable
    LINENot supportedNot supportedNot applicable
    WhatsAppSupportedNot supportedNot applicable
    Apple Messages for BusinessNot supportedNot supportedNot applicable
    Alexa (Voice)Not supportedNot supportedNot applicable

    Practical Benefits for ServiceNow Customers

    • Enables efficient, structured collection of multiple user inputs in LLM-driven conversations, improving the accuracy and relevance of Now Assist responses.
    • Supports conditional logic and user control over input steps, enhancing conversational flexibility and user experience.
    • Offers broad channel compatibility, especially for Microsoft Teams, SMS Twilio, and WhatsApp, enabling multichannel support for conversational automation integrated with LLMs.
    • Allows customization of input collection flow and confirmation messaging to ensure data quality before proceeding in conversations.

    Use the Input Collector control to gather data for use by Now Assist in conversations that use large language model (LLM) topic discovery.

    For an overview of the Input Collector from a user perspective, watch this video.

    Input Collector properties

    The Input Collector is only available for topics that use LLM discovery.

    The Input Collector can hold up to 5 of any of the LLM user inputs aside from another Input Collector. To collect more than 5 user inputs, place multiple Input Collector nodes in sequence or adjust the Value of the com.glide.cs.va_input_collector_max_nodes property in the System Properties [sys_properties] table.

    You can reorder nodes inside the Input Collector on both the canvas and table views. To reorder nodes on the canvas, select a given node inside the Input Collector and drag it up or down in the list. You can add or remove nodes from an Input Collector, or nodes between multiple Input Collectors, by selecting a node and dragging it into or out of an Input Collector node on the canvas. To reorder nodes in an Input Collector in the table view, select a given node in the list, then select the up or down arrow next to the node.

    Specify the flow action properties for the node that you want to create.

    Property Description
    Node name

    Name that identifies this node in the topic flow.
    Advanced
    Additional instructions for LLM

    Further instructions to the LLM, such as adding data formats, restrictions, or default values for user responses. You can create additional instructions in plain language, input a script, or define conditions with the data pill picker.
    Confirmation message

    Toggle switch to display a summary of collected inputs to the user at the end of a conversation. If Summary message is activated, the Virtual Agent, when activated, presents the information that you have entered and asks if everything is correct. Select Yes to continue the chat or No to restart collecting user input. You can also reply by typing a response in the chat window, to confirm or deny the summary or to change your answer. This option is active by default, and shows an enabled icon when activated.
    Hide or skip this node
    Conditionally show this node if

    No-code condition statement or low-code script that specifies a condition for presenting this node in the conversation. The condition must evaluate to true.
    Allow user to skip this node if

    No-code condition statement or low-code script that specifies a condition for letting users skip this node in the conversation. The condition must evaluate to true. You can set this field using either the condition builder or a script.

    Example Input Collector capability

    Basic properties include the node name. Advanced options include Additional instructions to LLM, Confirmation messages, and Hide this node.

    Input Collector canvas view

    Input collector canvas view, holding text and static choice input nodes. You can move nodes by selecting and dragging them inside, out of, or within the Input collector.

    Input Collector table view

    Input collector table view, showing text and static choice nodes, with up and down arrows to reorder nodes inside the collector.

    Channel support

    Table 1. Channel support for the Input Collector control
    Channel LLM support NLU/keyword support Constraints
    Web UI Not supported Supported None
    Mobile UI Not supported Supported None
    Now Assist panel Not supported Supported None
    Microsoft Teams Supported Supported None
    Slack Not supported Not supported Not applicable
    Workplace Not supported Not supported Not applicable
    Facebook Messenger Not supported Not supported Not applicable
    SMS Twilio Supported Not supported Not applicable
    LINE Not supported Not supported Not applicable
    WhatsApp Supported Not supported Not applicable
    Apple Messages for Business Not supported Not supported Not applicable
    Alexa (Voice) Not supported Not supported Not applicable