Platform Identify ways to improve service agentic workflow
Summarize
Summary of Platform Identify ways to improve service agentic workflow
The Identify ways to improve service agentic workflow in ServiceNow leverages AI to analyze customer feedback, performance metrics, and historical trends, providing actionable recommendations to optimize service delivery and enhance customer satisfaction. Users can interact with the analysis through follow-up questions or download the results as PDF or Word documents.
Show less
This workflow depends on AI applications, tools, and triggers and can be customized by duplicating and adjusting its settings. Access to specific features depends on your ServiceNow license tier.
Prerequisites and Setup
- You must have ServiceNow Otto for Platform installed, which is included with other AI applications.
- Assessment records linked to task tables are required for survey data analysis.
- The required role to access this workflow is snuxcgenai.platformaiimproveservices. Role masking and security controls must be configured to grant appropriate user access and data permissions, including roles needed to read Assessment and task-related records (e.g., itil role for Incident records).
Configuration
Workflow settings are managed via the Now Assist Skill Config Var Set in the Platform AI Agents and Skills scope. Key configurable elements include:
- Maximum number of records: Limits survey data processed (default 500).
- Analysis Time Frame: Defines the months of data analyzed (default 3 months).
- Post Analysis Actions: Options available after analysis such as downloading results or requesting more information.
Filters can be configured for survey and task data, enabling tailored analysis on specific tables like Assessment Instance or Task, with fields such as Assignment Group, Service, or Configuration Item.
Access and Use
- Access the workflow via AI Agent Studio under "Create and manage", selecting "Identify ways to improve service".
- The guided setup displays included AI agents and tools, with detailed descriptions and roles accessible in separate tabs.
- Agentic workflows are integrated into the Core UI and workspaces through the AI Activity panel, allowing tracking, input, and review of analyses.
- UI access can be enabled by selecting UI actions in AI Agent Studio and verifying the related system property is set.
Testing
Users with the sn.aiaadmin role can manually or automatically test the workflow in AI Agent Studio using sample utterances that specify the service area and time frame for analysis. Examples include requests to identify improvements based on surveys from the last few months or specific categories.
AI Agents Involved
- Survey Analysis AI agent: Responsible for collecting and analyzing survey data to generate improvement recommendations. Requires the same platform improvement services role.
Practical Benefits for ServiceNow Customers
- Enables proactive identification of service improvement opportunities based on real customer feedback and data trends.
- Supports customization to fit specific organizational needs and data sources.
- Integrates seamlessly within the ServiceNow platform for ease of use by service agents and managers.
- Facilitates continuous service quality enhancement through actionable insights and follow-up capabilities.
Use the Platform Identify ways to improve service agentic workflow to analyze feedback, performance metrics, and historical trends that identify areas for service improvement.
Identify ways to improve service overview
The Identify ways to improve service agentic workflow optimizes service delivery and customer satisfaction by analyzing feedback, metrics, and trends to provide actionable process improvement recommendations. After the analysis is generated, you can continue the conversation to ask follow-up questions or download the analysis as a PDF or Word document.
AI applications provide the agents, tools, and triggers for the Identify ways to improve service agentic workflow. You can activate the agentic workflow template by making triggers active and setting the display settings to include the ServiceNow Otto panel. To change this agentic workflow's instructions, duplicate it, adjust the settings to suit your specific needs, and activate the duplicated version instead.
Prerequisites and setup
To access this workflow, you must have ServiceNow Otto for Platform installed on your instance. You can get this by installing any other AI application.
Because this agentic workflow relies on survey data, you must have Assessment records associated with task tables to analyze.
Role masking
Required role: sn_uxc_gen_ai.platform_ai_improve_services.
Agentic workflows and their AI agents use role masking to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see Define security controls for an agentic workflow.
In the data access settings, add the necessary roles to enable reading of the Assessment table and other required tables. For example, add the itil role to the agentic workflow's list of approved roles so it can access Incident records.
Additional configuration
You can change agentic workflow settings by changing values for the Now Assist Skill Config Var Set. To access the variable set and make changes, do the following while in the Platform AI Agents and Skills scope:
- Go to the Now Assist Skill Config [sn_nowassist_skill_config] table.
- Open the record named Identify ways to improve service.
- In the Now Assist Skill Config Var Set related list, select Survey analysis input config.
- Edit the variable values.
- Save or update the record.
|
Config field |
Description |
Default value |
|---|---|---|
|
Maximum number of records |
Maximum number of records included in analysis |
500 |
|
Analysis Time Frame |
Time range, in months, for the survey analyzer to examine records to identify trends. Users can specify smaller ranges when running the agentic workflow, but this value defines the maximum limit. |
3 |
|
Post Analysis Actions |
List of possible follow-up actions a user can take before the agentic workflow completes. |
|
|
Config field |
Description |
Default value |
|---|---|---|
|
Table name |
Table that the filter applies to |
Assessment Instance [asmt_assessment_instance] |
|
Fields |
Fields that the user can add when invoking the agentic workflow |
Metric type.Name |
|
Config field |
Description |
Default value |
|---|---|---|
|
Table name |
Table that the filter applies to |
Task [task] |
|
Fields |
Fields that the user can add when invoking the agentic workflow |
|
Accessing the Identify ways to improve service agentic workflow
- Navigate to .
- Select Identify ways to improve service.
The first step of the guided setup includes a complete list of included AI agents. Selecting an AI agent name opens it in a new browser tab, where you can see the full description, role, list of steps, and tools. Tools are displayed in the second step of the AI agent guided setup, Add tools and information.
In-product agentic AI and UI actions
You can access agentic workflows in the Core UI and in workspaces in the AI Activity panel. From there, you can track their progress, provide or review input, and see the results of the work performed. For more information, see In-product agentic AI for more details about the AI Activity panel.
To enable users to access agentic workflows with UI actions, open the agentic workflow in AI Agent Studio and navigate to the Select channels and access step. You can select a UI action as a possible way to access the workflow
If you don't see your UI actions after configuring it in AI Agent Studio, verify that the property com.glide.agentic_processes_view.enabled is set to true. See Enable the in-product experience for agentic workflows.
Testing the Identify ways to improve service agentic workflow
You can manually test an agentic workflow execution or access on the Testing page of AI Agent Studio if you have the sn.aia_admin role and all other roles configured in the security controls. Start a manual test, select a test type and the workflow name, and use utterances in the Task field like the following samples. See Test an agentic workflow execution.
To evaluate the agentic workflow over many different execution logs, run an automated evaluation.
Sample utterance
After the workflow is activated in AI Agent Studio, enter similar phrases to the following in the ServiceNow Otto panel to trigger the workflow. You can also run this workflow on the Testing page of AI Agent Studio with the same utterance in the Task field if you have the sn.aia_admin role.
When invoking the agentic workflow, if you want to use additional filters, such as metric name or category, use the name of the field in the utterance. For example, "Identify ways to improve services for the Hardware category" is more likely to analyze the correct records than "Identify ways to improve Hardware."
- Make suggestions for continuous service improvement based on surveys within the last 3 months
- Summarize surveys to improve Hardware services based on survey results within the last 2 years
- Give ideas for improving case resolution based on Post-Case metric type survey results over the last month
AI agents used in the Identify ways to improve service agentic workflow
| AI agent name | AI agent description | Role required |
|---|---|---|
| Survey Analysis AI agent | Acquires survey data within the specified time range and analyzes it for ways to improve services | sn_uxc_gen_ai.platform_ai_improve_services |
Other Platform agentic workflows
For more information on other agentic workflows associated with the Platform workflow, see Platform agentic workflows.