--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Reference for Generative AI Controller # Reference for Generative AI Controller {#ariaid-title1} Release version: Australia Updated March 12, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 Reference for Generative AI Controller The Generative AI Controller in ServiceNow Australia release enables routing, governance, and monitoring of generative AI requests across Now Assist applications. It consists of multiple specialized tables and configuration properties designed to manage AI capabilities, track usage, log interactions, and ensure compliance with provider policies. Show full answer Show less ## Key Features * **Capability Management:** Tables like `sysoneextendcapability` and `sysoneextendcapabilitydefinition` define AI capabilities and their input/output variables, which cannot be altered once active to maintain system integrity. * **Builder Configuration:** `sysoneextendbuilderconfig` and `sysoneextendbuildercapability` link AI capabilities with providers and components for flexible AI model integration. * **Usage Tracking:** The `sysoneextendusage` table logs every instance where a generative AI capability is utilized, helping administrators monitor AI adoption and performance. * **Logging and Metrics:** Detailed logs of AI prompts, responses, edits, and errors are stored in `sysgenerativeailog` and `sysgenailogmetadata`, retained for 180 days with data protection for sensitive HR content. Performance metrics such as edit scores and guardrail activities are captured in `sysgenerativeaimetric` to evaluate AI response quality. * **Model Version Mapping:** The `sysgenaimodelversionmapping` table maintains relationships between AI model versions, providers, and configuration details for clear model management. * **Configurable System Properties:** Properties control behaviors such as default AI providers, user messages on failed AI queries or moderation rejections, logging enablement, token buffering for API calls, and domain-specific usage entitlements. ## Practical Benefits for ServiceNow Customers * **Governance and Compliance:** Enables controlled and compliant use of generative AI across ServiceNow applications, including data protection and moderation enforcement consistent with provider policies. * **Transparency and Monitoring:** Provides extensive logging and metrics to help administrators audit AI interactions, optimize model performance, and troubleshoot issues effectively. * **Flexibility and Control:** Allows configuration of AI capabilities, providers, and usage policies to fit organizational needs and ensure appropriate AI application. * **Data Security:** Sensitive logs, particularly HR data, are access-restricted, supporting compliance with privacy requirements. ## What Customers Can Expect ServiceNow customers leveraging the Generative AI Controller can expect a robust framework to integrate multiple generative AI models securely and in compliance with provider terms. They gain detailed visibility into AI usage and performance, with tools to configure capabilities and manage AI-driven workflows responsibly. The system's built-in safeguards and logging ensure AI-driven interactions are transparent, moderated, and auditable, supporting enterprise governance standards. Reference topics provide information about Generative AI Controller tables, and properties. ## Tables installed {#reference-for-generative-ai-controller__entry__3} | Name | Table | Description | |-|-|-| | OneExtend Capability | sys_one_extend_capability | Generative AI Controller capabilities for routing and governing generative AI requests for your ServiceNow AI applications. | | OneExtend Capability Definition | sys_one_extend_capability_definition | Attribute configuration for input and output variables for for generative AI capability definitions. | | OneExtend Capability Definition Attribute | sys_one_extend_definition_attribute | Input and output variables for for generative AI capability definitions. Variable names can't be changed if the capability is active and used on the instance. You can check whether a capability is used by going to the OneExtend Usages table. | | OneExtend Builder Config | sys_one_extend_builder_config | Determines which capability and provider is related to each generative AI builder component. | | OneExtend Builder Capability | sys_one_extend_builder_capability | Definitions for a capacity and its provider for builder components. | | OneExtend Usage | sys_one_extend_usage | Each usage of a generative AI capability across your Now Assist applications. | | Gen AI Log Metadata | sys_gen_ai_log_metadata | Log data about requests to the LLMs, including information about definition, errors, user, and feedback provided. AI-generated content can be tracked for a duration beyond six months. You can export historical data by writing a script to copy it into a different table without deleting the information. | | Generative AI Metric | sys_generative_ai_metric | Logs various metrics to help evaluate the performance and accuracy of LLM responses, such as edit score, edit distance, guardrail activity, and details about the LLM model used. | | Gen AI Model Version Mapping | sys_gen_ai_model_version_mapping | Maintains mappings between AI model versions, their providers, and configuration details, providing a clear understanding of how source models map to target models. It also includes associated metadata, such as skill type, model type, resource associations, and provider information. | | Generative AI Log | sys_generative_ai_log | Logs Generative AI prompts, responses, and edited responses to debug LLM calls. Log records are retained for 180 days. HR-related logs are restricted to HR Administrators, ensuring sensitive information remains protected. For more information, see [Generative AI Controller tables](https://www.servicenow.com/docs/Z7C6M46Lj9RIdgR5R2jVgw "Generative AI Controller use dedicated tables to log AI activities and track AI usage across the platform."). | [ ] ## Properties {#reference-for-generative-ai-controller__entry__35} | Property | Description | |-|-| | com.sn.generative.ai.provider | Default provider when capability definition has no default. Type: choice list No default value | | com.sn.generative.ai.ais.message | Message that is displayed when AI Search fails to find an answer to a query. Type: string Default value: No answer found. | | com.sn.generative.ai.log_prompt | Prompt that determines whether generative AI API calls are logged. Type: true \| false Default value: true | | com.sn.generative.ai.moderation.message | Message that is displayed if the OpenAI or Azure OpenAI moderation tools identify the content that goes against their terms of service. Type: string Default value: The response cannot be displayed as it's deemed inappropriate by OpenAI. | | com.glide.one.extend.token.buffer | Buffer that checks the request for the number of tokens before a OneExtend capability is executed. The maximum allowed request tokens are calculated based on the maximum tokens that are permitted by the AI provider's API minus the response token and buffer value that is specified in this system property. Type: integer Default value: 250 | | domain.llm.usage.entitled | Determines whether to use the LLM for a specific domain to process data or restrict its use. Type: true \| false Default value: true | [Table 1. Generative AI Controller properties] ## External links {#reference-for-generative-ai-controller__entry__50} | Provider | Data policy | Usage policy | |-|-|-| | Amazon Bedrock | [Data protection](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html) | [AWS Service Terms](https://aws.amazon.com/service-terms/) | | Google Cloud | [Google Cloud Platform Terms of Service](https://cloud.google.com/terms) | [Google Cloud Platform Terms of Service](https://cloud.google.com/terms) | | IBM watsonx | [Keeping your data secure and compliant](https://www.ibm.com/docs/en/watsonx/saas?topic=security-keeping-your-data-secure-compliant) | [Foundation model terms of use in watsonx.ai](https://www.ibm.com/docs/en/watsonx/saas?topic=solutions-terms-use) | | Microsoft Azure OpenAI | [Data, privacy, and security for Azure OpenAI Service](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy) | [Code of conduct for Azure OpenAI Service](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/code-of-conduct) | | OpenAI | [API data usage policies](https://openai.com/policies/api-data-usage-policies) | [Usage policies](https://openai.com/policies/usage-policies) | [ ]