---
sourceDocument: Australia ServiceNow AI Platform Administration
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/platform-administration
Release :
- australia
ft:locale :
- en-US
ft:publication_title :
- Australia ServiceNow AI Platform Administration
ft:clusterId :
- platadm
bundleId :
- platadm
workflow :
- Platform
---
# ServiceNow Otto for AI Search properties
# ServiceNow Otto for AI Search properties {#ariaid-title1}
Release version: Australia
Updated July 25, 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 ServiceNow Otto for AI Search properties
This document outlines system properties available in ServiceNow Otto for AI Search that allow customers to customize the behavior of Genius Results for Knowledge base articles.
These properties control caching strategies, timeouts, query eligibility, and content sanitization when using the AI-powered search features integrated with the Now LLM Service.
Show full answer Show less
## Key Properties and Their Uses
* **snaisassist.semanticcachemode** : Controls how AI Search uses caching and the Now LLM Service to retrieve Knowledge base articles Genius Results.
* **off**: Uses only a first-level cache and the Now LLM Service for exact matches; bypasses caches when Dynamic Translation is enabled.
* **offline**: Uses first- and second-level caches without contacting the Now LLM Service; returns no answer if caches miss; bypasses caches with Dynamic Translation.
* **online**: Uses caches and the Now LLM Service, falling back to the service if caches miss; caches results from the service; bypasses caches for Dynamic Translation.
This property is not present by default and must be added manually to override the default.
* **snaisassist.ullmapitimeout**: Sets the maximum wait time (in seconds) for answer generation responses from the Now LLM Service, with a default of 120 seconds. Not present by default and requires manual addition to customize.
* **snaisassist.uquestionregex**: Defines a case-insensitive Java regular expression pattern that restricts which search queries are eligible for Q\&A answer generation. For example, limiting to queries starting with interrogatives like "what," "where," "how," etc. By default, all searches are eligible if unset.
* **snaisassist.usanitizehtml**: Option to remove HTML tags from knowledge article text before sending it to the LLM for answer generation. Default is false; this property must be added manually to enable.
## Practical Considerations for ServiceNow Customers
* These properties allow you to tailor AI Search behavior to balance performance, accuracy, and data freshness depending on your organizational needs.
* Proper configuration of caching modes can optimize response times and reduce load on the Now LLM Service.
* Using the question regex pattern helps control which queries trigger AI-generated answers, improving relevance and resource usage.
* Sanitizing HTML content before AI processing can improve answer quality and security.
* Since many properties are not present by default, you will need to manually add them via the System Property \[sysproperties\] table using standard ServiceNow configuration steps.
System properties that you can use to modify behavior for ServiceNow® Otto for AI Search Genius Results.
These properties are available for ServiceNow Otto for AI Search.
Note:
To open the System Property \[sys_properties\] table's list view, select All, enter sys_properties.list in the navigation field, and press Enter.
{#properties-now-assist-ais__table_s4h_h2x_jdc__entry__2}
| Property | Description |
|-|-|
| sn_ais_assist.semantic_cache_mode | Operational mode for the Knowledge base articles Genius Results caches. Use this mode to control how AI Search uses the caches and the Now LLM Service when looking for Knowledge base articles Genius Result answers. For details about how AI Search caches Knowledge base articles Genius Result answers, see [Caching for Knowledge base articles Genius Results](https://www.servicenow.com/docs/livrluJWPEeApIv1yqfa6A#caching-now-assist-q-a-gr "AI Search provides two query-time caches to improve search performance for Knowledge base articles Genius Results. Caching enables AI Search to return previously generated answers without submitting knowledge articles to the Now LLM Service for answer generation."). * Type: string * Default value: off * Supported values: * off: Use the first-level cache and the Now LLM Service to find Knowledge base articles Genius Result answers. AI Search looks in the first-level cache for Knowledge base articles 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. Knowledge base articles 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 Knowledge base articles Genius Result.{#properties-now-assist-ais__dt-cache-interaction-on-online-ph} * offline: Use the first-level and second-level caches to find Knowledge base articles Genius Result answers. Don't submit queries to the Now LLM Service. AI Search looks in the first-level cache for Knowledge base articles 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 Knowledge base articles Genius Result. Knowledge base articles 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 Knowledge base articles Genius Result.{#properties-now-assist-ais__dt-cache-interaction-offline-ph} * online: Use the first-level and second-level caches and the Now LLM Service to find Knowledge base articles Genius Result answers. AI Search looks in the first-level cache for Knowledge base articles 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. Knowledge base articles 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 Knowledge base articles Genius Result. {#properties-now-assist-ais__ul_irj_gqg_jzb} * 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](https://www.servicenow.com/docs/P1YgMM0DTfCJvVsoqOoJ6Q "Add or create a property to control system behavior."). {#properties-now-assist-ais__ul_djh_kkg_jzb} |
| sn_ais_assist.u_llm_api_timeout | Maximum time in seconds to wait for Knowledge base articles Genius Result answer generation results from the LLM. * 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](https://www.servicenow.com/docs/P1YgMM0DTfCJvVsoqOoJ6Q "Add or create a property to control system behavior."). {#properties-now-assist-ais__ul_u4r_cyr_gxb} |
| sn_ais_assist.u_question_regex | Case-insensitive Java regular expression pattern that defines searches eligible for 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 Q\&A answer generation. When no value is defined, all searches in supported applications are eligible for Q\&A answer generation. * Type: string * Default value: none * Location: System Property \[sys_properties\] table {#properties-now-assist-ais__ul_jp5_hgf_zwb} To learn about Java regular expression pattern syntax, see [the Javadoc for the java.regex.util.Pattern class](https://docs.oracle.com/en/java/javase/21/docs/api/java.base/java/util/regex/Pattern.html). |
| sn_ais_assist.u_sanitize_html | Option to remove HTML tags from knowledge article text before sending to the LLM for Knowledge base articles Genius Result 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](https://www.servicenow.com/docs/P1YgMM0DTfCJvVsoqOoJ6Q "Add or create a property to control system behavior."). {#properties-now-assist-ais__ul_fbr_gyr_gxb} |
[Table 1. Properties for ServiceNow Otto for AI Search]
{#properties-now-assist-ais__table_s4h_h2x_jdc}