Exploring ServiceNow Otto for Virtual Agent

  • Release version: Australia
  • Updated March 12, 2026
  • 3 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 Exploring ServiceNow Otto for Virtual Agent

    ServiceNow Otto for Virtual Agent leverages large language models (LLMs) and generative AI to enhance Virtual Agent capabilities by improving deflection rates and reducing the extensive setup traditionally required for Natural Language Understanding (NLU) topic discovery. This integration simplifies topic creation, enabling faster deployment without deep AI expertise and supports multiple user access points such as chat widgets, mobile apps, and Microsoft Teams.

    Show full answer Show less

    Key Features

    • LLM-Driven Topic Discovery: Uses generative AI to streamline topic creation and reduces reliance on lengthy development cycles and subject matter experts. Existing NLU topics can be migrated to LLM topics via the Assistant Designer Asset library.
    • Guided Setup: Enables admins to configure ServiceNow Otto quickly and easily, requiring no special expertise.
    • Enhanced Search and Conversational Experience: Combines AI Search with chat to provide synthesized, actionable responses based on natural language queries, improving user satisfaction and resolution rates.
    • Service Catalog Integration: Allows users to interactively request and refine service catalog items, such as specifying product details within the same conversation, powered by generative AI.
    • Configurable Skill Picker: Admins can customize the skill picker interface to align with organizational needs, including labeling and promoted assets.
    • Multi-Portal Deployment: Supports deployment across various channels including chat widgets, mobile apps, and Microsoft Teams.
    • Performance Monitoring: Admins can track usage and performance metrics through the Conversational Interfaces console and AI Admin Hub to optimize Virtual Agent effectiveness.

    Key Outcomes

    • Faster Virtual Agent Deployment: The guided setup reduces configuration time from months to minutes, accelerating time-to-value.
    • Improved User Experience: Users receive precise, natural language-driven responses and actionable options that reduce the need to escalate to live agents.
    • Increased Deflection Rates: Enhanced AI capabilities help resolve more queries within Virtual Agent, lowering operational overhead.
    • Flexible and Scalable AI Assistant: ServiceNow Otto adapts to evolving user requests mid-conversation and supports multiple communication platforms, ensuring broad accessibility.
    • Comprehensive Analytics: Admins gain insights into ServiceNow Otto’s usage and impact, enabling data-driven improvements to Virtual Agent strategy.

    ServiceNow Otto for Virtual Agent uses large language models (LLMs) and generative AI skills to improve deflection rates and reduce the amount of time-consuming work that Natural Language Understanding (NLU) topic discovery requires.

    ServiceNow Otto capabilities bring generative AI to Virtual Agent. Using LLMs for topic discovery simplifies the amount of setup and configuration required for Virtual Agent. Topics that use keyword and Natural Language Understanding (NLU) discovery often require months of development and the involvement of dedicated subject matter experts. Unusual issues or questions may lead a user to contact a live agent instead. You can continue to use your existing NLU topics and migrate them into new LLM topics using the topic migration feature within Assistant Designer Asset library. For more information on topic migration, see Migrating NLU/keyword Virtual Agent topics to LLM topics.

    Use the guided setup to configure ServiceNow Otto for Virtual Agent in a few minutes. No expertise is necessary to launch the experience. For more information, see Configuring assistants overview.

    ServiceNow Otto for Virtual Agent is available through portals on the chat widget, the mobile app, and Microsoft Teams.

    Search in ServiceNow Otto for Virtual Agent

    ServiceNow Otto for Virtual Agent enhance the user experience by combining AI Search with chat. These skills can increase issue resolution in Virtual Agent and reduce deflections to a live agent.

    The following figure shows how the requester uses natural language rather than keywords in the chat. Now LLM Service determines the most likely option based on the requester's input and sends a synthesized response with possible action items. Queries can apply to both information searches and service catalog requests.

    Figure 1. Example of standard chat's synthesized response with conversational and non-conversational catalog options
    A summary of the iPad options along with catalog options to either Go to request or Start request in the Virtual Agent.

    ServiceNow Otto for Virtual Agent shows users the best possible answer to a query, in the form of actionable options displayed along with the results. The bot may generate answers based on what it found, or return actionable options or links. Users have the option to see more results as needed.

    Service Catalog access

    ServiceNow Otto for Virtual Agent also gives users access to available options in the Service Catalog. Users can request an item, such as a mobile phone. The user can then provide more information to refine the search. For example, they may refine their request to a blue 256-GB iPhone. They can even request a new item instead, all in the same conversation, and the generative AI creates its responses using natural language.

    For full catalog functionality in the chat window, enable the generative AI experience for catalog item request submissions. For more information, see Configure ServiceNow Otto in Conversational Catalog Request.

    LLM topic creation

    Admins can create LLM topics for ServiceNow Otto for Virtual Agent. For more information, see LLM assistants. Activate the ServiceNow Otto Topics skill in the ServiceNow Otto guided setup. For more information, see Configuring assistants overview.

    For more examples of having a conversation with ServiceNow Otto for Virtual Agent, see Using ServiceNow Otto for Virtual Agent.

    The skill picker is configurable based on the user's requirements. For example, a user can change the View all topics label in the skill picker and add or remove the bullet list of promoted assets from the skill selection message.

    Benefits

    ServiceNow Otto for Virtual Agent provides the following benefits.

    Benefit Feature User
    Configure ServiceNow Otto for Virtual Agent in a few minutes, from either the Conversational Interfaces console or the AI Admin Hub console. Guided setup experience virtual_agent_admin or admin
    ServiceNow Otto skills can be turned on within the guided setup. Activate an AI skill virtual_agent_admin or admin
    Deploy ServiceNow Otto for Virtual Agent on multiple portals using the chat widget, the mobile app, and Microsoft Teams. Configuring assistants overview virtual_agent_admin or admin
    Generative AI enhances the user search experience with the ability to generate answers and enabling the user to select the Show more results option for a new search. ServiceNow Otto Q&A Genius Results skill requesters
    Give users in-chat access to available options in the Service Catalog. ServiceNow Otto Multi-Turn Catalog Ordering skill requesters
    ServiceNow Otto for Virtual Agent switch easily between requests, using plain language when new queries are made in the same conversation. Mid-topic switching during ServiceNow Otto for Virtual Agent conversations requesters
    Monitor performance metrics for ServiceNow Otto for Virtual Agent from the Conversational Interfaces console. Conversational Interfaces console virtual_agent_admin or admin
    Monitor value metrics (ServiceNow Otto usage versus ServiceNow Otto for Virtual Agent) from the ServiceNow Otto admin console. Overview tab in AI Admin Hub virtual_agent_admin or admin