Platform Agentic Workflows - Classify Tasks Troubleshooting GuideSummary<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } Common troubleshooting steps for the Classify Tasks agentic workflow. Table of Contents 1. Record number not found 2. Fetching skill config issues 1. Record number not found Issue: "The record number INC##### appears to be incorrect or not found. Please provide the correct record number so I can continue with the task classification and field prediction workflow." Resolution: Missing role required to access the record. These roles are required for the Classify Tasks workflow as well as its agent(s). Steps: Navigate to AI Agent Studio > Create & Manage > Agentic workflowsSelect Classify TasksGo to the Define security controls > Define data access sidebar tabUnder Approved role(s), add the role required to access the record (e.g. `itil` role for Incident records)Save and continueRepeat steps 3 and 4 for all agents, found by navigating back to Classify Tasks and locating the agents under the Define key requirements tabs 2. Fetching skill config issues Issue: When calling the Get issue readiness state tool, users may encounter the following error: An error occurred while checking issue readiness. This implies the skill config cannot be found and therefore cannot determine the readiness state of the issue. When calling the Get similar records tool, users may encounter the following error: Error: Cannot read property "variable_sets" from undefined status. This implies the skill config cannot be found and therefore the Field Predictor skill config var set details cannot be identified. Resolution: The associated skill config is not available for the table. A skill config with the appropriate applicability filter is required that properly maps to the usecase and table. Steps: Option 1: Add a Now Assist Skill Config Applicability filter to existing Now Assist Skill Config for Classify Tasks Navigate to Now Assist Skill Config (sn_nowassist_skill_config)Search for Task Classify Tasks Skill ConfigGo to the Now Assist Skill Config Applicabilities section and add a new filterFor the new filter, add the following Filter parameters: usecase -- classify tasks (all case sensitive)table -- <table_name> (all case sensitive) Save and continue Option 2: Create a Now Assist Skill Config for Classify Tasks for the required table Navigate to Now Assist Skill Config (sn_nowassist_skill_config)Search for Task Classify Tasks Skill ConfigClone (Insert and Stay) the skill config NOTE: Clone the Field Predictor skill config var set as well and map it to the newly created skill config Go to the Now Assist Skill Config Applicabilities section and add a new filterFor the new filter, add the following Filter parameters: usecase -- classify tasks (all case sensitive)table -- <table_name> (all case sensitive) Go to the Now Assist Skill Config Status and set the skill to active: trueSave and continue Release<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } UXC Generative AI - v8+ (Xanadu and above)External Reference Doc: https://www.servicenow.com/docs/r/intelligent-experiences/classify-tasks.html