Document and visual insights AI agent

  • Release version: Zurich
  • Updated July 28, 2025
  • 1 minute to read

    • The document and visual insights AI agent gathers context from user input and document or image attachments, generates the requested information based on the content, and provides the information along with any relevant task details.

    Document and visual insights AI agent overview

    The document and visual insights AI agent performs tasks to process documents and images.
    Data extraction
    Extract specific information.
    Summarization
    Summarize the key topics of documents and images.
    Question answering (Q&A)
    Answer questions about the document or image content.

    The document and visual insights AI agent is not typically used in standalone mode and any use case can access it. For more information on AI agents, see Now Assist AI agents.

    Role masking enables users to limit the roles and privileges of AI agents during tool execution. AI agents that get installed with Now Assist applications are assigned pre-defined roles. If you select Users with specific roles for user access, you must configure the security controls to include these roles. Data access settings must also include these roles. For the instructions to change the security controls, see Define security controls for an AI agent.

    AI agent actions

    When used, the AI agent may attempt the following actions:
    • Determine the type of task to perform based on information provided by the user.
      • Data extraction
      • Summarization
      • Question answering (Q&A)
    • Retrieve the relevant record details.
    • Initiate the process based on the type of task.
    • Provide the task results as directed.
    • Prompt the user to upload a file for processing.
    • Display the results of the AI agent actions in a document view screen.
    • Provide citation sources.
    • Notify the user of task completion and next steps.