Now Assist in AI Search properties

  • Release version: Yokohama
  • Updated July 1, 2025
  • 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 Now Assist in AI Search properties

    This content details system properties available in the Yokohama release (updated July 1, 2025) that allow ServiceNow customers to configure and optimize the behavior of Now Assist in AI Search Genius Results. These properties affect how AI Search interacts with caches and the Now LLM Service to generate and retrieve answers for Q&A Genius Results, enabling tailored performance and answer generation based on specific organizational needs.

    Show full answer Show less

    Key Properties and Their Functions

    • snaisassist.semanticcachemode: Controls the operational mode for caching and answer retrieval. It supports three modes:
      • off: Uses only the first-level cache and the Now LLM Service. If no cache match is found, queries are sent to the Now LLM Service. Dynamic Translation bypasses caches and queries the Now LLM Service directly.
      • offline: Uses first-level and second-level caches without contacting the Now LLM Service. If no match is found, no answer is returned. Dynamic Translation bypasses caches and returns no answer.
      • online: Uses both caches and the Now LLM Service. If no cache match, queries are sent to the Now LLM Service, and generated answers populate both caches. Dynamic Translation bypasses caches and queries the Now LLM Service.
      This property is not present by default and requires manual addition to override the default off value.
    • snaisassist.ullmapitimeout: Defines the maximum wait time in seconds (default 120) for the Now LLM Service to generate Q&A answers, allowing control over response latency. This property is not present by default and must be added if customization is needed.
    • snaisassist.uquestionregex: A case-insensitive Java regular expression that restricts which search queries are eligible for Now Assist Q&A answer generation. For example, a pattern beginning with typical question words limits eligibility accordingly. If undefined, all searches in supported applications are eligible. This property is present in the System Property table by default.
    • snaisassist.usanitizehtml: Option to remove HTML tags from knowledge article text before sending it to the Now LLM Service, enhancing answer generation quality. Default is false. This property must be added manually if needed.

    Practical Implications for ServiceNow Customers

    • By configuring semanticcachemode, customers can balance between answer freshness and system performance based on their operational preferences, choosing whether to rely on cached answers or involve the Now LLM Service.
    • The ullmapitimeout property helps manage timeouts and service responsiveness, ensuring users receive answers within acceptable timeframes.
    • Using the uquestionregex property allows customers to refine which queries trigger AI-generated answers, improving relevance and reducing unnecessary processing.
    • Enabling usanitizehtml can improve the quality of AI-generated answers by cleaning knowledge article inputs before processing.
    • Since some properties are not present by default, customers must add them manually in the System Property table to customize behavior.

    System properties that you can use to modify behavior for Now Assist in AI Search Genius Results.

    These properties are available for Now Assist in AI Search.
    Note:
    To open the System Property [sys_properties] table's list view, select All, enter sys_properties.list in the Filter field, and press Enter.
    Table 1. Properties for Now Assist in AI Search
    Property Description
    sn_ais_assist.semantic_cache_mode Operational mode for the Now Assist Q&A Genius Results caches. Use this mode to control how AI Search uses the caches and the Now LLM Service when looking for Now Assist Q&A Genius Result answers.
    For details about how AI Search caches Now Assist Q&A Genius Result answers, see Caching for Now Assist Q&A Genius Results.
    • Type: string
    • Default value: off
    • Supported values:
      • off: Use the first-level cache and the Now LLM Service to find Now Assist Q&A Genius Result answers.

        AI Search looks in the first-level cache for Now Assist Q&A Genius Result answers that exactly match your search query and knowledge article result. If it doesn't find a matching answer, it sends your query and Knowledge article sys_id to the Now LLM Service for answer generation.

        Now Assist Q&A Genius Result answers generated by the Now LLM Service populate the first-level cache.

        When using Dynamic Translation, AI Search bypasses the caches and queries the Now LLM Service to generate an answer for the Now Assist Q&A Genius Result.

      • offline: Use the first-level and second-level caches to find Now Assist Q&A Genius Result answers. Don't submit queries to the Now LLM Service.

        AI Search looks in the first-level cache for Now Assist Q&A Genius Result answers that exactly match your search query and knowledge article result. If it doesn't find a matching answer, it uses semantic vector search to look for answers that match the meaning of your query in the second-level cache. If no cached answers match your query and knowledge article result, AI Search returns no answer for the Now Assist Q&A Genius Result.

        Now Assist Q&A Genius Result answers found in the second-level cache populate the first-level cache.

        When using Dynamic Translation, AI Search bypasses the caches and returns no answer for the Now Assist Q&A Genius Result.

      • online: Use the first-level and second-level caches and the Now LLM Service to find Now Assist Q&A Genius Result answers.

        AI Search looks in the first-level cache for Now Assist Q&A Genius Result answers that exactly match your search query and knowledge article result. If it doesn't find a matching answer, it uses semantic vector search to look for answers that match the meaning of your query in the second-level cache. If no cached answers match your query and knowledge article result, AI Search submits the query and article sys_id to the Now LLM Service for answer generation.

        Now Assist Q&A Genius Result answers generated by the Now LLM Service populate the first-level and second-level caches.

        When using Dynamic Translation, AI Search bypasses the caches and queries the Now LLM Service to generate an answer for the Now Assist Q&A Genius Result.

    • Location: Not present in the System Property [sys_properties] table by default. To override the default value, add this property by following the steps in Add a system property.
    sn_ais_assist.u_llm_api_timeout Maximum time in seconds to wait for Now Assist Q&A answer generation results from the Now LLM Service.
    • Type: integer
    • Default value: 120
    • Location: Not present in the System Property [sys_properties] table by default. To override the default value, add this property by following the steps in Add a system property.
    sn_ais_assist.u_question_regex Case-insensitive Java regular expression pattern that defines searches eligible for Now Assist Q&A answer generation. As an example, the pattern ^(what|where|when|why|who|whom|which|how)\b restricts eligibility to search queries that begin with one of the specified keywords.

    When this system property has a value defined, only searches in supported applications that match the specified pattern are eligible for Now Assist Q&A answer generation.

    When no value is defined, all searches in supported applications are eligible for Now Assist Q&A answer generation.

    • Type: string
    • Default value: none
    • Location: System Property [sys_properties] table

    To learn about Java regular expression pattern syntax, see the Javadoc for the java.regex.util.Pattern class.

    sn_ais_assist.u_sanitize_html Option to remove HTML tags from knowledge article text before sending to the Now LLM Service for Now Assist Q&A answer generation.
    • Type: true | false
    • Default value: false
    • Location: Not present in the System Property [sys_properties] table by default. To override the default value, add this property by following the steps in Add a system property.