Search result disparities between AI Search and Now Assist search features

  • Release version: Zurich
  • Updated July 6, 2026
  • 4 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 Search result disparities between AI Search and Now Assist search features

    ServiceNow’s AI Platform provides multiple search tools—AI Search, Now Assist Genius Results, and Now Assist in Virtual Agent—that may return different answers for the same search query. This variation is expected due to each tool’s distinct search methodology and architecture. Understanding these differences helps you manage user expectations and optimize search configurations across ServiceNow applications.

    Show full answer Show less

    Key Features

    • AI Search: Uses keyword-based search that matches search terms against indexed data. It applies techniques like lemma normalization, synonyms, stop words, and typo correction to refine matches. Results remain fairly consistent unless source data changes or machine learning relevancy adjustments occur.
    • Now Assist Genius Results: Employs a hybrid search combining keyword and semantic vector searches to capture both term matches and search intent. The top matches are compiled into a prompt sent to a large language model (LLM) for answer generation. Because LLMs are non-deterministic, results may vary even for identical searches submitted simultaneously, leading to significant differences from AI Search results.
    • Now Assist in Virtual Agent: Also uses hybrid search but with an agentic AI architecture that handles conversational context differently from Genius Results. It does not rely on a single prompt to the LLM, resulting in varied answers compared to both AI Search and Genius Results. Matching the search configuration between Virtual Agent and portal search helps reduce—but does not eliminate—disparities.

    Practical Implications for ServiceNow Customers

    • Expect differences in search results across ServiceNow’s AI search tools due to their unique architectures and processing methods.
    • Consistent search configurations across tools can reduce some result discrepancies but cannot guarantee identical outcomes, especially when LLMs are involved.
    • When deploying chat assistants or portals, verify search configuration alignment to minimize unexpected variances in user experience.
    • Recognize that AI Search is best for stable, keyword-focused searching, while Now Assist tools provide more dynamic, intent-driven answers but with inherent variability.

    Summary of Search Tool Differences

    Search Tool Search Mode Interaction Type LLM Usage
    AI Search Keyword search Query-based (search field) None
    Now Assist Genius Results Hybrid (keyword + semantic vector) Query-based (search field) Uses LLM with a single prompt for answer generation
    Now Assist in Virtual Agent Hybrid (keyword + semantic vector) Conversation-based (chat) Agentic AI with conversational context, multiple prompts to LLM

    The ServiceNow AI Platform® offers a variety of search tools, which may return different answers for the same or similar searches. This disparity in results is expected. It occurs because each tool uses a different approach and architecture to find results and generate answers that match your search.

    As an example of the same search returning different answers in different search tools, consider these results that might be displayed to a user searching for what is my travel policy:
    Figure 1. Search results from AI Search in Employee Center
    Employee Center portal search results for travel policy search.
    Figure 2. Genius Result answer from Now Assist Multi-Content Response Genius Result configuration
    Now Assist Multi-Content Response Genius Result answer generated for travel policy search.
    Figure 3. Chat answer from Now Assist in Virtual Agent
    Now Assist in Virtual Agent answer returned for travel policy question.

    In this example, each search tool returns a different answer even though the user's search (or question) is the same in all three tools. This is expected behavior, since the search tools all handle searches differently.

    AI Search

    The AI Search engine uses keyword search, meaning that it looks for the best matches for your search terms in its indexed source data. Search features such as lemma and Unicode normalization, synonyms, stop words, and typo handling may modify the set of terms that AI Search considers matches for your search, but the matching is always done on a per-term basis.

    Keyword search should return consistent results for the same search until your source data is updated. Machine learning relevancy can affect the exact order in which your results appear over time, though, so even if your data doesn’t change, your search may not return exactly the same result set today as it did the previous month.

    Now Assist Genius Results

    The Now Assist Genius Result configurations offered in Now Assist in AI Search use a hybrid search mode. This mode blends keyword search with semantic vector search to find results in the AI Search index based on the intention and meaning of your search as well as on the best term matches.

    The most relevant matching results are merged into a prompt that's sent to a large language model (LLM) for answer generation. Because LLMs aren't deterministic, they don't always produce the same output even when given the same input. As a result of the non-deterministic behavior of the LLM, Now Assist Genius Results are likely to return varying results for the same search, even when submitted at the same time.
    Note:
    For more information on how LLMs introduce variations into their results, see Discrepancies when using different AI search tools.

    Between the non-deterministic LLM behavior and the difference in search matching modes, Now Assist Genius Result answers can be expected to vary significantly from results returned by AI Search for the same search terms, even when using the same search configuration in both tools. This variance is expected because the two search tools take such different approaches when finding and generating answers for your search.

    Now Assist in Virtual Agent

    Now Assist in Virtual Agent uses hybrid search to find matching results in the AI Search index, like the Now Assist Genius Result configurations do.

    Unlike those Genius Result configurations, however, Now Assist in Virtual Agent has its own agentic AI back-end architecture for generating responses. This architecture doesn't rely on sending a single prompt to the LLM for answer creation the way the Now Assist Genius Result architecture does.

    Because of this architectural difference, results from Now Assist in Virtual Agent searches can vary from those returned by Now Assist Genius Results, even when processing the same search and using the same search configuration. Similarly, Now Assist in Virtual Agent results may vary from the results returned by AI Search keyword searches.
    Note:
    If you're seeing different results for the same search in Now Assist in Virtual Agent than you are in AI Search and Now Assist Genius Results, it's worth checking that your Now Assist in Virtual Agent chat assistant uses the same search configuration as your portal's search field does. For details on copying an existing search configuration to a chat assistant, see Assign search sources to a chat assistant.

    As previously described, using the same search configuration in the portal and your chat assistant doesn't guarantee that you will see exactly the same search results in Now Assist in Virtual Agent as you see in the portal using AI Search, but it does remove one possible source of difference.

    Summary of differences between search tools

    The following table summarizes some of the key differences between AI Search, Now Assist Genius Results, and Now Assist in Virtual Agent.
    Search tool Search mode Interaction LLM usage
    AI Search Keyword search Query-based (search field) None
    Now Assist Genius Results Hybrid (blend of keyword and semantic vector) search Query-based (search field) Most relevant search results sent to LLM in a single prompt for answer generation
    Now Assist in Virtual Agent Hybrid (blend of keyword and semantic vector) search Conversation-based (chat) Agentic AI which maintains conversational context when submitting prompts to LLM