Skip to main contentSkip to search
Powered by Zoomin Software. For more details please contactZoomin
Product Documentation | ServiceNowProduct Documentation | ServiceNow
Product Documentation | ServiceNow
  • Home
  • Technical Documentation
  • Release Notes
  • API Implementation
  • Accessibility
  • EnglishDeutsch日本語한국어FrançaisPortuguês
  • CommunityAsk questions, give advice, and connect with fellow ServiceNow professionals.
    DeveloperBuild, test, and deploy applications
    DocumentationFind detailed information about ServiceNow products, apps, features, and releases.
    ImpactAccelerate ROI and amplify your expertise.
    LearningBuild skills with instructor-led and online training.
    PartnerGrow your business with promotions, news, and marketing tools
    ServiceNowLearn about ServiceNow products & solutions.
    StoreDownload certified apps and integrations that complement ServiceNow.
    SupportManage your instances, access self-help, and get technical support.

Zurich Enable AI

Platform Analyze task trends agentic workflow

Save as PDF
Save topicSave topic & subtopicsSave entire publication
Share this page
Share to emailCopy latest version URL
Print
Table of contents
  • Enable AI experiences
    • ServiceNow AI implementation
      • Now Assist organization and tools
      • AI governance for Now Assist on the ServiceNow AI Platform
      • Data readiness for implementing Now Assist on the ServiceNow AI Platform
      • Application readiness for Now Assist on the ServiceNow AI Platform
        • Knowledge Base readiness for Now Assist on the ServiceNow AI Platform
        • Service Catalog readiness for Now Assist on the ServiceNow AI Platform
        • AI Search readiness for Now Assist on the ServiceNow AI Platform
        • Now Assist in Virtual Agent readiness on the ServiceNow AI Platform
      • Understanding large language models (LLMs)
      • Solving installation and configuration issues with Now Assist
    • Now Assist AI assets
      • Now Assist skills, agents, and agentic workflows on by default
      • Now Assist skills
        • Now Assist skills in the Platform workflow
          • Catalog item form slot-fill
          • Now Assist Conversational Help
          • Now Assist extract information from documents
          • Knowledge content recommendation
          • Navigation
          • Smart Documents Skill
          • Now Assist in Standard Ticket Page
      • Now Assist agentic workflows
        • Platform agentic workflows
          • Platform Analyze task trends agentic workflow
          • Platform Classify tasks agentic workflow
          • Platform Generate my work plan agentic workflow
          • Platform Generate resolution plan agentic workflow
          • Platform Identify ways to improve service agentic workflow
          • Platform Investigate problems agentic workflow
          • administer/now-assist-ai-agents/concept/email-task.html
          • Platform Process images for new tasks agentic workflow
          • Platform Propose survey responses agentic workflow
      • Platform AI agents
        • Platform Approval assistance AI agent
        • Platform Issue Readiness AI agent
        • Platform Request status AI agent
    • Large language models on the ServiceNow AI Platform
      • Now LLM Service updates
      • General guidelines for writing instructions for generative AI large language models (LLMs)
      • Long term stable models
      • Discrepancies when using different AI search tools
      • Providers and Models
        • Create a model
    • Now Assist
      • Exploring Now Assist Admin
        • Overview tab in Now Assist Admin
        • Now Assist Experiences
          • Now Assist panel
            • Activate Now Assist panel assistants
            • Standard chat
            • Enhanced chat
              • Activate Now Assist panel enhanced chat
            • Enable voice input for Now Assist panel
          • Now Assist context menu
            • Email recommendations using the Now Assist context menu
            • Summarize records with the Now Assist context menu
            • Improve Docs content in Strategic Portfolio Management with Now Assist context menu
            • Generate KB article with Now Assist context menu
            • Now Assist context menu usage dashboard
            • Use Now Assist context menu for custom skill deployment
              • Create Now Assist context Menu configuration
              • Create multiple Now Assist context menu skill configurations
              • administer/now-assist-platform/concept/nacm-variable-set-description.html
        • Analyzing Now Assist performance
          • Exploring Now Assist Analytics
          • Configuring Now Assist Analytics
            • Installing Now Assist Analytics
            • Map a skill to a dashboard
          • Using Now Assist Analytics
            • Usage and adoption
            • Self-Service performance
            • Skills performance
              • Skill details
            • Custom skill details
            • Now Assist Guardian analytics
            • User search analyzer
            • Now Assist context menu analytics
          • Now Assist Analytics reference
            • Now Assist Analytics roles
            • Now Assist Analytics dashboard indicator details
        • Now Assist Admin Settings
          • Multilingual service for Now Assist applications
            • Translation for Now Assist
            • Microsoft Azure OEM for Dynamic Translation in Now Assist
          • Data sharing and processes
            • Configure Now Assist privacy policies
            • Opt out of data sharing for Now Assist
            • Configure Now Assist data overflow processing
            • Assign the data steward role
          • Now Assist Guardian
            • Activate offensiveness protection for generative AI
            • Configure prompt injection attack protection
            • Configure sensitive topic filters
            • Export Now Assist Guardian logs
          • Manage AI models
            • Manage model providers
            • Manage version
          • Manage Integration
          • Review Now Assist account
      • Configuring Now Assist Admin features
        • Install Now Assist plugins
        • Turn on the Now Assist panel
      • Using Now Assist Admin
        • Activate a Now Assist skill
          • Configure chat summarization and chat reply recommendation skills in the Now Assist Admin console
          • Configure email reply recommendation in the Now Assist Admin console
        • Edit a Now Assist skill
        • Make a copy of a Now Assist skill
          • Configure case or incident summarization in the Now Assist Admin console
        • Analyzing Now Assist usage
      • Now Assist reference
        • Domain separation in the Now Assist Admin console
        • Fetch end points in Now Assist Conversational Help skills
        • Now Assist Admin roles
        • User data usage policy for Now Assist
        • Troubleshoot a Now Assist skill
      • Generative AI Controller
        • Exploring Generative AI Controller
          • Domain separation and Generative AI Controller
        • Configuring Generative AI Controller
          • Installing Generative AI Controller
          • Configuring API credentials for generative AI capabilities
            • Configure API Credentials for Aleph Alpha
            • Configure API Credentials for Amazon Bedrock
            • Configure API credentials for Azure OpenAI
            • Configure API credentials for Google AI Studio
            • Create API credentials for Google Vertex AI
            • Configure API credentials for IBM watsonx
            • Configure API credentials for OpenAI
            • Configure API credentials for a generic large language model (LLM) connector
          • Configure a generic large language model (LLM) connector
          • Set a provider for a generative AI capability
          • Select a model for Amazon Bedrock
          • Enable a generative AI capability in Virtual Agent Designer
          • Configure small talk filters
          • Configure AI search answers capability for web search
          • Enable recursive summarization for large inputs
          • Enable Dynamic Translation for capabilities in Generative AI Controller
          • Disable Dynamic Translation for LLM Virtual Agent conversations
          • Configure rate limiting for providers
        • Using Generative AI Controller
          • Use Generative AI Controller with Workflow Studio
          • Use Generative AI Controller with Virtual Agent Designer
          • Use Sentiment Analysis with Workflow Studio
          • Use a script with Generative AI Controller
        • Reference for Generative AI Controller
          • Generate Content action
          • Generic Prompt action
          • Sentiment Analysis action
          • Summarize action
    • Now Assist AI agents
      • Explore Now Assist AI agents
        • AI Agent Studio
        • Understand the Now Assist AI agents
        • In-product experience for agentic workflows
        • Best practices for AI agents configuration
          • General guidelines for creating AI agents and agentic workflows
            • Example AI agent
            • Example agentic workflow
        • Group Action Framework
        • Version control for AI agents and agentic workflows
        • Implement access control in Now Assist AI agents
        • AI agent learning
      • Configure Now Assist AI agents
        • Install Now Assist AI agents
        • Enable Now Assist Guardian for AI agents
        • Set up long-term memory
        • Configure Group Action Framework
          • Set up AI Search for GAF
        • Multiple conversations in Now Assist AI agents
        • Citations in Now Assist AI agents
          • Disable citations in AI Agent Studio
        • Follow-up conversations
        • Add recipients to usage spike, execution failure, and latency error email notifications
        • Role masking in Now Assist AI agents
      • Create an AI agent
        • Find AI agents
        • Define the specialty of an AI agent
        • Add tools and information to an AI agent
          • Add a catalog item to an AI agent
          • Add a conversational topic to an AI agent
          • Add a desktop action to an AI agent
          • Add a file upload to an AI agent
          • Add a flow action to an AI agent
          • Add a Knowledge Graph to an AI agent
          • Add a Now Assist skill to an AI agent
          • Add a record operation to an AI agent
          • Add a script to an AI agent
          • Add a search retrieval to an AI agent
          • Add a subflow to an AI agent
          • Add a web search to an AI agent
        • Define security controls for an AI agent
        • Add a trigger to an AI agent
        • Select channels and status for an AI agent
        • Duplicate an AI agent
        • Modify an AI agent
        • Manually test the execution of an AI agent
        • Test user access to an AI agent
        • Delete an AI agent
        • Create an external AI agent
          • Integrating external AI agents
          • ServiceNow AI agents as secondary agents
          • Create an external AI agent with manual integration
          • Create an external AI agent with the Agent2Agent protocol
      • Create an agentic workflow
        • Define key requirements for an agentic workflow
        • Define security controls for an agentic workflow
        • Add a trigger to an agentic workflow
        • Select channels and access for an agentic workflow
        • Duplicate an agentic workflow
        • Activate an agentic workflow template
        • Modify an agentic workflow
        • Manually test the execution of an agentic workflow
        • Test user access to an agentic workflow
        • Delete an agentic workflow
      • Deploy AI voice agents
        • Install Now Assist AI voice agents
        • Create an AI voice assistant
          • Configure custom assistant
        • Create an AI voice agent
        • Integrating voice assistant with CCaaS provider
          • Integrate ServiceNow voice assistant with Twilio voice service
          • Integrate ServiceNow voice assistant with Genesys Cloud service
        • AI voice agent analytics
        • AI voice agent reference
      • Evaluate agentic workflows and AI agents
        • Create a custom metric for evaluating agentic workflows
        • Agentic evaluation parser tool
        • General guidelines for AI agent and agentic workflow evaluation
      • Examples of using AI agents
        • Resolve an incident
        • Review and update tickets with the Ticket Status AI agent
      • Now Assist AI agents reference
        • Domain separation and Now Assist AI Agent Studio
        • AI Agent Analytics dashboard
        • Agentic evaluation run results
      • Model Context Protocol Client
        • Explore Model Context Protocol Client
        • Configure Model Context Protocol Client
          • Install Model Context Protocol Client
          • Add an MCP server in AI Agent Studio
            • Add an MCP server with OAuth 2.1
            • Add an MCP server with an API key
            • Add an MCP server with a connection and credential alias record
          • Add an MCP server tool to an AI agent
          • Test an AI agent
          • Model Context Protocol Client reference
    • Now Assist Data Kit
      • Exploring Now Assist Data Kit
      • Configuring Now Assist Data Kit
        • Install Now Assist Data Kit
      • Using Now Assist Data Kit
        • Add a dataset
        • Create a derived dataset
        • Generate synthetic data
          • Select the sample data
          • Define columns to generate data
          • Synthetic data generation skills
        • Add a ground truth to each dataset record
        • View data insights
        • Find and cleanse sensitive data
      • Now Assist Data Kit reference
        • Now Assist Data Kit roles (sn_data_kit.analyst)
        • Now Assist Data Kit roles (sn_data_kit.admin)
    • Now Assist Skill Kit
      • Exploring Now Assist Skill Kit
        • General guidelines for Now Assist Skill Kit
          • Scoping the skill
          • Creating a dataset using Now Assist Skill Kit
          • Developing the prompt
          • Evaluating the prompt
          • Deploying and monitoring the skill
        • Example use case for Now Assist Skill Kit
        • Security for Now Assist Skill Kit
      • Configuring Now Assist Skill Kit
        • Configure a skill prompt
        • Configure skill deployment settings
          • Example deployment with Workflow Studio
        • Configure security controls for a skill
      • Using Now Assist Skill Kit
        • Create a skill
          • Clone and edit a ServiceNow skill
        • Create a prompt
          • Add a tool
            • Add a retriever
              • Retriever chunking and reranking
            • Add a web search
            • Add Predictive Intelligence
            • Add Document Intelligence
        • Use prompt assistance
        • Test a prompt
        • Evaluate a prompt
        • Finalize and publish a skill
        • Activate a skill
        • Call a custom skill from a script
      • Now Assist Skill Kit reference
        • Now Assist Skill Kit roles
        • Field of use for Now Assist Skill Kit
        • Web search custom skill
    • AI Control Tower
      • Exploring AI Control Tower
        • AI Control Tower dashboard
          • AI Control Tower Home
            • Overview tab in AI Control Tower
            • AI strategy tab in AI Control Tower
            • AI asset inventory tab in AI Control Tower
            • Value tab in AI Control Tower
            • Health tab in AI Control Tower
            • Risk and compliance tab in AI Control Tower
            • AI cases tab in AI Control Tower
            • Evaluation tab in AI Control Tower
              • Value tab in the Evaluation dashboard
              • Human feedback for evaluations
              • Enabling evaluations
              • Configuring evaluations
            • Security & Privacy tab in AI Control Tower
            • AI Gateway tab in AI Control Tower
          • AI assets
            • AI asset inventory
              • View AI asset details
            • AI asset lifecycle
            • Approvals
            • Cases
            • Inquiries
            • AI strategies and goals
            • AI Task - All Security Tasks
          • Configurations
            • Data
            • Controls
              • Approvals
              • AI model providers
            • Multi-instance setup
            • AI discovery setup
            • AI Gateway
            • Playbooks
        • Product Owner portal
          • My overview tab in AI Control Tower
          • AI portfolio tab in AI Control Tower
        • Definitions of AI asset inventory
          • AI systems
            • Example of an AI system
          • AI models
          • Prompts
          • Datasets
          • Inter-dependencies
        • Explore Third-party LLMs and regions
        • Explore Now Assist AI asset discovery
        • Explore Enterprise AI discovery
          • Enterprise AI discovery: Unlock Visibility, Governance & Value
          • Create hyperscaler connections
            • Azure AI Foundry
              • Configure Azure portal
              • Connect to Azure AI Foundry from ServiceNow
            • AWS Bedrock
              • Configure AWS Bedrock console
              • Connect to AWS Bedrock from ServiceNow
                • Asset discovery
                • Usage
            • Google Cloud Platform (GCP) Vertex AI
              • Configure a Google Cloud Platform (GCP) service account
              • Connect to Google Cloud Platform (GCP) Vertex AI from ServiceNow
            • Copilot Studio
              • Configure Copilot Studio
              • Connect to Copilot Studio from ServiceNow
        • Explore AI Gateway
          • AI Gateway overview
          • Process flow of MCP servers Via AI Gateway
            • Add an MCP server
            • MCP server approval request
            • Setting up for connections with AI Gateway
          • View the MCP server record
          • Connect to MCP servers Via AI Gateway
            • Connecting with Copilot Studio Via AI Gateway
      • Configuring AI Control Tower workflows
        • Activation and installation of AI Control Tower
        • Configure AI Control Tower
        • Configure Multi-instance management for AI Control Tower
        • Configure third-party LLMs using AI Control Tower
      • Using AI Control Tower
        • Create an AI Control Tower Playbook Workflow
        • Create a Now Assist approval task
        • Creating AI assets
          • Create AI system assets
          • Create AI model assets
          • Create prompt assets
          • Create dataset assets
        • Creating requests for AI assets
          • Create change request for AI assets
          • Create off-boarding requests for AI systems
        • View AI assets by lifecycle stage
        • Complete AI asset lifecycle
        • Using value templates
          • Create a new value template
          • Edit a value template
          • Create a new value template mapping
          • Assign a default template
        • Create an AI case in the AI Control Tower
          • Create new AI case form
        • Create an AI issue in the AI Control Tower
          • Create new AI issue form
      • AI Control Tower Reference
        • Add value template form
        • AI Control Tower roles
        • AI Risk and Compliance roles
        • Tables installed with AI Control Tower
        • AI asset data model attributes
        • Evaluation dashboard References
          • Components installed with the Evaluation dashboard
          • Evaluation metrics and calculations
          • Evaluation flow
          • Evaluation flow for batch evaluations
    • Knowledge Graph
      • Exploring Knowledge Graph
        • Access Knowledge Graph Schema
        • Leverage Knowledge Graph prebuilt integration with Now Assist Virtual Agent and Now Assist Panel
        • Leverage Knowledge Graph prebuild integration with AI agents
        • Natural language queries use cases and examples
        • Workflow Data Fabric integration with Knowledge Graph
      • Configuring Knowledge Graph
        • Configure LLM for Knowledge Graph
        • Configure Microsoft OneDrive application for Knowledge Graph
      • Using Knowledge Graph Designer
        • Create a Knowledge Graph schema
        • Edit a Knowledge Graph schema
        • Manage nodes in a Knowledge Graph schema
        • Add or delete edges to a Knowledge Graph schema
        • Test a Knowledge Graph schema
          • Analyze Knowledge Graph logs for debugging
        • Create a copy of a Knowledge Graph schema
      • Using Enterprise graph schema
        • Tagging in Knowledge Graph
          • Create and manage Knowledge Graph tags
        • Setting up Enterprise graph in sub-production instance
        • Initial setup for Enterprise Graph schema in production instance
        • Access Enterprise Graph schema
        • View and manage Enterprise Graph schema
        • Select multiple tables
        • Test an Enterprise Graph schema
      • Reference for Knowledge Graph
        • Knowledge Graph roles
          • Knowledge Graph Admin [kg_admin]
    • MCP Server Console
      • Exploring MCP Server Console
      • Configuring MCP Server Console
        • Create a Model Context Protocol server
        • Create a tool for a Model Context Protocol server
      • Connecting to an MCP server from an MCP client
      • MCP Server Console reference
        • Components installed with MCP Server Console
    • Now Assist Readiness Evaluation
      • Exploring Now Assist Readiness Evaluation
      • Configuring Now Assist Readiness Evaluation
        • Run the GenAI/AgenticAI Assessment scheduled job
        • Configure the Now Assist Readiness Evaluation guided setup
      • Using Now Assist Readiness Evaluation
        • Using Now Assist Readiness Evaluation dashboard
          • Agentic AI - Assessment dashboard tab
          • Now Assist assessment dashboard tab
        • Assessing go or no-go
        • Reviewing your Now Assist assessment
        • Reviewing your agentic AI assessment
    • Natural Language Understanding
      • Exploring Natural Language Understanding
        • Activate the NLU Workbench
        • NLU Workbench roles
        • NLU Workbench properties
        • NLU language support
        • NLU Service updates
        • NLU models
      • Model management
        • Creating models
          • Create an NLU model from blank
          • Create an NLU model from a CSV file
          • Create an NLU model using a pre-built model
          • Duplicate an NLU model
          • Export an NLU model
          • Add an NLU model to an update set
          • Delete an NLU model
        • Build and train your model
          • NLU intents
            • Create an NLU intent
            • Reusing intents from prebuilt NLU models
            • Import an NLU intent
            • Resolve intent issues
          • NLU entities
            • Create a simple entity
            • Create a mapped entity
            • Create a pattern entity
            • Create a system-derived entity
            • Create an open-ended entity
            • Import entities
            • Using regular expressions in entities
          • NLU vocabulary
            • Create a regular vocabulary item
            • Create a pattern vocabulary item
            • Create a list vocabulary source
            • Create a table vocabulary source
            • Sync a table vocabulary source
            • Pre-built vocabulary
          • Test set creation and management
          • Train and try your NLU model
          • Test panel feedback
        • Test and publish your model
          • Test your model
          • Publish your NLU model
          • Compare draft and published versions of your NLU model
        • Irrelevance detection in NLU
        • Tune your model
        • NLU model settings
      • Multilingual model management
        • Model language grouping
        • Translate a multilingual model
        • Enable or disable a secondary model intent
        • Assign an NLU editor to a model
        • Import primary model content to a secondary model
      • Virtual Agent and NLU Workbench integration
      • NLU Workbench - Advanced Features
        • Install NLU Workbench - Advanced Features
          • Components installed with NLU Workbench - Advanced Features
        • Multi-model Batch Testing
          • Create a test set
          • Run a multi-model batch test
        • Cross-model Conflict Review
        • NLU Model Performance
        • NLU Expert Feedback Loop
        • Issue Auto Resolution Tuning in NLU
          • Issue Auto Resolution tuning options
        • Intent Discovery
          • Install Intent Discovery
            • Components installed with Intent Discovery
    • Natural Language Query
      • Exploring Natural Language Query
      • Using Natural Language Query
      • Configuring NLQ
        • Create an NLQ synonym
        • Create an NLQ shortcut
        • View NLQ logs
        • View NLQ Table Guesser logs
      • Natural Language Query References
        • NLQ properties
        • Natural Language Query roles
    • Agentic Desktop
      • Exploring Agentic Desktop
        • Agentic Desktop Design workspace
        • Agentic Desktop Execution workspace
        • Supporting information for Agentic Desktop
      • Configure Agentic Desktop
        • Download Agentic Desktop installer
      • Desktop actions in Agentic Desktop
        • Automate repetitive tasks by auto-capturing steps in Agentic Desktop
        • Automate repetitive tasks by manually capturing steps in Agentic Desktop
        • Add details to desktop actions in Agentic Desktop
        • Test and activate a desktop action in Agentic Desktop
        • Screen, anchor, and step properties in Agentic Desktop
      • Creating AI Agents for Agentic Desktop
        • Add a desktop action to an AI agent
      • Examples of creating desktop actions
        • Example: Automate badge request management using Agentic Desktop
        • Example: Automate shipping management tasks using Agentic Desktop
      • Examples of executing desktop actions using AI agents
        • Example: Use AI agents to process badge-related requests automatically
        • Example: Use AI agents to automatically enter data into the shipping management app
      • Agentic Desktop reference
        • Components installed with Agentic Desktop
        • System requirements and limitations in Agentic Desktop
    • Predictive Intelligence
      • Explore Predictive Intelligence
        • Predictive Intelligence frameworks
      • Install Predictive Intelligence
      • Configure Predictive Intelligence
        • Configuration tips for Predictive Intelligence
        • Create a custom stopwords list
        • Create a word corpus
        • Quick start tests for Predictive Intelligence
        • Activate solution version
        • Export trained solutions to production
        • Configuring advanced settings for your ML solutions
          • Configure class recall for a classification solution
          • Configure TF-IDF for solutions
          • Configure XGBoost for classification or regression solutions
          • Configure DBSCAN for a clustering solution
          • Configure HDBSCAN for a clustering solution
          • Configure Connect Component algorithm and Levenshtein Distance method for a clustering solution
          • Config parameters for model config in classification
          • Use LightGBM algo for classification model training
          • Minimum records needed for label to include it
          • Configure include only top N labels
          • Remove others label
      • Creating and training solutions
        • Create and train a classification solution
          • Exclude a class from prediction
          • Exclude a class from solution training
          • Tune a trained classification solution
          • Configuring target metrics for a trained classification solution
          • Using Group By for classification
          • Model Explainability
        • Create and train a similarity solution
          • Update your similarity score threshold
        • Create and train a clustering solution
          • Assign a name to a cluster
          • Generate a representative sample of a cluster
          • Apply purity on a clustering solution
          • Analyze a cluster with Cluster Insight
        • Create and train a regression solution
        • View solution training progress
          • Review classification solution statistics
          • Review solution similarity examples
      • Using Predictive Intelligence
        • Using Machine Learning APIs
        • Testing and monitoring predictions
          • Test a classification solution prediction
          • Test a similarity solution prediction
          • Track classification prediction results over time
        • Reviewing your ML solution training jobs
        • Reviewing prediction errors with the Observability Dashboard
        • Domain separation and Predictive Intelligence
        • Database View support for Predictive Intelligence
        • ServiceNow apps and features that use Predictive Intelligence
          • Use Predictive Intelligence in Workflow Studio with ML actions
        • Using MLSolutionFactory scriptable objects
        • Preserve ML solutions during a system clone
      • Predictive Intelligence references
        • Data Encryption in Predictive Intelligence
        • Predictive Intelligence language support
        • Predictive Intelligence properties
        • Predictive Intelligence roles
    • Document Intelligence
      • Exploring Document Intelligence
      • Configuring Document Intelligence
        • Set up Document Intelligence
        • Install Document Intelligence
        • Upgrade to Document Intelligence 3.0 or later from version 2.4 or earlier
        • Configure Document Intelligence settings
        • Set up document extraction use cases
          • Create a document extraction use case
          • Create a field for data extraction
          • Deactivate a data extraction field
          • Configure data extraction modes
        • Manage document extraction use cases
          • Duplicate a document extraction use case
          • Export a document extraction use case
          • Import a document extraction use case
          • Delete a document extraction use case
        • Set up document classification use cases
          • Create a document classification use case
          • Create a document class
          • Train a use case
        • Manage document classification use cases
          • Delete a document classification use case
        • Manage field values
      • Integrating Document Intelligence with other applications
        • Integrate with a custom application or workflow
        • Integrate with Customer Service Management
        • Integrate with Financial Services Operations
        • Integrate with Accounts Payable Operations
        • Integrate with Automation Center
      • Using Document Intelligence
        • Create a document task
        • Complete a document task
          • Extract fields using the Document Intelligence workspace
          • Extract fields using the draw tool
          • Classify documents using the Document Intelligence workspace
      • Monitoring Document Intelligence performance
        • View reports on the Document Intelligence Admin home page
        • Document Intelligence monitoring dashboard
        • Use case performance dashboard
      • Document Intelligence references
        • Components installed with Document Intelligence
        • Confidence scores
        • Data extraction modes
        • Data normalization
        • Document field statuses
        • Document Intelligence forms
          • Check box list form
          • Single field form
          • Single field group form
          • Table form
        • Document Intelligence properties
        • Document Intelligence roles
        • Document Intelligence terminology
        • Document task statuses
        • Domain separation and Document Intelligence
        • Languages supported by Document Intelligence
        • Limitations in Document Intelligence
    • Now Assist in Document Intelligence
      • Exploring Now Assist in Document Intelligence
        • Use cases in Now Assist in Document Intelligence
        • Document Intelligence workspace with Now Assist
        • Supporting information for Now Assist in Document Intelligence
      • Configuring Now Assist in Document Intelligence
        • Activate a Now Assist in Document Intelligence skill
        • Set up a use case for Now Assist in Document Intelligence
        • Turn on Full automation mode for a use case
        • Change the language models for a use case
        • Edit a use case in Now Assist in Document Intelligence
        • Make a copy of a use case in Now Assist in Document Intelligence
        • Deactivate a use case in Now Assist in Document Intelligence
        • Delete a use case in Now Assist in Document Intelligence
      • Using Now Assist in Document Intelligence
        • Review extracted information in the Document Intelligence workspace
      • Now Assist in Document Intelligence reference
        • Components installed with Now Assist in Document Intelligence
        • Data extraction modes in Now Assist in Document Intelligence
        • Document and visual insights AI agent
        • Document Intelligence tool for Now Assist Skill Kit
        • Field types in Now Assist in Document Intelligence
        • Now Assist in Document Intelligence forms
          • Question form for use case setup
          • Field form for use case setup
          • Table form for use case setup
        • Limitations in Now Assist in Document Intelligence
        • Large language models used by Now Assist in Document Intelligence
        • Languages supported by Now Assist in Document Intelligence
    • Task Intelligence
      • Exploring Task Intelligence
      • Configure Task Intelligence
        • Install Task Intelligence Admin Console
      • Manage machine learning models with Task Intelligence
        • Create a Task Intelligence model
        • Edit a Task Intelligence model
        • Assess a Task Intelligence model
          • Assess field-level accuracy for multi-output models
        • Task Intelligence Analytics and Monitoring
        • Export a Task Intelligence model
      • Task Intelligence references
        • Task Intelligence roles
        • Languages supported by Task Intelligence
    • ServiceNow AI Lens
      • Exploring ServiceNow AI Lens
        • ServiceNow AI Lens features
        • ServiceNow AI Lens landing page overview
        • Supporting information for ServiceNow AI Lens
        • ServiceNow AI Lens skill
      • Configure ServiceNow AI Lens
        • Activate the ServiceNow AI Lens skill
        • Download the ServiceNow AI Lens installer
        • Define default instructions for ServiceNow AI Lens
        • Define ServiceNow AI Lens behavior with Lens actions
        • Enabling ServiceNow AI Lens in Virtual Agent
      • Using ServiceNow AI Lens
        • Create a record in an instance by using ServiceNow AI Lens
        • Update a record in an instance by using ServiceNow AI Lens
        • Autofill catalog item form in the Service Portal
        • Trigger ServiceNow AI Lens from the desktop app
        • Extract and analyze your data by using ServiceNow AI Lens in the standalone mode
        • Extract and analyze data using ServiceNow AI Lens from Virtual Agent
      • ServiceNow AI Lens reference
        • Components installed with ServiceNow AI Lens
        • Field types supported
        • ServiceNow AI Lens limitations
        • Script include - AILensActionService
    • Conversation Insights
      • Exploring Conversation Insights
      • Install Conversation Insights
      • Conversation Insights reference
        • Components installed with Conversation Insights
    • Now Assist and Agentic AI glossary
    • Additional resources for AI products and solutions
    • Conversation Improvement Themes
      • Exploring Conversation Improvement Themes
      • Activating Conversation Improvement Themes
      • Using Conversation Improvement Themes
      • Reference for Conversation Improvement Themes
        • Components installed with Conversation Improvement Themes
        • Troubleshooting for Conversation Improvement Themes
Table of Contents

Platform Analyze task trends agentic workflow

Save as PDF
Save topicSave topic & subtopicsSave entire publication
Share this page
Share to emailCopy latest version URL
Print
  •  
  • UpdatedNov 18, 2025
  • 5 minutes to read
    • Zurich
    • AI Experiences

Use the Platform Analyze task trends AI agents agentic workflow to detect recurring task patterns so that you can flag and resolve them before they escalate.

Analyze task trends overview

The Analyze task trends agentic workflow can help enhance task management by detecting recurring patterns, predicting disruptions, and enabling a proactive resolution to reduce downtime and improve reliability. Tasks are grouped and indexed by the Large Language Model (LLM) so that the LLM can analyze common recurring issues and root patterns. The LLM then generates resolution recommendations based on the analysis and displays it to you. You can provide feedback for the LLM to guide additional analysis, and the conversation ends after you confirm satisfaction with the results.

The agents, tools, and triggers that are associated with the Analyze task trends agentic workflow are provided by Now Assist applications. You can activate the agentic workflow template by making triggers active and setting the display settings to include the Now Assist panel. If you want to change this agentic workflow's instructions, you must duplicate it, adjust the settings to suit your specific needs, and activate the duplicated version of the agentic workflow instead.

Prerequisites and setup

To access this workflow, you must have Now Assist for Platform installed on your instance, which you can get if you install any other Now Assist application, such as Now Assist for IT Service Management (ITSM).

For this agentic workflow to behave as expected, you should have at least 500 records on your task table.

You must also configure Group Action Framework (GAF). See Group Action Framework for more information on what GAF is and how to set it up. The Incident table is the default table for this workflow, but you can configure GAF for other task tables such as Case or HR Case.

Role masking

Required role: sn_uxc_gen_ai.platform_ai_analyze_trnds.

Agentic workflows and their AI agents use role masking to determine which users can access them. Ones installed with Now Assist 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. 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 enable reading of the tables for the records you want to access for trend analysis. 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 Analyze Task Trends.
  • In the Now Assist Skill Config Var Set related list, select Task Trends Input Config.
  • Edit the variable values.
  • Save or update the record.
Table 1. Analyze task trends configuration

Config field

Description

Default value

Analysis Time Frame

Range of time, in months, for the trends analyzer to look at records to identify trends. You can specify smaller ranges when running the agentic workflow, but this value defines the maximum limit.

3

GAF Record Limit

Number of records analyzed per GAF record grouping. See the preceding Prerequisites and setup section.

8

Accessing the Analyze task trends agentic workflow

To access the agentic workflow:
  1. Navigate to All > AI Agent Studio > Create and manage.
  2. Select Analyze task trends.

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.

Testing the Analyze task trends 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 name of the workflow, and use utterances in the Task field like the following samples. See Test an agentic workflow execution.

If you want to evaluate the agentic workflow over many different execution logs, run an automated evaluation.

Sample utterance

After the workflow has been activated in AI Agent Studio, similar queries to the following to run the agentic workflow in the Now Assist panel. 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.

Each utterance must include the name of the table and the time frame to analyze. If the utterance doesn’t include these things, the agentic workflow prompts you for more information.

The time frame specified by the user can’t exceed the maximum value set by the Analysis time frame configuration.

  • Analyze incident trends related to payment issues within the last two months
  • Analyze case trends within the last month
  • Analyze HR case trends with High Priority within the last two years
  • Analyze incident and problem trends within the last two weeks

Troubleshooting

When running this agentic workflow, it’s possible to see an error that states "I couldn't analyze as I didn't have the required resources." This error occurs when GAF isn’t configured for the table you want to analyze. See Configure Group Action Framework for steps to configure GAF for the table. If you’re still having issues after GAF is configured, reach out to Now Support.

AI agents used in the Analyze task trends agentic workflow

The following table lists the agents that are used in the Analyze task trends agentic workflow.
Important: In the Select channels and status step of each AI agent's guided setup, make sure that the Status toggle is enabled to activate the AI agent.
Table 2. AI agents names and descriptions in the Analyze task trends agentic workflow
AI agent name AI agent description Role required
Issue trend analysis AI agent Analyzes grouped task data to identify recurring issues and root causes. Provides detailed, actionable recommendations using structured analysis. sn_uxc_gen_ai.platform_ai_analyze_trnds

Other Platform agentic workflows

For more information on other agentic workflows that are associated with the Platform workflow, see Platform agentic workflows.

Previous

No previous section

Next

No next section

Previous

No previous section

Next

No next section

Log in to get a better experience

Log in
ServiceNow LogoThe world works with ServiceNow.™
  • Terms and conditions
  • Privacy statement
  • GDPR
  • AI Acceptable Use Policy
  • Cookie policy
©2025 ServiceNow. All rights reserved.
Title