Customer Service Management AI agent collection triage cases agentic workflow
Summarize
Summary of Customer Service Management AI Agent Collection Triage Cases Agentic Workflow
The Customer Service Management (CSM) AI agent collection for triage cases in the Zurich release enables ServiceNow customers to automate and streamline the handling of routine cases from email and other offline channels. This agentic workflow supports end-to-end case validation, creation, verification, and escalation, allowing faster resolution and reducing the need to create unnecessary cases by answering customer questions directly.
Show less
Customers can access, modify, and activate the Triage cases agentic workflow within AI Agent Studio. Activating the workflow includes enabling triggers and displaying the Now Assist panel for agent interaction.
Key Features
- AI Agents Integration: The workflow incorporates specialized AI agents for specific tasks:
- Triage Cases WrapUp: Summarizes and closes triaged cases with traceability.
- Context Validator: Validates record content by analyzing sentiment and classifying intents.
- Informational Queries: Generates consolidated summaries for informational intents.
- Case Creation: Automates case creation processes.
- Entity Extraction: Extracts and validates relevant entities from unstructured content.
- Document Verification: Checks required documents for case types and identifies any issues.
- Email Response: Drafts and sends automated email replies.
- Access Control and Security: Preconfigured Access Control Lists (ACLs) support secure operations, primarily for the
snesmagentrole by default. Customers should update ACLs when customizing roles to ensure proper permissions and security alignment. - Role Masking and Data Access: Supports B2B and B2C agent roles with role masking to limit privileges during workflow execution. Proper configuration of roles in security controls and data access settings is essential for accessing and processing case records.
- Localization and Multilingual Support: Fully supports multilingual workflows with guidelines for prompt language instructions and message handling to ensure accurate translation and user communication.
- Workflow Configuration: Includes defining key requirements, security controls for user and data access, setting triggers for automatic workflow launch, and selecting communication channels. The Now Assist panel provides real-time interaction and task completion support for agents.
Practical Benefits
- Automates routine case triaging, leading to faster case resolution and improved agent productivity.
- Reduces unnecessary case creation by directly answering customer queries when possible.
- Ensures secure and role-based access control for sensitive customer service data.
- Facilitates consistent handling of multilingual customer interactions.
- Enables customization and extension of the workflow to fit specific business needs.
Implementation Notes
- To customize, duplicate and modify the Triage cases agentic workflow and update all related instructions accordingly.
- Activate necessary AI agents by enabling their status in the Define Availability screen.
- Update ACLs when changing agent roles to maintain appropriate access permissions.
- Configure triggers and channels to automate workflow engagement and visibility through the Now Assist panel.
- Test the workflow in AI Agent Studio to validate functionality before deployment.
Use CSM AI agents agentic workflow to process all routine cases coming in through email and other offline channels and increase agent productivity through faster resolution.
Triage cases overview
Using the Triage cases agentic workflow, handle end-to-end validation, creation, verification, and escalation of cases or case types. Get the correct information from the case or interaction to answer customer questions directly and reduce the number of cases that must be created.
Refer to the information provided here on agents, tools, and triggers that are related to the Triage cases agentic workflow in AI agents for Customer Service Management.
To modify the Triage cases agentic workflow duplicate it, and adjust the settings according to your requirements. You can activate the agentic workflow template by making triggers active and setting the display settings to include the Now Assist panel.
Triage cases agentic workflow
Triage and provide faster resolution for all the routine cases coming in through email and other offline channels.
- Navigate to
- Select Triage cases.
Access control lists (ACLs)
Access Control Lists (ACLs) are preconfigured to support the Triage use case, including AI agents and their associated flows and actions, such as the Document Verification Agent. By default, ACLs are configured for the sn_esm_agent role. Customers can modify these ACLs to align with their specific business requirements and security policies. For more information, Configure security controls for a skill.
- Go to the sys_security_acl table.
- Use filters to locate ACLs related to your use case, AI agent, and internal flows or actions.
- Add your custom role to each relevant ACL record.
Triage cases AI agents
The following tables list the agents that are used in the Triage cases agentic workflow.
| AI agent | AI agent role |
|---|---|
| Triage cases WrapUp | Wrap up the case triage process using the Triage Cases Wrapup AI Agent. It synthesizes the execution details and posts the summary to the work notes of the source record to ensure traceability and closure. |
| Context validator | Validate the content of a record using the Context Validator AI Agent. It analyzes sentiment and identifies a list of intents from the input record. Invoke this agent whenever record content requires validation and intent classification. |
| Informational queries | Create a summary of all answers related to informational intent using the Informational Queries AI Agent. It retrieves a list of all intents, then processes each informational intent individually before generating the final summary. Invoke this agent whenever a consolidated response to informational queries is required. |
| Case creation | Automate and manage the end-to-end process of case creation using the Case creation AI agent. Invoke this agent whenever a case needs to be created. |
| Entity extraction | Extract entities from emails and documents using the Entity Extraction AI Agent. It matches the extracted entities against a predefined allowlist of fields to ensure relevance and accuracy. Invoke this agent whenever entity-level information needs to be identified and structured from unstructured content. |
| Document verification | Verify documents on a record using the Document Verification AI Agent to determine whether they match the required list for the case type. It identifies any missing documents or verification failures. Invoke this agent whenever document validation is needed. |
| Email response | Generate and send email responses using the Email Response AI Agent. It acts as a response assistant to draft, display, and deliver email replies. Invoke this agent whenever an automated email response is required. |
Role masking
Role masking enables users to limit the roles and privileges of agentic workflows during tool execution. Agentic workflows and their AI agents that get installed with Now Assist applications are assigned pre-defined roles. If you select Users with specific roles for user access, you must configure the security controls to include these roles. Data access settings must also include these roles. For the instructions to change the security controls, see Define security controls for an agentic workflow.
In the data access settings, you must also add the necessary roles to access the cases that need triaging. For example, you can add the csm role to the agentic workflow's list of approved roles so that it can access case records.
Localization in Triage cases
- Add an explicit language instruction at the top of your prompt telling the model to respond in the user's language — instructions placed first carry the most weight.
- Avoid wrapping user-facing text in quotes. Quoted strings act as strong anchors that can override translation rules and force verbatim reproduction. Use semantic descriptions instead.
- Where possible, deliver static messages through
gs.getMessage()in a script, and reserve the model's output for dynamic content only.
Triaging the case
- In Define key requirements the workflow’s purpose is clearly described and its steps with specific actions and criteria for each is outlined.
- In the Define security controls screen, you can set the access at user and data level.
- Define user access: Specify which users can access and interact with the agentic workflow. Once you save your selections, the system automatically generates an Access Control List (ACL).
- Define data access: Choose the user identity under which the Provide customer 360 insights agentic workflow will run. This determines the roles and associated data access permissions.Note:Choose the user identity this agentic workflow should run as to determine the roles and the data access permissions derived from them. Remember, when agentic workflows can access data, they can also share that data with the human user who interacts with them. Agent level role mask are: B2B agents (sn_customerservice_agent) and B2C agents (sn_customerservice.consumer_agent).
- In Add triggers you can set up optional triggers to launch the agentic workflow automatically without a user request. Triggers can be based on conditions or schedules you define and initiate agentic AI experiences.
- In Select channels and status, you can choose the channels where this agentic workflow will be available to engage with users who initiate interactions. Toggle the display for Engage via
the Now Assist panel to see the agentic flow in Now Assist panel.Note:To turn off the agentic workflow, toggle off Engage via the Now Assist panel.
- Select Save and test.
The agent executes the testing in AI Agent Studio for the agentic workflow.
In the Now Assist panel, the agent receives a notification as soon as the interaction is generated, which enables them to follow the on-screen instructions and complete the task. For more information, see Request the generative AI capabilities in Customer Service Management by using the Now Assist panel.