Now Assist Conversational Help

  • Release version: Yokohama
  • Updated July 31, 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 Now Assist Conversational Help

    Now Assist Conversational Help is a built-in ServiceNow skill that leverages Generative AI to provide precise answers directly within the Now Assist panel. It is enabled by default for users with appropriate roles and requires no additional subscription, making it immediately accessible as the "Get Help" feature.

    Show full answer Show less

    This skill integrates with the ServiceNow Now LLM Service (Large Language Model) to deliver contextual, relevant responses by searching ServiceNow product documentation synchronized across multiple global regions.

    How It Works

    • Query Submission: Users can either select the Get Help skill or enter queries directly into the Now Assist panel.
    • AI Search: Queries are sent to a central ServiceNow instance where AI Search scans knowledge tables containing product documentation synchronized via Instance Data Replication.
    • Re-ranking: The retrieved content chunks are re-ranked using Now Assist Q&A to improve relevance.
    • Cache Lookup: If an identical query exists in the cache, the stored answer is returned instantly; otherwise, the query and re-ranked content are processed by Now LLM to generate a contextual answer.
    • Version-Specific Results: Answers are tailored based on the release version of the user’s current instance, ensuring information reflects the latest updates and features.

    Key Benefits for ServiceNow Customers

    • Immediate Access: The skill is enabled by default with no extra subscription, simplifying adoption.
    • Accurate and Contextual Help: Utilizes AI and the Now LLM to deliver relevant answers from official ServiceNow documentation.
    • Multi-Region Support: Product content is synchronized across US East/West, EMEA, and APJC regions to optimize performance and availability.
    • Customizable Skills: Available skills in the Now Assist panel can be tailored in collaboration with integration teams to fit organizational needs.
    • Improved User Experience: Efficient query handling, including caching and re-ranking, ensures fast and precise responses.

    Configuration and Control

    The Get Help feature can be disabled if desired via the Now Assist Admin Settings. Additionally, the list of available skills shown in the Now Assist panel is customizable to align with specific use cases or integration requirements.

    This skill uses Generative AI application capabilities to provide answers to the questions on the Now Assist panel.

    Important:
    This Now Assist skill is turned on by default. The skill will be automatically available to appropriate role users for the application. For more information, see Now Assist skills, agents, and agentic workflows on by default.
    The Now Assist Conversational Help skill displays as Get Help on the Now Assist panel.
    Note:
    The Get Help feature is available as a part of Now Assist entitlements and no new subscription is required. The feature is enabled by default and you can turn it off in the Now Assist Admin Settings. The ServiceNow Now LLM Service (Large Language Model) is the default model provider for this Now Assist skill to retrieve precise answers to the users' questions.
    You can ask your question in two ways:
    • Select Get Help skill and submit a query to use the help option in the Now Assist panel.
    • Submit your query directly in the Now Assist panel. It will perform discovery and find the most appropriate skill among the listed, based on the keywords you entered. This discovered skill is used to retrieve answers for your queries.
      Note:
      The available skills displayed in the Now Assist panel can be customized in consultation with the integration teams.

    How Conversational Help works

    Your query goes through the following steps to retrieve the best response.
    1. AI search

      The query is be sent to a central ServiceNow instance, where AI Search will search the knowledge table that stores content from product doc content.

      We use Instance Data Replication (IDR) that synchronizes product documentation content from Now Support instances.
      Note:
      Multiple central ServiceNow instances are deployed across three regions: US East or US West, EMEA, and APJC.
    2. The top matching chunks (or records) along with the user’s query, are sent to the Now Assist Q&A Genius Result configuration to generate a meaningful, contextual answer.
    3. Re-ranking

      The Now Assist Q&A, an out of box (OOB) capability, re-ranks the retrieved chunks to ensure better relevance.

    4. Cache lookup
      • If the user query exists in the cache, the pre-stored answer is returned.
      • If the query is not cached, the query and re-ranked chunks are sent to Now LLM to generate a meaningful answer.
    The Now LLM retrieves the most relevant result from https://www.servicenow.com/docs/ portal and displays it in the same panel.
    Note:
    Effective from this release, the query will retrieve results based exclusively on the release version of the user's current instance. This enhancement is integrated into the query process to ensure the delivery of precise results that reflect the latest updates and features.

    Now Assist Conversational Help skill

    For more information, see Fetch end points in Now Assist Conversational Help skills.