---
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


---

# Insurance CSR support AI agent

# Insurance CSR support 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 Insurance CSR support AI agent

The Insurance CSR support AI agent is designed to assist customer service representatives (CSRs) during live insurance calls by providing real-time answers.
It leverages typed questions or the latest call transcript to retrieve relevant customer policy, coverage, claim, billing data, or knowledge-base guidance.
This helps CSRs respond quickly and efficiently without the need to switch screens.
Show full answer Show less  

## How It Works

* The agent captures the customer's latest question either from the call transcript or directly typed input by the CSR.
* It classifies the question into categories such as general knowledge, product catalog, or customer-specific records, ensuring it is within scope (policies, coverages, claims, servicing cases, or procedures).
* If the question references earlier selected records ambiguously, the agent requests CSR confirmation to identify the correct record.
* For sub-record questions (e.g., coverages or beneficiaries), it identifies the parent record and asks the CSR to choose if multiple matches exist.
* The agent retrieves customer data, product information, and knowledge-base guidance to generate a relevant answer.
* Answers are presented appropriately as lists, detailed records, sub-record breakdowns, or summaries, with citations of knowledge-base sources when applicable.
* If no relevant information is found, the CSR is informed, and the agent offers to process the next customer request.

## Configuration and Access

* **Third-party Access:** Can be enabled to allow external AI agents to use this AI agent (default is off).
* **AI Specialist Access:** Enables AI specialists to configure inputs, response templates, and tool mappings (default is off).
* **Long-term Memory:** When enabled, the agent uses all previous user interactions as context for improved responses (default is off).

These settings are managed via system properties and the AI Agent configuration table.

## Tools and Roles

* The agent uses scripts, conversation transcript readers, subflows, and insurance data lookup tools to deliver answers.
* Access is restricted to users with specific roles: `sninscsr.claimsagent` and `sninscsr.servicingagent`.
* Data access is similarly restricted by these identity roles to ensure appropriate data security and privacy.

## Integration and Usage

The AI agent can be configured as an assistant within the Virtual Agent or ServiceNow Otto panel using the Assistant Designer, facilitating seamless CSR workflows during insurance customer interactions.  
The agent gives a customer service representative (CSR) real-time answers during a live insurance call, either from a typed question or from the latest call transcript, retrieving the customer's policy, coverage, claim, and
billing data or knowledge-base guidance so the CSR can respond quickly without switching screens.

## Workflow {#fso-insurance-csr-support-ai-agent__jvkumezgnnrf}

The agent helps the CSR answer a customer's insurance question during a live call, whether typed directly or picked up from the call transcript.

1. When the CSR selects Get customer request, read the latest call transcript to pick up the customer's most recent question; otherwise take the CSR's typed question directly.
2. Classify the question as a general knowledge question, a product-catalog question, or a question about the customer's own records, and confirm it's within scope --- insurance policies, coverages, claims, servicing cases, or procedures.
3. If the question refers to a record picked from an earlier list, resolve which record it means, asking the CSR to confirm when it's ambiguous.
4. If the question asks about a sub-record like coverages or beneficiaries without naming the parent policy or claim, first look up the matching parent records and ask the CSR which one to use.
5. Look up the customer's data, relevant product information, and knowledge-base guidance as needed to answer the question.
6. Present the results --- as a list, a single record's details, a sub-record breakdown, or a short summary, depending on what was asked --- citing the knowledge-base source when guidance is included.
7. Let the CSR know when nothing was found, then offer to pull the next customer request and wait for the next question.
{#fso-insurance-csr-support-ai-agent__ol_ncf_vxv_vyy}  
{#fso-insurance-csr-support-ai-agent__jvkumezgnnrf__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 | Scripts :   Conversation Transcript Reader Subflows :   Insurance Data Lookup |
| Allowed user roles The specific user roles that can access this AI agent. | * sn_ins_csr.claims_agent * sn_ins_csr.servicing_agent {#fso-insurance-csr-support-ai-agent__ul_jyw_phw_skc} |
| Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | * sn_ins_csr.claims_agent * sn_ins_csr.servicing_agent {#fso-insurance-csr-support-ai-agent__ul_rcs_qhw_skc} |
| Triggers | CSR Interaction for Insurance |
| 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]


