--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Exploring Generative AI Controller # Exploring Generative AI Controller {#ariaid-title1} Release version: Brazil Updated September 10, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Learn how Generative AI Controller works as the control and visibility layer for all generative AI requests across your ServiceNow applications, what it controls, and how it integrates with third-party LLM providers. ## Generative AI Controller overview {#exploring-generative-ai-controller__section_lbv_r4k_wwb} Every AI request from generative AI features, AI agents, and custom skills passes through Generative AI Controller before reaching your LLM provider. The controller enforces governance policies, applies privacy controls, and records activity for monitoring and troubleshooting. Generative AI Controller integrates with external LLMs, including ones by OpenAI, Azure OpenAI, Google Cloud (AI Studio and Vertex), IBM watsonx, and Amazon Bedrock. Note: Depending on your license, you will have access to certain application features, generative AI skills, agentic workflows, and AI agents. For more information, see [ServiceNow product tiers](https://www.servicenow.com/docs/QCGkmpN33vownhxo8L1ecg "ServiceNow structures its products and packages in three tiers — Foundation, Advanced, and Prime. Each tier incorporates AI and builds progressively on the previous one with additional AI capabilities, agents, and governance tools."). ## Generative AI Controller governance and controls {#exploring-generative-ai-controller__section_xcc_wkd_qjc} Generative AI Controller manages the following controls for generative AI activity across your ServiceNow applications: Logging : Records all generative AI requests and responses for debugging and auditing. Rate limiting : Restricts the number of requests to an LLM provider within a given time frame. Data privacy : Masks personally identifiable information in prompts before they are sent to an LLM. External LLM connectivity : Connects your Now Assist applications to a third-party LLM provider. Guardian guardrails : Applies content and safety policies to generative AI requests. ## Generative AI Controller benefits {#exploring-generative-ai-controller__section_pbv_r4k_wwb} {#exploring-generative-ai-controller__table_qbv_r4k_wwb__entry__2} | Benefit | Feature | |-|-| | Integrate with third-party AI service providers to customize your AI experience | OpenAI, Azure OpenAI, Google AI, IBM watsonx, Amazon Bedrock | | Govern and monitor all generative AI activity in your ServiceNow applications | Data Privacy, [Guardian guardrails](https://www.servicenow.com/docs/hdgQA7KQb7lcA0lXFO9xzg "AI Guardian is built on the ServiceNow Small Language Model (SLM) and monitors generative AI interactions to detect offensive content, prompt injection attacks, and sensitive topics."), [Rate limiting](https://www.servicenow.com/docs/rbNugrr_wAxC02LHw0KJCA "Configure rate limiting to control the traffic flow to the one_extend request by restricting the number of requests that can be made within a certain time frame."), and Activity logging | | Use your own API keys for AI processing | [Bring your own key for third-party AI provider integration](https://www.servicenow.com/docs/vlgawOL71fSDc~7w_NWajg "The bring-your-own-key (BYOK) feature enables you to use your own API credentials from supported cloud AI providers, such as Azure OpenAI, Amazon Bedrock, and Google Gemini, to run generative AI skills and AI agents.") | [ ] {#exploring-generative-ai-controller__table_qbv_r4k_wwb} ## Get started with Generative AI Controller * The Generative AI Controller application is installed automatically with any [ServiceNow AI application](https://www.servicenow.com/docs/DXIiljicT2y3QrwyNpgJWQ "ServiceNow Otto uses generative AI to enhance user productivity and efficiency through conversation and proactive experiences. Starting with the Brazil release, AI Admin Hub is being prepared for deprecation and replacement by AI Admin Center."). * Sign up and create an account with a generative AI provider. * To sign up with OpenAI, go to their [official platform website](https://platform.openai.com/). * To get started with Azure OpenAI, go to their [documentation](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/quickstart). * To start using AI Studio with Gemini API, go to the [AI Studio homepage](https://ai.google.dev/aistudio/). * To use Vertex AI on the Google Cloud, go to the [Vertex AI homepage](https://cloud.google.com/vertex-ai). * To get started with IBM watsonx, go to [Getting started with IBM watsonx as a Service](https://www.ibm.com/docs/en/watsonx/saas?topic=getting-started). * To get started with Amazon Bedrock, [set up an IAM user with the correct permissions](https://repost.aws/knowledge-center/create-access-key) and then [explore the Converse API](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html). * [Configure credentials for your preferred AI service provider](https://www.servicenow.com/docs/2KZJeFz1lI07qwrRDrRIuQ "Configure the credentials and connections for your preferred generative AI service provider to integrate third-party generative AI on the ServiceNow AI Platform.") for the Generative AI Controller capabilities. * Activate [AI assets](https://www.servicenow.com/docs/tHKlq54FkdU2RwLiTObdMQ "Generative AI skills use large language models to enterprise data to complete tasks within workflows. You can activate and configure skills, or build custom skills for your organization.") for your workflows and configure governance settings such as data privacy, [guardrails](https://www.servicenow.com/docs/hdgQA7KQb7lcA0lXFO9xzg "AI Guardian is built on the ServiceNow Small Language Model (SLM) and monitors generative AI interactions to detect offensive content, prompt injection attacks, and sensitive topics."), and [rate limiting](https://www.servicenow.com/docs/rbNugrr_wAxC02LHw0KJCA "Configure rate limiting to control the traffic flow to the one_extend request by restricting the number of requests that can be made within a certain time frame."). * Build custom skills for your organization's unique requirements using [AI Skill Kit](https://www.servicenow.com/docs/rXlzROHfVxB_PPntyEiYyA "Use ServiceNow AI Skill Kit to create and publish custom prompts and skills for ServiceNow Otto. Creating custom skills and prompts gives you greater flexibility with ServiceNow Otto's generative AI capabilities."). * [Monitor generative AI activity](https://www.servicenow.com/docs/mbJrGtJCFFVUnZ2t~6kvQA "Generative AI Controller use dedicated tables to log AI activities and track AI usage across the platform.") through logs for troubleshooting and compliance.