--- 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 --- # AI insight AI agent # AI insight 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 AI insight AI agent The AI insight AI agent is designed to assist ServiceNow customers in exploring and understanding customer engagement or account data through conversational interactions. It provides detailed insights such as health scores, adoption scores, value realization, risks, contract value, and forecasts future scores with recommended improvements. This agent supports informed decision-making by delivering accurate, date-stamped data and actionable suggestions based on historical trends and peer benchmarks. Show full answer Show less ## How It Works * The agent initiates conversations by greeting users and listing available topics including health score, adoption scores, value realization, risks, objectives, and contract value. * Users ask questions, and the agent retrieves matching data from the customer success knowledge graph or relevant records, strictly using existing data without guessing missing values. * It can forecast upcoming scores and recommend improvements when prompted, leveraging historical data and peer trends. * The agent encourages further engagement by suggesting follow-up questions or next steps, continuing the conversational cycle until the user ends it. ## Configuration and Access Control * **Third-party Access:** Administrators can enable or disable third-party AI agents' access to this agent. This is off by default. * **AI Specialist Access:** When enabled, AI specialists gain additional configuration options to map inputs and outputs, allowing deeper customization. This is off by default. * **Long-term Memory:** Optionally, the agent can retain context from all previous user interactions to enhance responses. This is disabled by default. * **User Roles and Data Access:** Access to the agent and its data is controlled through specific user roles. For example, the data access role 'snacctlc.customersuccessagent' governs what data the agent can retrieve and act upon. * **Integration with Channels:** The agent can be configured for use in Virtual Agent or ServiceNow Otto panel via Assistant Designer, supporting conversational workflows. ## Practical Benefits for ServiceNow Customers * Enables quick, conversational access to comprehensive customer engagement insights, enhancing customer success management. * Helps forecast key metrics and identify risks or opportunities, supporting proactive account management. * Supports customization and controlled access to ensure compliance and tailored user experiences. * Facilitates ongoing dialogue with the data, allowing users to explore multiple facets of customer engagements efficiently. The agent answers questions about a customer engagement or account. It reports health scores, adoption scores, value realization, risks, contract value, and other engagement data, and it forecasts scores and recommends improvements. ## Workflow {#tmt-ai-insight-ai-agent__fuzlmujffwhe} The agent helps the user explore engagement or account data through a conversation. 1. Greet the user and list the topics the agent can cover, such as health score, adoption scores, value realization, risks, objectives, and contract value. 2. Wait for the user to ask a question. 3. Collect the data that matches the question topic, or search the customer success knowledge graph for record-level details such as risks, objectives, outcomes, and notes. 4. Answer from the retrieved data only. The agent pairs each score with its date or period and does not guess missing values. 5. Forecast the next score or recommend improvements when the user asks, based on historical values and peer trends. 6. Suggest specific follow-up questions or next actions, and repeat the cycle until the user ends the conversation. {#tmt-ai-insight-ai-agent__ol_xef_dsm_dyk} {#tmt-ai-insight-ai-agent__fuzlmujffwhe__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 : Collect Insight Context Data Tool : Customer Success KG Tag | | Allowed user roles The specific user roles that can access this AI agent. | Not defined. | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | sn_acct_lc.customer_success_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 | Not applicable. | [Table 1. Configuration] Learn more about Customer Success Management at [Customer Success Management](https://www.servicenow.com/docs/access?context=account-lifecycle-events-landing&version=australia&pubname=australia-acct-lifecycle-events&ft:locale=en-US).