{"revision":"c10276e953456835cdbb1f3a60d58ae1980be353","document":{"id":24278,"path":"intelligent-experiences/plat-not-intent-identification-agent-ai-agent.md","title":"Intent identification AI agent","bundle":null,"doc_type":null,"release":"australia","body":"\n# Intent identification AI agent\n\nThis AI agent analyzes and identifies the input email body intent. A list of admin-configured intents are compared with the input email body for a potential match.\n\n## Workflow\n\nThe agent fetches the email body using a given email sys\\_id.\n\n1.  Fetch the email body and execution context for the intent analysis and continue with the next step.\n2.  Check for malicious attempts, such as prompt injections.\n3.  Analyze the input to determine the overall thread context and the latest sender’s goal, which can represent either an actionable request, expression, statement, or interest. The email body can include a conversation or email thread involving multiple participants.\n4.  Perform intent analysis to evaluate whether a given input utterance semantically matches an intent from an admin-configured list.\n\n<table><thead><tr><th>\n\nField\n\n</th><th>\n\nDescription\n\n</th></tr></thead><tbody><tr><td>\n\nAllow third party to access this AI agent\n\n</td><td>\n\nWhen 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.\n\n</td></tr><tr><td>\n\nAllow AI specialists to access this AI agent\n\n</td><td>\n\nWhen 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.\n\n</td></tr><tr><td>\n\nManage long-term memory\n\n</td><td>\n\nWhen 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://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/na-aia-reference.md).\n\n</td></tr><tr><td>\n\nTools\n\n</td><td>\n\n-   **Scripts**\n\nContext Fetcher\n\nIntent Fetcher\n\n\n</td></tr><tr><td>\n\nAllowed user roles The specific user roles that can access this AI agent.\n\n</td><td>\n\nsnc\\_internal, snc\\_external\n\n</td></tr><tr><td>\n\nData access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take.\n\n</td><td>\n\nintent\\_identification\\_ai\\_user, sn\\_notif\\_agents.notification\\_ai\\_reader\n\n</td></tr><tr><td>\n\nTriggers\n\n</td><td>\n\nOptional. None defined by default. An admin can specify triggers if desired. For more information, see [Add a trigger to an AI agent](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/add-trigger-aia.md).\n\n</td></tr><tr><td>\n\nChannels\n\n</td><td>\n\nConfigure an assistant for Virtual Agent or ServiceNow Otto panel using [Assistant Designer](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/conversational-interfaces/configure-now-assist-va.md).\n\n</td></tr><tr><td>\n\nUsed in agentic workflows\n\n</td><td>\n\nIntent to Action\n\n</td></tr></tbody>\n</table>Learn more about Notifications in [Notifications](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/platform-administration/notifications.md).\n\n**Parent Topic:**[Notifications AI agents](https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/australia/markdown/australia/intelligent-experiences/platform-notifications-ai-agents-overview.md)\n\n"}}