Supporting information for Now Assist for IT Service Management (ITSM)
Get a quick overview of the important information that is related to the Now Assist for IT Service Management (ITSM) application.
Supported versions
- For Core UI: Starting with Vancouver Patch 2
- For Service Operations Workspace for ITSM: Starting with version 6.0.0
Supported language models for all Now Assist for ITSM skills and AI agents
You can use Now LLM Service, Now LLM Long Term Stable models (LTS), Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all Now Assist skills and AI agents. Use the Configuration Controls in AI Control Tower to define which options are available, then set the skill-level preferences in the Now Assist Admin console. For more information, see Large language models on the ServiceNow AI Platform®.
Role masking for Now Assist for ITSM agentic workflows, AI agents, and skills
Mask roles to restrict user access to agentic workflows, standalone AI Agents, and skills. This ensures that users receive only the necessary permissions for their tasks to enhance security and reduce the risk of unauthorized access.
Consider a scenario where a user is given roles A, B, and C and each role can access only a specific set of data. Using Access Control Lists (ACLs), the user can access any data or functions that roles A, B, and C could access. When role masking is applied, the user can only access data specific to that role.
When an ITSM skill is executed, access to its features is initially governed by ACL permissions. This ensures that users can only access the data and functions for which they are authorized. If the skill uses a Large Language Model (LLM) to perform its function, an additional layer of access control, which is role masking, is applied to the output generated by the LLM.
- Data Retrieval
ACL permissions associated with role A are used to fetch the relevant data from the incident table. This ensures that the user can only access data that they are authorized to view.
- Data Summarization
After the data is retrieved, an LLM is used for the incident summarization. Role masking is applied to the summarization output based on the access defined for role A and the summarized output is tailored based on the access privileges defined by role masking for role A.
By applying both ACL permissions and role masking, the system ensures a secure and granular access control mechanism for ITSM skills, protecting sensitive information while providing users with the insights they need to perform their tasks effectively.
For information on role masking, see Role masking in Now Assist AI agents.
Supported user interfaces
| Interface | Features |
|---|---|
| Service Operations Workspace for ITSM |
|
| Core UI |
|