--- 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 --- # Service map AI agent # Service map AI agent {#ariaid-title1} Release version: Australia Updated August 14, 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 Service map AI agent The Service map AI agent automates the creation of service maps by processing machine learning (ML)-based and tag-based candidates. Running every 15 minutes after activation, it identifies candidates not processed in the last 90 days, analyzes their potential as business services, and generates non-operational service maps for administrative review. This agent requires no manual input during its runs and records outcomes for transparency and tracking. Show full answer Show less ## Key Features * **Automatic Scheduling:** Runs every 15 minutes post-activation without needing user intervention. * **Candidate Processing:** Handles up to 100 candidates per type by default, analyzing and mapping those representing business services. * **Non-operational Maps:** Created service maps are initially non-operational to allow administrators to review before activation. * **Error Handling and Retries:** Temporarily failed candidates (e.g., due to AI concurrency limits) are retried at the next run; other failures are not retried automatically. * **Configurable Processing Limits:** Limits for ML-based and tag-based candidates can be increased by adjusting system properties and reactivating the agent, with consideration for AI resource consumption. * **Access Controls:** Permissions can be set to allow third-party AI agents and AI specialists to use this AI agent, with additional configuration options available for specialists. * **Long-term Memory Management:** Optionally enables use of previous interactions as context for large language models (LLM), configurable via system properties. * **Scripts and Tools:** Includes specific scripts for managing ML-based and tag-based candidate data retrieval, analysis, and service topology creation. * **Role-based Security:** Access is restricted to users with designated roles such as servicemappingaiuser, cmdbread, itomadmin, and others. * **Integration Options:** Can be configured with Virtual Agent or ServiceNow Otto panel assistants through Assistant Designer, though it is not used in agentic workflows by default. ## Practical Application for ServiceNow Customers ServiceNow customers can leverage this AI agent to efficiently and continually generate service maps based on up-to-date candidate data without manual processing. Administrators retain control through reviewable, non-operational maps and can tune processing limits to balance AI resource use. The agent's configurable access controls and integration with Virtual Agent enable tailored deployment in enterprise environments, enhancing service mapping accuracy and operational readiness in IT Operations Management. This AI agent runs automatically on a schedule and creates service maps from ML-based and tag-based candidates. ## Workflow {#itom-service-map-creation-ai-specialist-ai-agent__zsmdlwierhjt} After you activate the agent from the Service Mapping home page, the agent runs automatically every 15 minutes. No user input is required for each candidate. On each run, the agent does the following: 1. Finds the machine learning (ML) candidates and tag-based candidates that it hasn't processed in the last 90 days. 2. Analyzes each candidate to determine whether it represents a business service. 3. Creates a service map for each candidate that represents a business service. The service maps are non-operational by default so that an administrator can review them before activation. 4. Records the outcome for each candidate. To see each run, open AI Activity in the Service Mapping list navigation. {#itom-service-map-creation-ai-specialist-ai-agent__ol_sm_agent_workflow} ## Retries for failed candidates {#itom-service-map-creation-ai-specialist-ai-agent__sm-processing-rules} * If the platform returns a temporary error, such as reaching the limit of concurrent AI agent plans, the candidate is processed at the next run. * If an invocation fails for any other reason, the candidate isn't retried automatically. ## Processing limit {#itom-service-map-creation-ai-specialist-ai-agent__sm-processing-limit} By default, the agent can process 100 candidates for each candidate type. When the agent reaches the limit for a candidate type, it stops processing that candidate type and its status is set to Paused. The agent stays stopped until you raise the limit. To raise the limit and reactivate the agent, first configure the following properties: 1. For ML-based candidates: sn_sm_gen_ai.agent_invocation_limit.ServiceMapCreationAISpecialist 2. For tag-based candidates: sn_sm_gen_ai.agent_invocation_limit.TagBasedServiceMapCreationAISpecialist You can change the value based on your available AI resources. After raising the limit, reactivate the agent in the Service Mapping workspace. Note: Raising the limit increases AI resource consumption, because the agent processes more candidates. ## AI agent configuration {#itom-service-map-creation-ai-specialist-ai-agent__sm-agent-configuration} {#itom-service-map-creation-ai-specialist-ai-agent__sm-agent-configuration__entry__2} | Field | Description | |-|-| | Allow third party to access this AI agent | When enabled, third-party AI agents can use this agent. This value is off (false) by default. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the External discoverable field. | | Allow AI specialists to access this AI agent | When enabled, AI specialists can use this agent. This value is off (false) by default. When set to true, more configuration options for tools become available so that an AI specialist can map inputs and response templates to tool outputs. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the Specialist enabled field. | | Manage long-term memory | When enabled, all previous user interactions are used as context for the LLM. This value is off (false) by default. This setting is defined by the sn_aia.ltm.enable_long_term_memory system property. For more information, see [ServiceNow Otto AI agents reference](https://www.servicenow.com/docs/MUqSU8rHp3ao~q3QEWgHkA "Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents."). | | Tools | Scripts for ML-based candidates : create_service_topology : Get Candidate Running Processes : Get ML Candidate Full Data : Save Candidate Analysis : save_run_record Scripts for tag-based candidates : create_service_topology : Get Tag Candidate Full Data : Get Tag Candidate Running Processes : Save Candidate Analysis : save_run_record | | Allowed user roles The specific user roles that can access this AI agent. | snc_internal | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | service_mapping_ai_user, cmdb_read, itom_admin, snc_internal, snc_required_script_writer_permission, sn_bm_client.benchmark_data_viewer, sn_itom_license.reader | | Triggers | Optional. None defined by default. An admin can specify triggers if desired. For more information, see [Add a trigger to an AI agent](https://www.servicenow.com/docs/NXqRJBQV_Vw00FEzklcAJw "In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met."). | | Channels | Configure an assistant for Virtual Agent or ServiceNow Otto panel using [Assistant Designer](https://www.servicenow.com/docs/access?context=configure-now-assist-va&version=australia&pubname=australia-conversational-interfaces&ft:locale=en-US). | | Used in agentic workflows | Not applicable. | [Table 1. Configuration] Learn more about IT Operations Management at [IT Operations Management](https://www.servicenow.com/docs/access?context=r_ITOMApplications&version=australia&pubname=australia-it-operations-management&ft:locale=en-US).