--- 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 --- # LEAP Ansible Execution Agent AI agent # LEAP Ansible Execution Agent AI agent {#ariaid-title1} Release version: Australia Updated October 5, 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 LEAP Ansible Execution Agent AI agent The LEAP Ansible Execution Agent is designed to automate incident remediation by running Ansible playbooks associated with each resolution step of an incident. It integrates with the Ansible Automation Platform to launch jobs, prompts users to manually complete any resolution steps without mapped playbooks, and provides status updates on job execution. This agent helps streamline incident management by combining automated and manual actions while tracking progress and results. Show full answer Show less ## Key Features * **Incident Remediation Workflow:** The agent identifies the incident record, logs execution start, retrieves mappings between resolution steps and Ansible jobs, and guides users through both automated and manual steps in sequence. * **User Interaction:** For steps without playbook mappings, users are prompted to complete tasks manually and confirm completion before proceeding. * **Job Management:** For mapped jobs, the agent displays job template details, collects necessary input via a single form, launches the job, reports job IDs and statuses, and waits for user confirmation before moving on. * **Status Reporting:** Provides summaries of processed steps, launched jobs with statuses, manual completions, and failures, and records overall success or failure on the incident record. * **Job Control:** Users can request job status checks, view job outputs, cancel jobs, or relaunch jobs as needed. ## Configuration and Access * **Third-Party and Specialist Access:** Administrators can enable third-party AI agents and AI specialists to use this agent through configuration settings. Enabling AI specialist access unlocks advanced options for input and response template mapping. * **Long-Term Memory:** Optional long-term memory can be enabled to allow the agent to use previous user interactions as context for the large language model (LLM), improving interaction quality over time. * **User Roles:** Access is restricted to users with the `snitomleap.leapansibleagentworker` role, which governs both usage and data access permissions. * **Tools and Protocols:** The agent uses specific tools to retrieve job details, launch jobs, fetch mappings, and record journal entries, facilitating seamless integration with ServiceNow and Ansible Automation Platform. * **Triggers and Channels:** No default triggers are defined, but administrators can add triggers if desired. The agent can be configured for use within Virtual Agent or ServiceNow Otto assistant panels using the Assistant Designer. ## Practical Benefits for ServiceNow Customers By leveraging the LEAP Ansible Execution Agent, customers can automate complex incident resolution steps that involve Ansible playbooks, reduce manual effort, and improve incident resolution speed and accuracy. The agent's ability to manage both automated and manual steps in a guided workflow ensures comprehensive incident remediation. Moreover, its configurable access controls and integration with ServiceNow's AI framework provide flexibility and security aligned with enterprise requirements. The LEAP Ansible Execution agent runs the Ansible playbooks mapped to each resolution step of an incident. It launches jobs through Ansible Automation Platform, prompts the user to complete unmapped steps manually, and reports job status on request. ## Workflow {#leap-leap-ansible-execution-agent-ai-agent__plofspgpddds} The agent helps the user remediate an incident by running the Ansible playbooks mapped to its resolution steps. 1. Identify the incident record and log on the record that execution has started. 2. Retrieve the mapping between the resolution steps and their Ansible jobs, and inform the user if no mapping exists. 3. Work through the resolution steps in order, asking the user to complete any step that has no playbook mapped and to confirm when it's done. 4. For each mapped job, show the user the job template details and collect any required launch inputs in a single form. 5. Launch the job, report the Ansible job ID and its status, and wait for the user to confirm before moving to the next step. 6. Summarize the steps processed, the jobs launched and their status, the manual steps completed, and any failures. 7. Record the overall success or failure status on the incident record. 8. Check job status, show job output, cancel a job, or relaunch a job whenever the user asks. {#leap-leap-ansible-execution-agent-ai-agent__ol_chb_eot_qdr} {#leap-leap-ansible-execution-agent-ai-agent__plofspgpddds__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 | Model Context Protocol : Get Job Details : Job Template Launch Retrieve : Job Templates Retrieve : Launch Job Templates Record Operation : Get LEAP Ansible Mapping Script : Fetch Record SysId and publish Journal entry | | Allowed user roles The specific user roles that can access this AI agent. | sn_itom_leap.leap_ansible_agent_worker | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | sn_itom_leap.leap_ansible_agent_worker | | 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]