--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Classify tasks # Platform Classify tasks agentic workflow {#ariaid-title1} Release version: Brazil Updated September 28, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 6 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 Platform Classify tasks agentic workflow The Platform Classify tasks agentic workflow automates the process of gathering relevant task information, prioritizing tasks, assigning teams, detecting sentiment, and generating task summaries. This workflow leverages AI applications that include agents, tools, and triggers to enhance task management efficiency and accuracy within ServiceNow. Show full answer Show less To activate the workflow, you enable its triggers and configure display settings to include the ServiceNow Otto panel. Customization requires duplicating the workflow and adjusting settings on the duplicate before activation. Access to specific features depends on your ServiceNow license tier. ## Prerequisites and Setup * ServiceNow Otto for Platform must be installed, typically included with other AI applications. * Group Action Framework (GAF) configuration is required for expected workflow behavior. * The required role to access this workflow is **snuxcgenai.platformaiclassifytasks**. * Security controls must be configured to grant appropriate roles access to the workflow and the relevant records, such as adding the **itil** role for Incident record classification. ## Configuration Workflow behavior can be tailored via the **Now Assist Skill Config Var Set** located in the Platform AI Agents and Skills scope. Key configurable aspects include: * **Search Mode:** Choose between Keyword, Semantic, or Hybrid search for identifying task context. * **AIS and GAF Fields:** Define how the workflow gathers work items, with GAF taking priority if both are set. * **Return Fields and Profiles:** Specify data to return from AI Search and profiles for integration. * **Issue Readiness:** Optionally enable if the Issue Readiness AI agent is active to influence workflow execution. * **Search Term Source:** Select whether search terms come from the record itself or user utterances. ## Accessing and Using the Workflow * Access the workflow via **AI Agent Studio \> Create and manage \> Classify tasks**. * Review included AI agents and tools through the guided setup interface. * Use the AI Activity panel in Core UI or workspaces to track workflow progress and interact with results. * Enable UI actions within AI Agent Studio to allow users to invoke the workflow through the interface. * Ensure the system property **com.glide.agenticprocessesview.enabled** is set to **true** to display UI actions. ## Testing * Manual testing is available in AI Agent Studio's Testing page for users with the **sn.aiaadmin** role. * Use sample utterances like "Populate the priority and assignment group for INC0001" to validate workflow behavior. * Automated evaluation can be performed to analyze multiple execution logs for performance insights. ## AI Agents Involved The workflow primarily uses the **Record field value prediction AI agent** , responsible for fetching, predicting, updating records, and generating summaries and justifications. This agent requires the **snuxcgenai.platformaifieldpredictor** role and must be activated via its status toggle in guided setup. ## Benefits for ServiceNow Customers Implementing this agentic workflow enables customers to automate task classification and prioritization, reducing manual effort and improving decision accuracy. The integration with AI agents and the Group Action Framework allows for more intelligent task management, leading to faster resolution times and better resource allocation within ServiceNow environments. Use the Platform Classify tasks agentic workflow to gather relevant information about tasks automatically and make decisions about priorities and assignments. ## Classify tasks overview The Classify tasks agentic workflow can help improve efficiency and accuracy by automatically gathering information, prioritizing tasks, assigning teams, detecting sentiment, and generating task summaries. The agents, tools, and triggers that are associated with the Classify tasks agentic workflow are provided by AI applications. You can [activate the agentic workflow template](https://www.servicenow.com/docs/9UjEwm2jQ1rzG05iHokkgA "Activate an agentic workflow that come installed with ServiceNow applications in AI Agent Studio.") by making triggers active and setting the display settings to include the ServiceNow Otto panel. If you want to change this agentic workflow's instructions, you must [duplicate it](https://www.servicenow.com/docs/jYTn11I8S6SrpWTEmMVUYA "Duplicate an existing agentic workflow in AI Agent Studio to save time by not having to manually configure or create agentic workflows."), adjust the settings to suit your specific needs, and activate the duplicated version of the agentic workflow instead. Note: Depending on your license, you will have access to certain application features, generative AI skills, agentic workflows, and AI agents. For more information, see [ServiceNow product tiers](https://www.servicenow.com/docs/QCGkmpN33vownhxo8L1ecg "ServiceNow structures its products and packages in three tiers — Foundation, Advanced, and Prime. Each tier incorporates AI and builds progressively on the previous one with additional AI capabilities, agents, and governance tools."). ## Prerequisites and setup To access this workflow, you must have ServiceNow Otto for Platform installed on your instance, which you can get if you install any other AI application. For this agentic workflow to behave as expected, you must also configure Group Action Framework (GAF). See [Set up AI Search for Group Action Framework](https://www.servicenow.com/docs/ffOEZTUJ~d76UU282Ef9XA "Configure AI Search to enable Group Action Framework (GAF) to improve quality and consistency of agentic AI and generative AI on the ServiceNow AI Platform.") and [Configure Group Action Framework](https://www.servicenow.com/docs/Fojcg5Tp9mQPiZyDzTa61w "Set up Group Action Framework (GAF) to improve the response quality, recall speed, and consistency of AI agents.") for more information on getting started with GAF. ## Role filtering Required role: sn_uxc_gen_ai.platform_ai_classify_tasks Agentic workflows and their AI agents use [role masking](https://www.servicenow.com/docs/iVyTaqmQoRgcYyPxVs0o1w "Role masking for AI agents and agentic workflows helps users enhance security by enabling them to limit their roles during tool execution and verify that AI agents run with least-access privileges.") 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](https://www.servicenow.com/docs/~2RVfaXYWpMJMGxQAsOjqA "In the guided setup for an agentic workflow, define security controls for who can access the agentic workflow and what data the agentic workflow has access to."). In the data access settings, you must also add the necessary roles to enable reading of the tables for the records you want to classify. For example, you can add the itil role to the agentic workflow's list of approved roles so that it can access Incident records. ## Additional configuration You can change different settings related to the agentic workflow 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 Task Classify Tasks Skill Config. * In the Now Assist Skill Config Var Set related list, select Field Predictor. * Edit the variable values. * Save or update the record. The Classify tasks configuration variable set includes the following variables. You can configure either the AIS fields or the GAF field for determining how the agentic workflow gathers what work the user has. If you configure both, GAF takes priority when running the agentic workflow. For more information about GAF, see [Group Action Framework](https://www.servicenow.com/docs/I76FimN1OYcNEzEQX~XWrA "Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs."). {#classify-tasks__entry__2} | Config field | Description | |-|-| | Search Mode | Options include Keyword, Semantic, or Hybrid. Keyword-based searches look at individual phrases, while semantic-based searches rely on the phrasing of utterances as well. Hybrid utilizes both strategies. Default: Keyword | | AIS Search Fields | Fields used by AI Search operations to find similar records for improved prediction context | | Capability | OneExtend capability for enhanced field prediction functionality. See [Generative AI Controller reference](https://www.servicenow.com/docs/c4O8DxLB3hsQV1tT7ZR5EA "Reference topics provide information about Generative AI Controller tables, and properties.") for more details. | | GAF Config | Skill configuration for [Group AI Framework (GAF)](https://www.servicenow.com/docs/I76FimN1OYcNEzEQX~XWrA "Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs."). | | AIS Return Fields | Fields returned by AI Search to the agentic workflow to base decisions on | | GAF Config | Group Action Framework grouping configuration record, which is a collection of groups of records to make searching easier | | AIS Search Profile | Profile for AI search, such as ServiceNow Otto for Virtual Agent. | | Capability Payload | Server-side script to generate custom payloads for OneExtend capability integration | | AIS Fallback Table | Table used if GAF is not configured | | Return Fields | Field values returned from identified relevant records | | Check for Issue Readiness | Uses the information provided by the Issue Readiness AI agent Warning: Only enable if the Issue Readiness AI agent is active on your instance. Otherwise, the agentic workflow will not execute. | | Fields | Field values to predict and update | | Table | Table where you want to execute the agentic workflow on | | Search Term Source | Options include Record-based and Utterance-based. Record-based derives search terms for generating context from the record itself. Utterance-based relies on the user-submitted utterance for search term options. Default: Record-based | [Table 1. Classify tasks configuration] ## Accessing the Classify tasks agentic workflow To access the agentic workflow: 1. Navigate to AllAI Agent StudioCreate and manage. 2. Select Classify tasks. {#classify-tasks__ol_fkq_csr_y2c} The first step of the guided setup includes a complete list of included AI agents. Selecting the name of an AI agent 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 Agentic workflows can be accessed 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](https://www.servicenow.com/docs/EpcQgY1TW9zL1noCh~NGXA "Dedicated spaces in workspaces and in the Core UI enable you to use agentic workflows directly in record forms. You can view agentic workflow progress and previous executions, and you can answer follow-up questions for ones that require human supervision.") for more details about the AI Activity panel. To enable users to access agentic workflows with UI actions, you can 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, ensure that the property com.glide.agentic_processes_view.enabled is set to true. See [Enable the in-product experience for agentic workflows](https://www.servicenow.com/docs/PvLU7GeYwsa0d8NtKQr7ug "Enable the AI Workflows panel and UI actions for agentic workflows on forms in the Core UI and workspaces to track agentic AI executions."). ## Testing the Classify tasks 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](https://www.servicenow.com/docs/~2RVfaXYWpMJMGxQAsOjqA "In the guided setup for an agentic workflow, define security controls for who can access the agentic workflow and what data the agentic workflow has access to."). Start a manual test, select a test type and the name of the workflow, and use utterances in the Task field like the following samples. See [Test an agentic workflow execution](https://www.servicenow.com/docs/BPtZDqaKWhE5rXB3yvW9vQ "Test your agentic workflow in AI Agent Studio to analyze how it functions while it executes the instructions that you defined."). If you want to evaluate the agentic workflow over many different execution logs, run an [automated evaluation](https://www.servicenow.com/docs/LFnqFJCapULD8~5IbYOcJg "Evaluate agentic AI assets against datasets to monitor performance and compare benchmarks."). ## Sample utterance After the workflow has been activated in AI Agent Studio, enter these or similar phrases in the ServiceNow Otto panel to trigger the workflow. You must have the sn.now_assist_panel_user role to run 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. * Populate the priority and assignment group for INC0001 * Populate the empty fields on INC0001 * Find the priority for INC001 ## AI agents used in the Classify tasks agentic workflow The following table lists the agents that are used in the Classify tasks agentic workflow. Important: In the Define availability step of each AI agent's guided setup, make sure that the Status toggle is enabled to activate the AI agent. {#classify-tasks__entry__33} | AI agent name | AI agent description | Role required | |-|-|-| | Record field value prediction AI agent | Fetches, predicts, creates, and updates records with the provided details. Provides summary and justification for recommendations. | sn_uxc_gen_ai.platform_ai_field_predictor | [Table 2. AI agents names and descriptions in the Classify tasks agentic workflow] ## Other Platform agentic workflows For more information on other agentic workflows that are associated with the Platform workflow, see [Platform agentic workflows](https://www.servicenow.com/docs/sNLCaoIlv3fOyOjzNa1R3Q "You can use the available Platform agentic workflows to achieve business outcomes with self-executing autonomous AI agents."). *[\>]: and then