--- 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 --- # Rack placement AI agent # Rack placement AI agent {#ariaid-title1} Release version: Australia Updated October 27, 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 Rack placement AI agent The Rack placement AI agent automates the process of allocating data center racks based on the capacity requirements specified in a change request. It validates the request, applies relevant placement policies for the data center, selects suitable racks, and documents the outcome directly on the change request. This agent streamlines rack allocation to ensure that capacity needs are met efficiently and consistently. Show full answer Show less ## Workflow * Retrieves the change request and checks for existing affected configuration items (CIs), prompting the user to continue or exit accordingly. * Validates capacity requirements in the change request. * Retrieves placement policies for the data center and racks; if no policies exist, defaults are applied without user input. * Finds racks that meet the capacity requirements. * Displays the structured request, applied policies, placement results, any issues encountered, and a decision summary explaining rack selections or exclusions. * Records a work note on the change request indicating success or failure of the allocation and moves the request to Design Complete. * Handles failures by notifying the user and logging the failure in the final step; issues writing results back are also treated as failures. ## Configuration and Access * **Third-party access:** Can be enabled to allow external AI agents to utilize this agent; disabled by default. * **AI specialist access:** When enabled, provides additional configuration options for mapping inputs and responses; disabled by default. * **Long-term memory:** Can be enabled to maintain context from previous user interactions for the language model; disabled by default. These settings are managed via specific configuration tables and system properties within ServiceNow, allowing customization based on organizational needs. ## Tools and Roles * **Tools used:** Includes scripts for finalizing allocation, finding rack placement, retrieving change requests, retrieving policies, and validating requests. * **Access roles:** Restricted to users with designated roles such as `snnicore.dcopsagent` and `snnicore.inventoryagent` to ensure appropriate data access and actions. ## Integration and Usage The agent can be integrated with ServiceNow Virtual Agent or the Otto panel via Assistant Designer, supporting agentic workflows such as the Racks Allocation Workflow. It is designed to support Telecommunications Network Inventory processes effectively. This AI agent finds a data center rack allocation that fits the capacity requirements of a change request. It validates the request, applies the placement policies for the data center, and records the outcome on the change request. ## Workflow {#tni-rack-placement-ai-agent__zmduuvksnyjb} The agent helps the user find racks that can accommodate the capacity requirements of a change request. It runs on its own, and the only question it asks is the one about existing affected CIs. 1. Retrieve the change request. If it already has affected CIs, ask the user whether to continue with rack placement or finish without changes. 2. Validate the capacity requirements in the change request. 3. Retrieve the placement policies for the data center and its racks. This step always runs before the racks are found. If no policy exists for the data center, the agent continues with default values and does not ask the user for a policy. 4. Find the racks that can accommodate the requirements. 5. Show the user the structured request, the policy, the placement, any issues writing the results back, and a decision summary that explains why racks were chosen or excluded. 6. Add a work note to the change request that says whether the allocation succeeded or failed and summarizes the outcome, and move the change request to Design Complete. This final step runs on every exit, including early exits. 7. If any step fails, tell the user, and then record the failure in the final step. A placement that has issues writing the results back also counts as a failure. {#tni-rack-placement-ai-agent__ol_ukn_uae_wmn} {#tni-rack-placement-ai-agent__zmduuvksnyjb__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 | Script : finalize_allocation : find_rack_placement : retrieve_change_request : retrieve_policy : validate_change_request | | Allowed user roles The specific user roles that can access this AI agent. | * sn_ni_core.dc_ops_agent * sn_ni_core.inventory_agent | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | * sn_ni_core.dc_ops_agent * sn_ni_core.inventory_agent | | 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 | [Racks Allocation Workflow](https://www.servicenow.com/docs/access?context=servicenow-otto-agentic-workflows&version=australia&pubname=australia-telecom-network-inventory&ft:locale=en-US) | [Table 1. Configuration] Learn more about Telecommunications Network Inventory at [Telecommunications Network Inventory](https://www.servicenow.com/docs/access?context=telecom-network-inventory&version=australia&pubname=australia-telecom-network-inventory&ft:locale=en-US).