--- 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 --- # Friendly fraud AI agent # Friendly fraud AI agent {#ariaid-title1} Release version: Australia Updated September 28, 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 Friendly fraud AI agent The Friendly fraud AI agent assists human agents in resolving friendly fraud disputes efficiently and compliantly. It analyzes the dispute case details, references relevant knowledge articles and historical cases, and recommends an appropriate resolution action. The agent supports decision-making by providing real-time context and examples of similar past overrides, ensuring accuracy and adherence to published guidance. Show full answer Show less ## Key Features * **Case Analysis:** Retrieves detailed information on the fraud dispute, including case, transaction, customer, and amount data. * **Recommendation Engine:** Uses knowledge articles and past case data to suggest a resolution action and reasoning. * **Historical Insights:** Surfaces up to two similar past cases where recommendations were overridden to inform the agent's decision. * **Decision Support:** Presents recommended actions (decline dispute, issue credit/write-off, or proceed with dispute) and requests the agent's final resolution choice, prompting for an explanation if it significantly differs from the recommendation. * **Communication Drafting:** Automatically drafts rejection communication when disputes are declined and guides next steps. * **Task Updates:** Records recommended and final resolution actions on the task, with confirmation messaging upon completion. * **Configurable Access Controls:** Allows enabling/disabling third-party AI and AI specialist access, management of long-term memory for interaction context, and role-based permissions for users and data access. * **Integration:** Invoked by the Evaluate Friendly Fraud workflow and enabled for the ServiceNow Otto panel to streamline agent workflows. ## Practical Benefits for ServiceNow Customers * Improves resolution accuracy and compliance by grounding decisions in documented guidance and historical precedent. * Reduces manual research time by automatically surfacing relevant case and knowledge information. * Supports consistent dispute handling by prompting agents to explain deviations from AI recommendations. * Enhances agent productivity through automated communication drafting and streamlined task updates. * Offers flexible configuration to control who can access and configure the AI agent based on organizational roles. The agent guides the human agent through resolving a friendly fraud dispute. It recommends an action based on published guidance and similar past overrides, then supports the agent's decision with real-time context to keep resolutions accurate and compliant. ## Workflow {#fso-friendly-fraud-ai-agent__cmrraimyucgd} The agent helps the human agent decide how to resolve a friendly fraud dispute. 1. Look up the friendly fraud task and display its case, transaction, customer, and dispute amount details. 2. Retrieve the knowledge article on resolving friendly fraud disputes and use it to determine a recommended action and reason. 3. Record the recommended action and reason on the task. 4. Check historical friendly fraud cases where the recommendation was overridden and surface up to two similar past examples. 5. Present the recommendation, its reasoning, and any historical insight, then ask the agent to choose a resolution action --- decline the dispute, issue a credit and write-off, or proceed with the dispute. 6. If the agent's choice differs significantly from the recommendation, ask them to explain why. 7. Draft rejection communication when the agent declines the dispute, and let the agent know what to do next. 8. Update the task with the resolution taken and confirm with a closing message. {#fso-friendly-fraud-ai-agent__ol_efs_dpr_vkp} {#fso-friendly-fraud-ai-agent__cmrraimyucgd__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 | Flow Actions : Check if friendly fraud task valid for further processing : Get recently closed friendly fraud tasks with overrides : Update friendly fraud recommended action and recommended action reason : Update friendly fraud resolution action taken Subflows : Get friendly fraud task details Search retrievals : Get knowledge article | | Allowed user roles The specific user roles that can access this AI agent. | * sn_bom_credit_card.dispute_agent * sn_bom_credit_card.dispute_agent_connector | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | * sn_bom_credit_card.dispute_agent * sn_bom_credit_card.dispute_agent_connector | | Triggers | No triggers are defined in this AI agent; it is invoked by the Evaluate Friendly Fraud workflow. | | Channels | Enable the AI agent for the ServiceNow Otto panel. | | Used in agentic workflows | Help resolve friendly fraud disputes | [Table 1. Configuration]