Enable AI experiences -- Take advantage of artificial intelligence-based tools to prioritize and automate routine tasks, detect major incidents, and surface insights.
ServiceNow product tiers -- 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.
ServiceNow AI implementation -- Getting ready to implement Now Assist is more than just installing plugins—it’s about laying the groundwork for a seamless, intelligent experience across your workflows. Whether you're enabling conversational catalogs, automating content generation, or enhancing user interactions, a few key steps will ensure your data is ready, your applications are prepared, and your organization's AI policy is in alignment with your implementation.
Now Assist organization and tools -- The Now Assist experience includes generative AI skills, agentic AI, and conversational user engagement layer. A good AI experience depends on quality data and a coherent AI policy that functions as its guiding star. AI Search capabilities and other tools help connect the pieces.
AI governance -- As organizations increasingly adopt AI to drive efficiency, innovation, and customer experience, AI governance becomes essential to ensure responsible use, regulatory compliance, and alignment with enterprise goals. Now Assist provides a comprehensive governance framework through key roles and applications that work together to manage AI across its life cycle.
Data readiness -- High-quality data that is complete, accurate, and contextually relevant is the foundation for delivering precise, meaningful, and trustworthy AI responses.
Application readiness -- Now Assist leverages the power of the ServiceNow AI Platform to deliver AI solutions. Ensure that your instance is ready to take advantage of AI capabilities by preparing Platform applications, such as Service Catalog and AI Search.
Knowledge Base readiness -- The knowledge base is the engine that enables Now Assist to deliver intelligent, accurate, and context-aware responses across AI Search, Q&A Genius Results, and other AI-powered experiences.
Service Catalog readiness -- A well-structured Service Catalog is essential to unlocking the full potential of Now Assist. As the backbone of many self-service workflows, the catalog enables Now Assist to interpret user requests accurately, present the right options, and minimize friction in the experience.
AI Search readiness -- Now Assist in AI Search is built directly on the robust foundation of ServiceNow AI Search. AI Search provides the underlying infrastructure that enables Now Assist to retrieve and rank enterprise content—such as knowledge articles, records, and documentation—based on relevance and access permissions.
Now Assist in Virtual Agent readiness -- Now Assist enhances Virtual Agent with AI-driven capabilities that understand natural language, guide users through complex tasks, and deliver high-confidence answers without relying on rigid keyword matching or manual configurations.
Now Assist AI assets -- The Now Assist AI experience includes generative AI skills, AI agents, and AI agentic workflows. These components work alone or in combination to help achieve efficiencies and results on your instance.
AI assets on by default -- Starting with the Zurich Patch 4 release, some Now Assist skills, agents, and agentic workflows are turned on by default.
Now Assist skills -- Now Assist products provide generative AI skills that are tailored to meet the needs of users in different workflows.
Skills in the Platform workflow -- Most Now Assist generative AI products include skills in the Platform workflow, such as product navigation. Some Now Assist products include skills for the conversational user and platform experience, as well as knowledge article recommendations.
Article optimization -- The article optimization skill in ServiceNow AI Platform provides recommendations for improving the quality and health of knowledge articles, providing actionable feedback to authors and managers. The recommendations for knowledge articles become available after you activate the Article Optimization skills in Now Assist Admin.
Catalog item form slot-fill -- With the catalog item form slot-fill skill, Now Assist can automatically complete catalog item forms based on what users search for.
Conversational Help -- This skill uses Generative AI application capabilities to provide answers to the questions on the Now Assist panel.
Extract information from documents -- The extract information from documents skill allows you to use Now Assist predictions to extract information from document and image files.
Knowledge content recommendation -- Knowledge generative AI skills on the ServiceNow AI Platform provides recommendations for editing a knowledge article. Once activated, this skill is available on the Now Assist context menu.
Navigation -- Use the navigation skill in Now Assist to take you where you want to go on the ServiceNow AI Platform.
Now Assist in Standard Ticket Page -- The Now Assist in Standard Ticket Page skill allows you to display summaries generated by Now Assist, providing overviews of recent activities and ticket details.
Potential knowledge gaps -- The potential knowledge gap skill helps find missing or incomplete knowledge coverage by analyzing service interactions. Gap recommendations become available after you activate the knowledge gaps skills in Now Assist Admin.
Requester approval checklist skill -- The requester approval checklist skill in the ServiceNow AI Platform generates a structured checklist by mapping real-time request data against your organization’s knowledge articles.
Smart Documents Skill -- Accelerate document insights with instant summaries, interactive Q&A, and FAQs using Now Assist in Document Management.
Now Assist Q&A Genius Results -- The Now Assist Q&A Genius Results skill enables users to get answers to their questions from knowledge articles, external sources, and uploaded files directly in the Now Assist panel.
Now Assist agentic workflows -- Agentic workflows are AI‑driven workflow orchestrations that use one or more AI agents to achieve a specific outcome. They go beyond single‑step automation by dynamically planning, executing, and adapting actions based on context, data, and intermediate results.
In-product agentic AI -- 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.
Enable the in-product experience -- Enable the AI Workflows panel and UI actions for agentic workflows on forms in the Core UI and workspaces to track agentic AI executions.
Platform agentic workflows -- You can use the available Now Assist AI agents Platform agentic workflows to achieve business outcomes with self-executing autonomous AI agents.
Classify tasks -- Use the Platform Classify tasks agentic workflow to gather relevant information about tasks automatically and make decisions about priorities and assignments.
Analyze task trends -- Use the Platform Analyze task trends agentic workflow to detect recurring task patterns of closed tickets so that you can understand the root cause and get recommendations to prevent them from happening in future.
Generate my work plan -- Use the Platform Generate my work plan agentic workflow to create personalized work plans for currently assigned work.
Generate resolution plan -- Use the Platform Generate resolution plan agentic workflow to fetch task record details, generate resolution summary steps, and update comments or work notes.
Help optimize team productivity -- Use the Platform Help optimize team productivity agentic workflow to gather relevant information about tasks automatically and make decisions about priorities and assignments.
Identify escalation signals -- Use the Platform Identify escalation signals agentic workflow to identify tickets that require attention before they are escalated, such as tickets near the end of their SLA or ones without recent updates.
Identify ways to improve service -- Use the Platform Identify ways to improve service agentic workflow to analyze feedback, performance metrics, and historical trends that identify areas for service improvement.
Investigate problems -- Use the Platform Investigate problems agentic workflow to perform root cause and risk assessments so that you can create an actionable resolution plan for a problem.
Process images for new tasks -- Use the Platform Process images for new tasks agentic workflow to convert images to actionable tasks.
Propose survey responses -- Use the Platform Propose survey responses agentic workflow to assist requesters in completing surveys.
Platform AI agents -- Explore different AI agents available in platform Now Assist applications.
Approval assistance AI agent -- The Approval assistance AI agent is an AI agent that enables you to see your list of pending approvals, as well as see the details about your pending approvals. You can then approve or reject requests and tickets from Now Assist in Virtual Agent.
Issue Readiness AI agent -- The Issue Readiness AI agent analyzes the current state of a task to assess and determines whether it is ready to be worked on.
Request status AI agent -- The Request status AI agent is an AI agent that enables you to view tickets and make updates to them from Now Assist in Virtual Agent, the Now Assist panel, or Microsoft Teams.
Domain Separation AI agent -- The Domain Visibility AI agent enables Domain Admins to manage user domain visibility using guided, conversational workflows in the Now Assist panel.
Large language models on the ServiceNow AI Platform -- ServiceNow AI Platform utilises large language models (LLM) for generative AI and agentic AI functionality. You can choose the ServiceNow LLM or supported third-party models. LLMs bring about the Generative AI application capabilities by understanding and generating human language, and processing vast amount of data.
Now LLM Service updates -- The Now LLM Service provides access to specialized large language models (LLMs) that are developed by ServiceNow. It also provides access to open-source LLMs that are selected, configured, or enhanced by ServiceNow, from the ServiceNow community and partners. Review these reference materials and model cards for additional information about the Now LLM Service and about the models used.
Writing instructions for large language models -- When using Now Assist products and skills, you may have the option to give specific instructions or other guidance to the LLM. Writing generative AI instructions is different from conducting a keyword search. Use the following general guidelines when crafting your instructions.
Long term stable models -- Long term stable (LTS) models support regulated industries, such as financial institutions, with stronger AI lifecycle management, governance, transparency, and compliance tools.
Discrepancies when using different AI search tools -- Different AI search tools may return different answers for the same or similar searches. This difference in results is expected. It occurs because each large language model (LLM) uses a different approach to find results and generate answers that match your search.
Providers and Models -- You can bring your own large language model (LLM) provider and API to use with Now Assist.
Now Assist -- ServiceNow Now Assist uses generative AI to enhance user productivity and efficiency through conversation and proactive experiences.
Exploring Now Assist Admin -- Learn how Now Assist Admin brings generative AI capabilities to the ServiceNow AI Platform. With Now Assist Admin, you can improve the productivity and efficiency in your organization, deliver better self-service, recommend actions and provide answers, and empower your users to search more effectively.
Overview tab in Now Assist Admin -- The Now Assist Admin console provides quick and effortless access to the important information that you need to set up, configure, and monitor Now Assist applications and features.
Now Assist Experiences -- Explore Now Assist panel and Now Assist context menu under the Now Assist Experiences tab of Now Assist Admin.
Now Assist panel -- With the Now Assist panel, you can get assistance from generative AI experiences to solve customer issues faster. Use this conversational interface to summarize a chat, case, or incident, get help, or generate resolution notes so that you can get the context of this information more quickly.
Standard chat -- With the Now Assist panel standard chat, you can get assistance from generative AI experiences to solve customer issues faster. Use this conversational interface to summarize a chat, case, or incident, get help, or generate resolution notes so that you can get the context of this information more quickly.
Enhanced chat -- Now Assist panel enhanced chat is a conversational support experience within a dynamic window that also includes the ability to have multiple active conversations and superior search capabilities. Use Now Assist panel enhanced chat to improve your productivity and efficiency by leveraging generative AI to perform tasks such as summarize a chat, case, or incident, request help, generate resolution notes, among others.
Premium chat -- Now Assist panel premium chat is an AI chat experience built into your ServiceNow environment that lets you ask questions, get answers from your organization's knowledge, and take action on records — all in one place. It supports file uploads, web search, and multi-step agentic tasks, so you can handle more complex requests without leaving the panel.
Now Assist context menu -- The Now Assist context menu uses generative AI to help agents summarize, create, and edit written content, thus streamlining their writing tasks.
Email recommendations using the Now Assist context menu -- Use the Now Assist context menu to compose or respond to emails with recommendations from Now Assist with generative AI template suggestions. The Now Assist context menu enables users to generate email response recommendations in new, forward, reply, or reply all scenarios.
Summarize records with the Now Assist context menu -- Use the Now Assist context menu to generate a record summary for the page, using Generative AI application assisted summarization capabilities in workspaces and UI16. The Now Assist context menu can generate a new summary, expand or collapse the summary card, share the summary to work notes, regenerate, or copy the summary.
Now Assist context menu usage dashboard -- Use the Now Assist Context Menu dashboard to monitor the use of Now Assist context menu across the different applications.
Analyzing Now Assist performance -- Use the Now Assist Analytics dashboard to monitor the usage and performance of generative AI features and capabilities offered under Now Assist.
Exploring Now Assist Analytics -- Learn how Now Assist Analytics enables users with the Now Assist Analytics Viewer or Now Assist Analytics Admin role to monitor the usage, value, and performance of generative AI features and capabilities offered under Now Assist.
Configuring Now Assist Analytics -- Configure the Now Assist Analytics dashboard to view the usage, value, and performance indicators of Now Assist.
Installing Now Assist Analytics -- You can install the Now Assist Analytics application (sn_na_analytics) with Now Assist applications if you have the admin role.
Map a skill to a dashboard -- Map a Now Assist skill to a dashboard to view skill performance indicators and skill details.
Using Now Assist Analytics -- The Now Assist Analytics dashboard provides indicators and breakdowns that help monitor the performance of generative AI features, capabilities, and skills active on your instance.
Usage and adoption -- The Usage and adoption dashboard page contains key usage and performance indicators that help you evaluate the adoption of Now Assist in your organization.
Skills performance -- Use the Skills performance dashboard page to view usage and performance indicators of one or more Now Assist skills that are active.
Skill details -- Use the Skill details dashboard page to view usage and performance indicators of a skill.
Custom skill details -- Use the Custom skill details dashboard page to view usage and performance indicators of custom skills.
Now Assist Analytics reference -- Now Assist Analytics reference topics include information about user roles and details of the indicators on the dashboard.
Now Assist Analytics roles -- Now Assist Analytics requires the following roles to view and manage the dashboard functionality.
Now Assist Analytics dashboard indicator details -- Indicator details help you understand the data and calculations behind an indicator that is presented in the form of a visualization on the dashboard.
Now Assist Admin Settings -- Configure general settings for all Now Assist applications from the Settings tab in the Now Assist Admin console.
Multilingual service for Now Assist -- Now Assist applications use the multilingual capabilities of large language models (LLMs) to translate user-generated content.
Opt out of data sharing for Now Assist -- Data sharing improves ServiceNow AI products. You can opt out of data sharing from the Now Assist Admin console Settings page.
Assign the data steward role -- Select a data steward to make decisions about data sharing with ServiceNow in Now Assist applications.
Manage AI models -- Access and select the LLM (large language model) provider used for various Now Assist skills. The selection impacts all the skills within the capability.
Manage model providers -- Edit or customise the model provider for a skill or skill group at the instance level from the list of supported third party model providers, including the default Now LLM Service. You can also review the model policy set by your organisation, and view the change history here.
Manage Integration -- Choose the preferred integration type for configuring the available model providers. There are two ways to configure a model provider in Now Assist Admin. You can either select Original Equipment Manufacturer (OEM) or Bring Your Own Key (BYOK).
Manage version -- Manage the version of the model providers across skills and instance levels. You can change and update versions for the out-of-box and custom skills.
Review Now Assist account -- Review your Now Assist license details on the Account page of the Now Assist Admin console to make sure that you're up to date on what's available to you.
Configuring Now Assist Admin features -- Use the Now Assist Admin console to activate the various Now Assist applications and skills that you’re entitled to.
Now Assist suite -- The Application Manager uses Now Assist suite versions to verify compatibility between multiple Now Assist applications in one instance.
Example -- The Application Manager uses Now Assist suite versions to verify compatibility between multiple Now Assist applications in one instance.
Activate the Now Assist panel standard chat -- Activate the Now Assist panel standard chat to enable your agents to use Now Assist skills, in a side panel on the user interface.
Activate Now Assist panel enhanced chat -- Activate the Now Assist panel enhanced chat to enable your agents to use Now Assist skills, such as task summarization or navigation, in a side panel on the user interface.
Enable voice input for Now Assist panel -- Give users the option to use their voice when interacting with the Now Assist panel to make the panel more accessible. Voice input enables you to use the panel without needing to use a keyboard.
Configure disambiguation -- Configure the disambiguation property that controls when the assistant asks clarifying questions before responding to a Now Assist in Virtual Agent or Now Assist panel user request.
Using Now Assist Admin -- Use Now Assist Admin to explore the various Now Assist plugins, skills and associated Generative AI application features you're entitled to.
Activate a Now Assist skill -- Configure the triggers, settings, and display locations for Now Assist skills to enable GenAI capabilities across the ServiceNow AI Platform.
Configure chat summarization and chat reply recommendation skills -- Define the triggers, inputs, and display location for chat summarization and chat reply recommendation by using the guided setup in the Now Assist Admin console. The activation steps are conceptually same for both the skills.
Configure email reply recommendation -- Configure the email recommendation Now Assist skill to enable agents to draft email replies based on contextual information.
Edit a Now Assist skill -- Edit the configuration of a Now Assist skill to choose the inputs or triggers and the display location of the skill output.
Make a copy of a Now Assist skill -- The 'Make a copy' feature enables you to create a copy of a Now Assist skill so that you can experiment with skill settings and configure the skill to fit your business needs.
Configure case or incident summarization in the Now Assist Admin console -- Configure case or incident summarization by using the guided setup in the Now Assist Admin console. You can choose the input tables and fields as well as customize the prompt output for copies of the record summarization skills.
Archive a Now Assist skill -- The 'Archive' option in the navigation pane within Now Assist Admin allows you to archive copies and custom Now Assist skills.
Analyzing Now Assist usage -- Use the Now Assist analytics and monitoring tools in the Overview page to review the summaries, skill usage information, and issues that need your attention.
Now Assist reference -- Reference topics include information about user roles, data usage, and domain separation for Now Assist.
Default and target model version -- Model version is the large language model version a skill uses to route requests to process users' queries. Default model version is where all the requests route to by default. This is pre-set by ServiceNow. A target model version is chosen to route your requests to a different version at run-time, rather than using the default version.
Domain separation in the Now Assist Admin console -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for the Now Assist Admin console. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
User data usage policy for Now Assist -- Now Assist is designed to keep user data safe and secure. You can also mask sensitive data or opt-out of sharing data for model improvements.
Troubleshoot a Now Assist skill -- Run diagnostics for a skill on the Now Assist Admin console and get information about the status of your skill configuration.
Now Assist panel system properties -- Use system properties to customize Now Assist panel. Some properties are available on a system properties form, but some lesser-used properties are available only from the System Property [sys_properties] table.
Generative AI Controller -- Use Generative AI Controller to integrate third-party large language models (LLMs) with your workflows.
Exploring Generative AI Controller -- Learn more about generative AI concepts and how to integrate third-party generative AI into the ServiceNow AI Platform to create content, summarize task records, and analyze user sentiment.
Domain separation and Generative AI Controller -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for Generative AI Controller. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
Installing Generative AI Controller -- You can install the Generative AI Controller application (sn.generative.ai) with Now Assist applications if you have the admin role.
Configure API credentials for IBM watsonx -- Configure your API credentials to use IBM watsonx Granite models in custom workflows and Virtual Agent Designer topics.
Configure a generic large language model (LLM) connector -- Connect an external LLM to the ServiceNow AI Platform by using a generic LLM connector. With a connector, you can write your own prompts to send to the LLM and create your own generative AI capabilities.
Configure small talk filters -- Redirect users to different Virtual Agent topics if small talk, such as greetings, expressions of gratitude, complaints, or requests to close, are detected in conversations.
Configure AI search answers capability for web search -- AI web search is a OneExtend capability that enables end users to perform web searches and receive AI-powered answers. The capability supports multiple AI providers and integrates with virtual assistants and workflows.
Enable recursive summarization for large inputs -- Use recursive summarization to break down the requests to the large language models (LLMs) into smaller pieces so that you can maintain the context for generative AI capabilities.
Disable Dynamic Translation for LLM Virtual Agent conversations -- Enable dynamic translation of chat messages into English before they are sent to the ServiceNow large language model (Now LLM) in generative AI topics to support users who speak other languages.
Configure rate limiting for providers -- Configure rate limiting to control the traffic flow to the one_extend request by restricting the number of requests that can be made within a certain time frame.
Bring your own key for third-party AI provider integration -- The bring your own key (BYOK) feature enables you to use your own API credentials from supported cloud AI providers, such as Azure OpenAI, Amazon Bedrock, and Google Gemini, to run Now Assist skills and AI agents.
Configure a custom resource path for BYOK models -- Enter a custom resource path in your bring your own key (BYOK) model configuration so that Generative AI Controller can connect to AI service providers, such as Azure OpenAI, that use a different web address than the default.
Generative AI Controller tables -- Generative AI Controller use dedicated tables to log AI activities and track Now Assist usage across Now Assist capabilities.
Now Assist AI agents -- The ServiceNow Now Assist AI agents are entities that mimic human-like intelligence by using large language models (LLMs). AI agents can perform tasks that range from simple automated responses to complex problem solving. By using AI agents, you can reduce the workloads of your live agents and help increase their productivity.
Explore -- Learn how the Now Assist AI agents enhance live agent productivity by mimicking human-like intelligence to manage tasks ranging from automated responses to complex problem solving.
AI Agent Studio -- Create, manage, or test AI agents and agentic workflows so that you can create self-executing workflows to help you achieve your business goals.
Understand the Now Assist AI agents -- The Now Assist AI agents application is designed to securely leverage your data, workflows, and integrations directly within the ServiceNow AI Platform. AI agents can dynamically adjust their actions based on the progress and changing conditions of incidents or cases to help verify that they stay focused on achieving their objectives.
AI agents best practices -- AI agents can dynamically adjust the actions that are based on the progress and changing conditions of incidents or cases to help ensure that they stay focused on achieving their objectives.
Now Assist AI agents capabilities -- Lists the features supported by Now Assist AI agents, including configuration options and functional capabilities.
Writing effectively for agentic AI -- By following some general guidelines for creating AI agents and agentic workflows, you can create clear and effective instructions that help maximize their efficiency and effectiveness.
Example AI agent -- Use the example AI agent with clear name, description, AI agent role, and list of steps fields to use as a guide when creating your own AI agents.
Example agentic workflow -- Use the example agentic workflow with clear name, description, and list of steps fields to use as a guide when creating your own agentic workflows.
Group Action Framework -- Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs.
Version control -- Version control enables you to track changes made to instructions sent to the LLM for AI agents and agentic workflows.
Security for AI agents -- Implement security controls for AI agents and agentic workflows through access control lists (ACLs), user identities, and role masking to implement the access control-based security measures in the agentic system.
Role masking -- 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.
ACLs, role masking, and user identities -- Access control lists (ACLs) and role masking serve distinct security functions in AI Agent Studio. The difference between these two mechanisms helps you configure agents with the correct permissions and access boundaries.
Deny-by-default ACL configuration -- The ServiceNow AI Platform enforces a deny-by-default ACL (Access Control Lists) configuration for AI agentic types on freshly reset instances, for any AI agents and agentic workflows that don't have an individual ACL configured to reduce unauthorized access risks.
AI agent learning -- Enhance AI agent learning through episodic memory, enabling agents to improve by learning from past successful interactions.
Configure -- Configure the Now Assist AI agents to execute agentic workflows with AI agents and mapped tools.
Install Now Assist AI agents -- Install Now Assist AI agents on your ServiceNow instance to enable the agentic AI experience.
Set up Now Assist AI agents -- The default (base system) AI agents provide preconfigured agentic workflows that address common business challenges across ServiceNow applications. Before activating the default AI agents, you must verify that your instance meets the prerequisites and complete the required configuration steps.
Enable Now Assist Guardian -- Identify and block offensive messages that are sent by human agents automatically by enabling Now Assist Guardian in AI agents. With this capability, you can help reduce your agentic workflow or test from being exposed to harmful content.
Select the model provider -- Choose the large language model (LLM) service provider for Now Assist AI agents in AI Agent Studio.
Set up long-term memory -- Make AI agents remember your preference or facts from previous interactions and use memories for more focused conversations.
Long-term memory categories for Now Assist AI Agents -- Long-term memory (LTM) categories define the types of semantic information that a Now Assist AI agent can learn and retain about users over time. You can add new categories and map them to specific agents to personalize agent responses based on accumulated user context.
Create a long-term -- Add a long-term memory category to add it an AI agent while setting up long term memory
Map a long-term memory category to an AI agent -- Map the created long-term memory category to the agents that should use it. Categories must be mapped individually to each agent; they are not applied globally by default.
GAF -- Set up Group Action Framework (GAF) to improve the response quality, recall speed, and consistency of AI agents.
Set up AI Search for GAF -- Configure AI Search to enable Group Action Framework (GAF) to improve quality and consistency of agentic AI and Now Assist generative AI on the ServiceNow AI Platform.
Multiple conversations -- Multiple active conversations enable live agents to maintain separate conversations for different records. You can preserve the context of multiple conversations and enable multiple AI agents to interact at the same time through the Now Assist panel.
Citations in Now Assist AI agents -- You can see citations on the Now Assist panel when you execute AI agents and agentic workflows in Now Assist AI agents that provide summaries to get similar incidents and relevant knowledge articles.
Hide citations -- Disable citations for specific agentic workflows or AI agents in AI Agent Studio where citations aren’t required or involve confidential information.
Follow-up conversations -- AI agents continue with follow-up conversations after the AI agent execution is complete.
Usage, failure, and latency notifications -- Add or change recipients to email notifications triggered by unexpected or undesired behavior in AI agent and agentic workflow executions.
Create an AI agent -- Create an AI agent in AI Agent Studio to solve problems for your users and coordinate with other AI agents while executing the agentic workflows.
Find AI agents -- Find available AI agents in AI Agent Studio to explore your options when creating agentic workflows.
Define the specialty -- In the guided setup for an AI agent, write a clear description defining your agent and its role. You can also configure supported LLMs, enable third-party access, and manage long-term memory.
Add tools and information -- Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives.
Catalog item -- Add a Service Catalog to an AI agent in AI Agent Studio so that your users can access conversational catalog items.
Conversational topic -- Add a Virtual Agent topic to an AI agent in AI Agent Studio so that you can use conversations to get additional information from the user. For example, a conversational topic could be used to let a user select a date range for surveys.
Add defined desktop action for desktop and web-based tasks -- Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can execute defined path desktop actions for repetitive tasks in desktop and web environment.
File upload -- Upload files for analysis by an AI agent in AI Agent Studio to grant your AI agent access to specialized knowledge.
Flow action -- Add a flow action to an AI agent in AI Agent Studio. Define the flow action to use it as a reusable operation in automating the ServiceNow AI Platform features without having to write code.
Knowledge Graph -- Add a Knowledge Graph to an AI agent in AI Agent Studio that uses the structured and unstructured data from different ServiceNow records to enhance the performance of AI agents.
Now Assist skill -- Add a generative AI skill to an AI agent in AI Agent Studio. You can customize the skills to meet the needs of your users in different workflows.
Record operation -- Add a record operation to an AI agent in AI Agent Studio to create, update, look up, or delete records.
Script -- Create a script to add it to an AI agent in AI Agent Studio. With scripts, you can use the scriptable APIs and back-end integration to support the AI agent.
Search retrieval -- Add a search retrieval to an AI agent in AI Agent Studio. Leveraging the Retrieval-Augmented Generation (RAG) enables an AI agent to retrieve and incorporate relevant information from an external source.
Subflow -- Add a subflow tool to an AI agent in AI Agent Studio. Subflows are reusable sequences of processing steps that can be called from within a flow.
Web search -- Add a web search to an AI agent in AI Agent Studio using a third-party search API such as Microsoft Bing or Google.
Define security controls -- In the guided setup for an AI agent, define security controls for who can access the AI agent and what data the AI agent has access to.
Add a trigger -- In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met.
Kill Switch -- The kill switch feature detects and stops runaway AI agent triggers that execute repeatedly against the same records, preventing unnecessary consumption of Now Assist interactions.
Select channels and status -- In the guided setup for an AI agent, activate the AI agent to use in an assistant in Now Assist for Virtual Agent, and set the processing messages.
Duplicate an AI agent -- Duplicate an existing AI agent in AI Agent Studio so that you can save time by not having to manually configure or create AI agents.
Modify an AI agent -- Modify an AI agent in AI Agent Studio to suit your changing business needs.
Test execution manually -- Analyze the execution of an AI agent so you can see that it functions the way that you defined it.
Test user access -- Run a manual test to verify that only the users you want to access the AI agent can do so.
Delete an AI agent -- Delete an AI agent from AI Agent Studio if you no longer need it.
Create an external agent -- Create external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers as primary agents.
Integrating external AI agents -- Integrate and configure external agents with the ServiceNow agentic AI system using Agent2Agent (A2A) protocol integration to use in agentic workflows created in the AI Agent Studio.
External agents with Agent2Agent -- Create external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers.
A2A API Key credential behavior -- Starting in Now Assist AI Agents 7.1.x, the header included in each A2A request is driven by the API Key credential record and it is not injected automatically by the flow action.
Create an agentic workflow -- Create an agentic workflow in AI Agent Studio so that AI agents can coordinate to solve complex problems.
Define key requirements -- In the guided setup for an agentic workflow, write a clear description of what the agentic workflow is, add AI agents, and select unsupported AI model providers.
Define security controls -- 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.
Add a trigger -- In the guided setup for an agentic workflow, add triggers to run the agentic workflow automatically when certain conditions are met.
Select channels and access -- In the guided setup for an agentic workflow, activate the agentic workflow to use in the Now Assist panel or UI actions in the Core UI and workspaces.
Duplicate an agentic workflow -- Duplicate an existing agentic workflow in AI Agent Studio to save time by not having to manually configure or create agentic workflows.
Modify an agentic workflow -- Make changes to existing agentic workflows in AI Agent Studio to adjust them to suit your business needs.
Test execution manually -- Test your agentic workflow in AI Agent Studio to analyze how it functions while it executes the instructions that you defined.
Test user access -- Run a manual test to verify that only the users you want to access the agentic workflow can do so.
Deploy AI voice agents -- AI voice agents are generative AI-powered agents that bring natural, conversational experiences to phone-based support. As part of the broader AI agent ecosystem, they connect with telephony providers to replace rigid menu trees with seamless and human-like interactions that can help make support faster and more intuitive.
Install Now Assist AI voice agents -- Install Now Assist AI voice agents on your ServiceNow instance to enable voice-based support through agentic AI experience.
Create an AI voice assistant -- Create an AI voice assistant to enable natural, conversational voice interactions between users and AI voice agents.
Configure custom assistant -- Configure a custom telephony provider to use instead of the out-of-the-box voice assistant.
Create an AI voice agent -- Create an AI voice agent in the AI Agent Studio to resolve cases, incidents, or tasks through the phone channel.
Integrating voice assistant with CCaaS provider -- Enable users to get voice-based support from ServiceNow AI voice agents by integrating ServiceNow voice assistant with supported third-party Contact Center as a Service providers (CCaaS).
Integrate voice assistant with Twilio -- Enable users to get support from AI voice agents by integrating a ServiceNow AI voice assistant with the Twilio voice service.
Integrate voice assistant with Genesys (SIP) -- Enable users to get support from AI voice agents by integrating a ServiceNow voice assistant with Genesys Cloud service using the Session Initiation Protocol (SIP) communication channel.
Integrate voice assistant with 3CLogic -- Enable users to get support from AI voice agents by integrating a ServiceNow AI voice assistant with the 3CLogic voice service.
Integrate voice assistant with Five9 -- Enable users to get support from AI voice agents by integrating a ServiceNow voice assistant with Five9 voice service.
Test AI voice agents -- Test your AI voice agents associated with a voice assistant from the Assistant Designer. You can make browser-based voice calls and view turn-by-turn analysis of AI voice agents invoked, tools executed, and latency data during the conversation.
Test a voice assistant from Assistant Designer -- Test your voice assistant and the AI voice agents assigned to it by making browser-based voice calls and viewing turn-by-turn analysis directly from Assistant Designer.
Test a voice agent from AI Agent Studio -- Test your AI voice agent directly from AI Agent Studio by launching the voice testing interface from the agent's channel configuration page.
AI voice agent analytics -- The Voice dashboard page in the Analytics tab of Assistant Designer helps you monitor the usage and performance metrics for AI voice agents.
Evaluate agentic AI assets -- Agentic evaluations enable you to test agentic AI assets against defined datasets to verify quality before deployment. Run results score performance, identify issues, and provide opportunities for optimization.
Explore -- Automated evaluations test your agentic AI assets and help determine when they're ready for production. Learn more about how evaluations work, who they’re designed for, and the benefits they deliver.
Guidelines for evaluations -- Learn about agentic evaluation runs and different recommendations for evaluating your agentic AI assets against datasets to check for completion, performance, and tool execution.
Evaluate -- Find guidance for every stage of the agentic evaluation lifecycle, from initial setup to reevaluation.
Getting started -- Learn what you need to run your first agentic evaluation.
FAQs -- Find answers to common questions about setting up and running evaluations.
Execute a run -- Evaluate agentic AI assets against datasets to monitor performance and compare benchmarks.
Generate conversations -- Create execution log data for AI voice agentic assets By creating new conversations from typical scenarios you configure.
Track and monitor -- Monitor the status of an active evaluation run to catch errors early and confirm when results are ready to review.
Review results -- Assess your agent's overall performance after a run completes, including per-metric scores and issue counts. Use the results as your starting point for diagnosing quality issues and opportunities for improvement before deployment.
Review issues -- Identify and prioritize specific quality failures detected during an evaluation run, organized by severity. Use issue severity and metric relevance to decide which failures to address before deployment.
Analyze traces -- Investigate the full record of an agentic interaction to diagnose the root cause of a quality failure. Trace each step the agent took, including tool calls and outputs, to pinpoint where things went wrong.
Apply optimizations and reevaluate -- Review and accept system-generated recommendations to improve agent quality based on detected issues. Apply optimizations before triggering a re-evaluation to confirm that changes resolved the failures.
Troubleshoot -- Find solutions to common evaluation errors, including run failures, data ingestion issues, and unexpected results.
Create a custom metric -- Create a custom metric for evaluating AI agents and agentic workflows to test the outputs against expected responses.
Reference -- Find technical reference material for roles, metrics, and output formats of agentic evaluations.
Parser tool -- Use the outputs of the agentic evaluation parser tool in your scripts for custom metrics to customize the criteria for effective AI agents and agentic workflows.
Run results page -- Learn about agentic evaluation runs and the meaning behind different evaluation scores from the agentic evaluation results page.
Examples of using AI agents -- Review different ways that you can leverage the Now Assist AI agents application in agentic workflows across the platform.
Resolve an incident -- Help your live agents resolve an incident faster with Now Assist AI agents by using the Now Assist panel.
Review and update tickets -- Review the status of your tickets and take standard ticket actions, such as adding comments, using the Ticket Status AI agent in Now Assist in Virtual Agent.
Reference -- Find more information about user roles, tables, and the different properties that are installed in Now Assist AI agents.
Domain separation -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for Now AssistAI Agent Studio. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
AI Agent Analytics dashboard -- Track the AI agent use and efficiency gain on your instance through the AI Agent Analytics dashboard. The dashboard can reveal trends in how AI agents are used to improve the time to resolution and the number of tasks closed.
Run results page -- Learn about agentic evaluation runs and the meaning behind different evaluation scores from the agentic evaluation results page.
Model Context Protocol Client -- The ServiceNow Model Context Protocol Client (MCP Client) enables you to access the Model Context Protocol tools that are hosted externally and published using an MCP Server in the ServiceNow AI Agent Studio.
Exploring Model Context Protocol Client -- The Model Context Protocol (MCP) is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and services. MCP facilitates communication between an AI host application (like AI Agent Studio), an MCP Client embedded in the host, and one or more MCP Servers that expose specific capabilities such as tools.
Install Model Context Protocol Client -- Install the MCP Client application on your ServiceNow instance to enable using the tools from the MCP Server in AI agents.
Adding an MCP Server in AI Agent Studio -- An MCP Server hosts the APIs and tools required by an AI application, enabling it to receive and process calls from MCP Clients to govern ingress traffic and to promote secure and efficient access to tools. Adding an MCP Server in the AI Agent Studio helps you to leverage the Model Context Protocol as a tool in an AI agent.
MCP Server Others -- Add an MCP Server by selecting a Connection and Credential Alias record.
Add Model Context Protocol tool -- Add an MCP tool to an AI agent in the AI Agent Studio so that your users can access the MCP server.
Test an AI agent -- Analyze the performance of an AI agent with a Model Context Protocol tool added to it to verify that it functions the way that you defined it.
Model Context Protocol Client reference -- Find more information about user roles, tables, and the different properties that are installed with the Model Context Protocol Client application.
AI Agent Advisor -- The AI Agent Advisor automatically discovers automation opportunities in your instance based on actual operational data and helps you to deploy AI agents to implement them.
Explore -- AI Agent Advisor automatically discovers automation opportunities in your instance and helps you to deploy AI agents to implement them.
Supporting information -- Get a quick overview of the important information that is related to the AI Agent Advisor application.
Configure -- Configure settings for AI Agent Advisor.
Confirm installation -- Confirm the installation of the AI Agent Advisor application.
Set up automation opportunity discovery -- Configure the data sources, filters, and schedule that AI Agent Advisor uses to analyze your instance and identify automation opportunities.
Use -- Use AI Agent Advisor to automatically discover automation opportunities in your instance and deploy AI agents to implement the automations.
AI Agent Advisor in Now Assist Center -- Use AI Agent Advisor in Now Assist Center to automatically discover automation opportunities in your instance and deploy AI agents to implement the automations.
Reference -- The following topics provide additional information about the features and properties installed with AI Agent Advisor.
Now Assist Center -- Set up, manage, and optimize your generative‑AI solutions on the ServiceNow AI Platform from a single workspace.
Explore -- The ServiceNow Now Assist Center application is a single control hub that brings together other Now Assist capabilities and configuration functions, making it fast and effortless for administrators to set up and manage generative AI solutions from a unified experience.
Now Assist Center workspace -- Use the Now Assist Center workspace to set up, monitor, and manage your Now Assist solutions.
Side navigation bar -- The side navigation bar provides access to Now Assist applications and features integrated with Now Assist Center.
Home page -- The Now Assist Center home page provides features to quickly set up your Now Assist implementation, find automation opportunities, track performance of Now Assist solutions, and access related Now Assist applications.
Now Assist panel -- The Now Assist panel is the conversational interface where you can interact with the AI companion to perform setup, solution building, and question answering tasks.
AI Agent Advisor -- AI Agent Advisor automatically discovers automation opportunities in your instance based on actual operational data and helps you to deploy AI agents to implement them.
Now Assist Readiness Evaluation -- Now Assist Readiness Evaluation is a solution designed to simplify and automate the agentic AI and Now Assist implementation assessment process. It automates assessment processes, evaluates data readiness, and provides actionable insights to help you quickly adopt AI capabilities.
Supporting information -- Get a quick overview of the important information that is related to the Now Assist Center application.
Configure -- Install and configure settings for Now Assist Center.
Enable the Now Assist panel -- Enable the Now Assist panel to have your AI companion perform setup, configuration, and administrative tasks more quickly using natural language prompts.
Set up automation opportunity discovery -- Configure the data sources, filters, and schedule that AI Agent Advisor uses to analyze your instance and identify automation opportunities.
Use -- Use Now Assist Center to set up, manage, and optimize your Now Assist solutions from a single, guided, conversational workspace.
Activate an actionable use case -- Activate a Now Assist solution from an actionable use case card on the Now Assist Center home page.
Using Now Assist Readiness Evaluation -- Use Now Assist Readiness Evaluation to help you prepare to launch generative AI and agentic AI for your organization.
View your AI readiness assessment -- Review the readiness assessments that the Now Assist Readiness Evaluation has identified for your instance.
Using AI Agent Advisor in Now Assist Center -- Use AI Agent Advisor to automatically discover automation opportunities in your instance and deploy AI agents to implement the automations.
Use Now Assist Guardian features -- Use Now Assist Guardian features in the Now Assist Center workspace to detect offensive content, prompt injection attacks, and sensitive topics in generative AI interactions.
Monitor -- Monitor AI readiness, usage, and performance using Now Assist Center.
Now Assist Center Overview -- Use the Now Assist Center Overview dashboard to monitor key metrics for AI asset activation, adoption, and usage across your organization.
Now Assist Center Performance Explorer -- Use the Now Assist Center Performance Explorer dashboard to review and analyze the execution details of assistants and AI agents across your organization.
Now Assist Center Business Value -- Use the Now Assist Center Business Value dashboard to monitor the business value generated by AI assets across your organization, including total executions, time saved, and cost saved.
Add a value configuration -- Add a value configuration to define the business value metrics calculated for an AI asset, including average time saved per execution and average hourly rate.
Reference -- The following topics provide additional information about the features and properties installed with Now Assist Center.
Now Assist Data Kit -- Use ServiceNowNow Assist Data Kit to add datasets to a data catalog. The curated data works with ServiceNow SDK to enable the AI skill development and evaluation.
Exploring Now Assist Data Kit -- The Now Assist Data Kit plugin for Now Assist enables you to add datasets to a data catalog and create collections for use in ServiceNow SDK.
Configuring Now Assist Data Kit -- Configure system properties, plugins, and roles to enable all features of Now Assist Data Kit.
Using Now Assist Data Kit -- Use Now Assist Data Kit to add datasets to a data catalog to create collections for use in ServiceNow SDK.
Add a dataset -- Import data from a ServiceNow table or a local file into Now Assist Data Kit as a dataset. Datasets are the foundation of data collections, which you publish for use in custom skill evaluation in Now Assist Skill Kit.
Create a derived dataset -- Create a smaller, derived dataset from an existing dataset using Now Assist Data Kit. Use derived datasets to isolate specific records for focused ground truth labeling or evaluation without modifying the original dataset.
Generate synthetic data -- Create synthetic data using the Standard data generator in Now Assist Data Kit. Use synthetic data to imitate real-world records so you can run evaluations or create training for a test model without using production data.
Select the sample data -- Add the available sample data to enhance the accuracy and relevancy of the generated data in the Now Assist Data Kit application. The sample data can be curated, added into the data collection, or published.
Define columns to generate data -- Provide detailed definitions to preview a test for each column that you want the data to generate the results for.
Add a ground truth to each dataset record -- Add a ground truth to each record in a dataset. A ground truth is an expected correct output for a given record. During evaluation in Now Assist Skill Kit, your custom skill's actual output is compared against the ground truth to measure accuracy and identify areas for improvement.
View data insights -- You can view data insights to see the completeness and distribution of your generated data.
Find and cleanse sensitive data -- You can scan your datasets for sensitive data, like personally identifiable information (PII). If you find sensitive data, then you can cleanse it from your datasets.
Now Assist Data Kit roles (sn_data_kit.analyst) -- Users with this role can access the Now Assist Data Kit Home page and edit and save ground truth data. Assign this role to analysts and AI practitioners who work with datasets and ground truth in Now Assist Data Kit.
Now Assist Data Kit roles (sn_data_kit.admin) -- Users with this role can create, update, and publish datasets and data collections in Now Assist Data Kit. This role includes all permissions granted by sn_data_kit.analyst.
Now Assist Skill Kit -- Use ServiceNow Now Assist Skill Kit to create and publish custom prompts and skills for Now Assist. Creating custom skills and prompts enables you to have greater flexibility with Now Assist's generative AI capabilities.
Exploring Now Assist Skill Kit -- Use the Now Assist Skill Kit plugin for Now Assist to create and activate custom prompts and skills for Now Assist.
Example use case for Now Assist Skill Kit -- As an AI developer, you can create custom skills with Now Assist Skill Kit. For this example, create a custom skill for child incident summarization.
Configure a skill prompt -- Configure your skill prompt to set the model that is used and the randomness and creativity of the response.
Configure skill deployment settings -- Configure the deployment settings for the skill that you have created. The deployment settings enable you to choose where the admin can find the skill in Now Assist Admin.
Configure security controls for a skill -- You must define an access control list (ACL) and role restrictions for all skills. An ACL enables you to restrict who is able to access and execute a skill to only users with the correct role. Role restrictions enable users to limit roles during skill execution.
Using Now Assist Skill Kit -- Use Now Assist Skill Kit to create and publish prompts and custom skills for Now Assist.
Create a skill -- Create a custom skill for Now Assist. Creating a custom skill enables you to have greater flexibility with Now Assist's generative AI capabilities.
Clone a skill -- Clone an existing skill to use it as a starting point for a new one. You can clone both base system ServiceNow skills and custom skills you have created.
Create a prompt -- After you create a custom skill, create a prompt. Creating a prompt enables you to choose what skill inputs to use, as well as the type of tool.
Add a tool -- Add and configure tools in the Now Assist Skill Kit tool canvas to gather data and context before a prompt runs. Tools can be chained sequentially, run in parallel, or branched conditionally using decision nodes.
Add a retriever -- Add a retriever to your prompt to augment and add context to your prompts with AI search results.
Retriever chunking and reranking -- When you’re building a skill prompt that uses a retriever you can use chunking and reranking to enhance the accuracy and relevance of your responses.
Add a web search tool -- Add a web search tool to your skill to retrieve web content and include it as context in your prompt.
Use prompt assistance -- Use prompt assistance to get a jump start with your prompt development by selecting an example from the prompt library or using Now Assist to generate one.
Test a prompt -- After you create a prompt for your custom skill, test the prompt template before you finalize it. Testing the prompt verifies that you’re seeing the expected prompt results before it’s activated.
Evaluate a prompt -- Use the Now Assist Skill Kit evaluation tools to evaluate the effectiveness of your skill prompts.
Finalize and publish a skill -- When you’re satisfied with your prompt, you can publish your custom skill. Publishing the skill enables a Now Assist admin to activate it.
Activate a skill -- After you publish a skill, a Now Assist admin must activate it in Now Assist Admin. Activating the skill makes it available for users to trigger within the platform.
Field of use for Now Assist Skill Kit -- Now Assist Skill Kit is included in various Now Assist packages that cover a given customers’ ability to build Now Assist skills.
Web search custom skill -- The web search custom skill performs an internet search to answer a query. Web search is used whenever the LLM and AI Search are unable to provide results or whenever web search mode is activated.
AI Control Tower -- The AI Control Tower is a platform that connects different parts of an organization to speed up the AI adoption.
Explore -- Explore and learn about the AI Control Tower and its role in managing the AI asset inventory, overseeing configurations, integrating with other applications, and handling the asset approval workflow.
AI Control Tower dashboard -- The AI Control Tower dashboard displays a comprehensive overview of the AI status, AI inventory, and other AI related metrics.
Overview tab -- Explore the overview tab in AI Control Tower and the widgets available on the tab.
AI strategy tab in AI Control Tower -- The AI strategy tab includes information about all the AI-related priorities, goals, planning items, and execution items—projects and demands in the AI Control Tower workspace.
AI asset inventory tab in AI Control Tower -- The AI asset inventory includes all the AI-related assets used by an organization, including AI models, prompts, systems, and databases.
Value tab in AI Control Tower -- Use the Value dashboard page to gain insights into the value realized from multiple types of AI in your organization.
Adoption tab in AI Control Tower -- Use the Adoption dashboard page to view data about user engagement and feedback, and adoption of every type of AI.
Health tab -- Monitor the performance of guardrails enabled through Now Assist Guardian.
Risk and compliance tab in AI Control Tower -- The Risk and compliance tab on the AI Control Tower displays the risk classification of AI assets and the compliance posture for selected authority documents and policies.
AI cases tab in AI Control Tower -- Track, monitor, and analyze your AI case workflows, identify your workflow bottlenecks, and check your accountability of your AI-related risks by using the AI risk and compliance dashboard. As an AI steward, you can also use the dashboard to track the status and trends of your AI-related inquiries.
Security & privacy tab in AI Control Tower -- Review AI asset security metrics such as access issues, dormant and privileged AI agents, and map the relationships of your ServiceNow agents, agentic workflows, and tools.
AI Gateway tab -- Explore the AI Gateway tab in the AI Control Tower.
AI assets -- An AI asset refers to a digital tool or resource that uses artificial intelligence to carry out particular tasks or address problems. Examples include machine learning models, chatbots, natural language processing systems, image recognition software, and similar technologies.
AI asset inventory -- AI asset inventory includes all the AI assets such as AI models, AI systems, prompts, datasets, and MCP servers that an organization can use.
Manage AI assets list -- The AI assets list in AI Control Tower shows all AI assets that have been discovered or registered.
AI asset lifecycle -- The AI asset lifecycle defines the stages for managing an AI system, model, prompt, or dataset throughout its useful life.
Approvals -- The approvals are requests created to either approve or reject an asset. The Approvals menu displays a list of Now Assist approvals.
Cases -- You can view all the assigned and unassigned AI cases in a list view in the AI Control Tower.
Inquiries -- You can view all the assigned and unassigned inquiries in a list view in the AI Control Tower.
AI strategies and goals -- You can track and monitor the progress of your strategic priorities, goals, planning items, and execution items—projects and demands classified as Artificial Intelligence in other ServiceNow applications.
AI Task -- Use the All Security Tasks tab to view all AI security tasks for your instance. You can also create an AI task on this page.
Configurations -- Explore the AI Control Tower Configurations page to manage and govern ServiceNow AI assets.
Automation rules -- The Automation rules define how AI assets are set to be under managed assets.
Multi-instance Setup -- The multi-instance setup enables a prod (manager) instance to control, manage, and communicate with multiple sub-prod (managed) instances for AI Control Tower.
AI Gateway -- Explore the AI Gateway page and its tab in the AI Control Tower Configurations.
Playbooks -- The Playbook templates list has a record of Approval Playbook for Now Assist approvals and Asset lifecycle playbook templates.
Product Owner portal -- Explore the product owner view and navigate through the accessible tabs in the AI Control Tower.
My overview tab -- The My overview tab in the AI Control Tower home page displays all active assets to the asset owner and the AI stewards for assets that they manage or own.
AI portfolio tab -- The AI portfolio tab in the AI Control Tower home page displays all AI assets, which includes (active, inactive, and completed) to the workspace users.
AI systems -- Explore the AI systems in detail with examples.
Example of an AI system -- The AI Control Tower application and the AI Risk and Compliance application play a critical role in managing and governing the responsible use of AI systems, especially in high-stakes domains such as banking and finance.
AI models -- Explore the AI models in detail with examples.
Prompts -- Explore the prompts in detail with examples.
Datasets -- Explore the datasets in detail with examples.
Inter-dependencies -- Explore the inter-dependencies of AI systems, AI models, and datasets.
Explore Now Assist AI asset discovery -- Explore the synchronizing process of AI assets including models, datasets, prompts, skills, and agentic AI components into the AI Asset Inventory of AI Control Tower.
AI connections -- AI connection is a core feature of the AI Control Tower. It provides a unified view of all AI assets across hyperscalers, AI apps, and agentic AI frameworks via Service Graph Connectors.
Service Graph Connectors for AI Control Tower -- You can use Service Graph Connectors (SGC) to import and integrate third-party data into CMDB and non-CMDB tables to create AI connections.
AWS -- The AI Service Graph Connector for Amazon enables you to discover and import AI assets from your AWS environment into ServiceNow AI Control Tower.
AWS APIs -- Explore the AWS APIs used in AI Service Graph Connector for Amazon.
Databricks -- The AI Service Graph Connector for Databricks enables you to discover and import AI assets from your Databricks environment into ServiceNow AI Control Tower.
Create an AI connection for Databricks -- Create an AI connection for Databricks in AI Control Tower using the AI Service Graph Connector for Databricks.
GCP Vertex AI -- The AI Service Graph Connector for GCP Vertex AI enables you to discover and import AI assets from your Google Cloud environment into ServiceNow AI Control Tower.
Create an AI connection for GCP Vertex AI -- Create an AI connection for GCP Vertex AI in AI Control Tower using the AI Service Graph Connector for GCP Vertex AI (1.1.1).
Hugging Face -- The AI Service Graph Connector for Hugging Face enables you to discover and import AI assets from your Hugging Face environment into ServiceNow AI Control Tower.
Create an AI Connection for Hugging Face -- Create an AI connection for Hugging Face in AI Control Tower using the AI Service Graph Connector for Hugging Face (Version 1.1.0).
IBM -- The AI Service Graph Connector for IBM enables you to discover and import AI assets from your IBM environment into ServiceNow AI Control Tower.
Create an AI connection for IBM -- Create an AI connection for IBM in AI Control Tower using the AI Service Graph Connector for IBM.
IBM APIs -- Explore the IBM APIs used by the AI Service Graph Connector for IBM
Data mapping -- The AI Service Graph Connector for IBM uses separate data sources and staging tables for each asset type, per service. The staged data is transformed and loaded into target CMDB tables.
Target CMDB classes -- When you complete setting up the connection, you can configure the integration to periodically pull data from IBM. The data is saved in tables that extend from the Configuration Item [cmdb_ci] table.
Properties -- AI Service Graph Connector for IBM properties control the behavior of the connector.
LangGraph -- The AI Service Graph Connector for LangGraph enables you to discover and import AI assets from your LangGraph environment into ServiceNow AI Control Tower.
Create an AI connection for LangGraph -- Create an AI connection for LangGraph in AI Control Tower using the AI Service Graph Connector for LangGraph (1.1.1).
LangGraph APIs -- Explore the APIs used in AI Service Graph Connector for LangGraph.
Target Tables -- Target tables for storing AI Service Graph Connector for LangGraph data.
Microsoft -- The AI Service Graph Connector for Microsoft enables you to discover and import AI assets from Azure AI Foundry and Copilot Studio environments into ServiceNow AI Control Tower.
Azure and Copilot APIs -- Explore the APIs used in AI Service Graph Connector for Azure and Copilot.
Target Tables -- Target tables for storing Service Graph Connectors for Azure and Copilot data.
Moveworks -- The AI Service Graph Connector for Moveworks enables you to discover and import AI assets from Moveworks environments into ServiceNow AI Control Tower.
Create an AI connection for Moveworks -- Create an AI connection for Moveworks in AI Control Tower using the AI Service Graph Connector for Moveworks (Version 2.0.1).
n8n -- The AI Service Graph Connector for n8n enables you to discover and import AI assets from your n8n environment into ServiceNow AI Control Tower.
Create an AI connection for n8n -- Create an AI connection for n8n in AI Control Tower using the AI Service Graph Connector for n8n (Version 1.0.2).
Properties for n8n -- AI Service Graph Connector for n8n properties control the behavior of the connector.
Target Tables -- When you complete setting up the connection, you can configure the integration to periodically pull data from a n8n project. The data is saved in tables that extend from the CMDB CI classes and other non-CMDB classes.
OpenAI -- The AI Service Graph Connector for OpenAI enables you to discover and import AI models and track model usage from your OpenAI environment into ServiceNow AI Control Tower.
Create an AI connection for OpenAI -- Create an AI connection for OpenAI in AI Control Tower using the AI Service Graph Connector for OpenAI (Version 1.0.0).
OCI -- The AI Service Graph Connector for OCI enables you to discover and import AI assets from your OCI environment into ServiceNow AI Control Tower.
Create an AI connection for OCI -- Create an AI connection for OCI in AI Control Tower using the AI Service Graph Connector for OCI.
OCI APIs -- Explore the OCI APIs used by the AI Service Graph Connector for OCI
Data mapping -- The AI Service Graph Connector for OCI uses separate data sources and staging tables for each asset type, per service. The staged data is transformed and loaded into target CMDB tables.
Target CMDB classes -- When you complete setting up the connection, you can configure the integration to periodically pull data from OCI. The data is saved in tables that extend from the Configuration Item [cmdb_ci] table.
Salesforce -- The AI Service Graph Connector for Salesforce enables you to discover and import AI assets from your Salesforce environment into ServiceNow AI Control Tower.
Create an AI connection for Salesforce -- Create an AI connection for Salesforce in AI Control Tower using the AI Service Graph Connector for Salesforce (Version 1.1.0).
Salesforce APIs -- Explore the APIs used in AI Service Graph Connector for Salesforce.
Snowflake -- The AI Service Graph Connector for Snowflake enables you to discover and import AI assets from your Snowflake environment into ServiceNow AI Control Tower.
Create an AI connection for Snowflake -- Create an AI connection for Snowflake in AI Control Tower using the AI Service Graph Connector for Snowflake (Version 2.0.5).
Snowflake Statements API Reference -- The connector uses the Snowflake Statements API to query AI assets and usage data. The following queries are executed during discovery and usage collection.
AI Gateway -- Explore the AI Gateway, its value, and learn how to use and configure it for your Model Context Protocol (MCP) transactions.
Creating AI assets -- You can create AI assets to track and manage the life cycles of your AI systems, AI models, prompts, and datasets.
Create AI system assets -- Create AI assets to track and manage the life cycles of your AI systems.
Create AI model assets -- Create AI assets to track and manage the life cycles of your AI models.
Create prompt assets -- Create AI assets to track and manage the life cycles of your prompts.
Create dataset assets -- Create AI assets to track and manage the life cycles of your datasets.
Creating requests for AI assets -- You can manage deployed AI assets effectively by creating change requests for updates to existing assets or by creating offboarding requests for retiring assets.
View AI assets by life-cycle stage -- View AI assets based on the AI asset life-cycle stage that they are currently in. Use this information to determine which AI assets require your attention.
Complete AI asset lifecycle -- Complete the AI asset lifecycle process starting from assessment through deployment.
Using value templates -- Use value templates to define, calculate, and track the value delivered by your AI systems and models.
Add a value template -- Add a value template to define, calculate, and track the value delivered by an AI asset.
Edit a value template -- Edit a value template to update how value is calculated for AI assets.
Create an AI case in the AI Control Tower -- Create an AI case in the AI Control Tower by providing a detailed description, such as system behavior, affected users, and any relevant data. Ensure all necessary information, such as supporting attachments, is included for prompt resolution.
Create new AI case form -- Use the Create New AI case form in the AI Control Tower to report an AI case with the necessary details.
AI Control Tower roles -- Certain roles are installed along with the installation of the AI Control Tower.This section also covers roles which are installed with AI Risk and Compliance.
AI Control Tower email notifications -- Email notifications are sent automatically when specific events occur across AI Control Tower workflows.
Knowledge Graph -- The Knowledge Graph application, uses the structured and unstructured data from ServiceNow records, knowledge bases, and external sources to enhance the performance of Now Assist Virtual Agent, AI agents, and generative AI skills.
Exploring Knowledge Graph -- Knowledge Graph provides a connected representation of data that maps entities and their relationships, adding context and meaning to information to enable intelligent search, insights, and AI-driven experiences.
Configuration item relationships and Knowledge Graph -- Configuration item (CI) Relationships enable Knowledge Graph to answer natural language questions about service dependencies and infrastructure topology by storing typed parent-child relationships between CMDB configuration items.
Using Enterprise graph schema -- Use Enterprise Graph for accurate natural language query responses, across the entire database.
Tagging in Knowledge Graph Designer -- Use Knowledge graph tags to mark the key tables, that are important for answering natural language questions for specific use cases.
Improving Natural Language Queries with Tag configuration -- AI instructions add more business context to natural language queries. They guide users and promote responses that more closely align with their needs and expectations.
Create Knowledge Graph tag -- Create Knowledge Graph tags for Now Assist Virtual Agent, AI agent or Now Assist panel Enterprise Graph using Knowledge Graph Designer to improve accuracy of natural language queries.
Managing Knowledge Graph tags -- Edit or delete Knowledge Graph tags for Now Assist Virtual Agent, AI agent or Now Assist Panel Enterprise Graph use case.
MCP Server Console -- MCP Server Console enables secure and governed access to functionality on a ServiceNow instance for AI applications with Model Context Protocol (MCP) servers. MCP servers extend ServiceNow AI Platform functionality into any external MCP client and employee experience over the Model Context Protocol.
Explore -- Learn about how you can use Model Context Protocol (MCP) servers to allow AI applications to access data and perform actions on a ServiceNow instance.
Configure -- Create a Model Context Protocol (MCP) server and configure the tools and inputs it exposes to MCP clients.
Create a server -- Create a Model Context Protocol (MCP) server and configure which tools it exposes to MCP clients.
Create a tool -- Create a tool from various tool categories, to expose it to Model Context Protocol (MCP) clients from an MCP server.
Create a tool from Subflow -- Create a tool from Subflow to expose it to Model Context (MCP) clients from an MCP Server. Subflows and actions empower agents to complete tasks seamlessly —from submitting requests to routing for approval and confirming outcomes across workflows, without leaving the client interface.
Create a tool from Action -- Create a tool from Action to expose it to Model Context Protocol (MCP) clients from an MCP Server.
Create a tool from REST API -- Create a tool from REST APIs to expose it to Model Context Protocol (MCP) clients from an MCP Server.
Create a tool from Knowledge Graph -- Create a tool from Knowledge Graph to expose it to Model Context Protocol (MCP) clients from an MCP Server. Knowledge Graph provides agents with accurate, relationship-aware access to live instance data. This enables more precise, context-aware responses in every workflow by directly querying relationships.
Create a tool from Now Assist skill -- Create a tool from Now Assist skills to expose it to Model Context Protocol (MCP) clients from an MCP Server.
Create an app -- Build, register, and display user interfaces along with your tool's logic with MCP apps. This allows you to implement and manage interactive interfaces for your tools that can be displayed by MCP clients.
Connect -- Connect to a Model Context Protocol (MCP) server from an MCP client by creating an OAuth inbound integration and configuring the client with the server details.
ServiceNow(Glide) configuration for IDP -- This process involves setting up the necessary tables and mappings within your ServiceNow instance. This includes configuring ServiceNow, creating the MCP server, and connecting the MCP client.
Integrate and test IDP with MCP server -- This phase within integration of MCP server with IDP involves connecting the MCP client (such as Claude Desktop) to the configured systems.
Reference -- Reference topics include information about MCP Server Console roles, tables, and more.
Installed components -- Several types of components are installed with activation of the MCP Server Console application, including tables and user roles.
Domain separation and MCP Server Console -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.Domain separation is supported for MCP Server Console. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
Now Assist Readiness Evaluation -- The Now Assist Readiness Evaluation app helps prepare your organization for implementing agentic AI for ITSM and CSM, Now Assist for five products, or both.
Explore -- The Now Assist Readiness Evaluation app automates assessment processes, evaluates data readiness impacting implementation, and provides actionable insights to promote adopting Now Assist quickly. The app enables you to assess whether updates, installations, or customizations of your instance could affect implementation. The assessments provide direct hyperlinks to improve any issues found.
Configure -- Run the scheduled jobs and complete the Now Assist Readiness Evaluation guided setup configuration steps before viewing the generative AI and agentic AI assessment results.
Run individual assessment scheduled jobs -- Use individual scheduled jobs to assess readiness for Now Assist and agentic AI implementations across your instance.
Use -- The Now Assist Readiness Evaluation app helps you find actionable items in your implementation preparation and provides direct hyperlinks to improve upon those gaps.
Agentic AI - Assessment dashboard tab -- The Now Assist Readiness Evaluation dashboard's Agentic AO AI - Assessment tab helps determine agentic AI readiness for IT Service Management (ITSM) and Customer Service Management (CSM) by delivering automated, data-driven insights.
Now Assist Assessment dashboard tab -- The Now Assist Readiness Evaluation dashboard's Now Assist Assessment dashboard tab helps determine generative AI readiness for Now Assist by delivering automated, data-driven insights.
Assessing readiness status -- The Now Assist Readiness Evaluation app shows you a high-level overview of your go or no-go status for your organization's readiness to implement agentic AI, generative AI, or both in Now Assist.
Reviewing your Now Assist assessment -- This automated assessment process evaluates potential implementation impacts and provides actionable insights for Now Assist products.
Reviewing your Agentic AI assessment -- This automated assessment process evaluates potential implementation impacts and provides actionable insights for agentic AI in Now Assist for IT Service Management (ITSM) and Now Assist for Customer Service Management (CSM).
Reference -- Now Assist Readiness Evaluation admins and implementers can work with select system properties for additional customization.
Natural Language Understanding -- ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.
Exploring Natural Language Understanding -- ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.
NLU Workbench properties -- Refer to these system properties for the Natural Language Understanding (NLU) application.
NLU language support -- The NLU Workbench application provides support for creating NLU models in different languages for use in other applications, such as Virtual Agent.
NLU Service updates -- Refer to this documentation so you are up to date with changes to the NLU Service.
NLU models -- Use NLU models to apply ServiceNow Natural Language Understanding on your instances. Create, manage, test, and publish NLU models with the NLU Workbench.
Model management -- Manage your NLU model's life cycle in the NLU Workbench. Model management phases guide you through the iterative process of building, testing, and publishing your model.
Creating models -- Creating models is the first step to taking advantage of Natural Language Understanding (NLU) in your instances. Create models for Virtual Agent and AI Search in the NLU Workbench.
Create an NLU model from blank -- Create a Natural Language Understanding (NLU) model from scratch. Start with an empty model to have full control over the model's content.
Create an NLU model from a CSV file -- Upload a CSV or XLSX (Excel Workbook) file containing utterances and their intents to create a Natural Language Understanding (NLU) model. Use this method to quickly create models from your data or other exported models.
Duplicate an NLU model -- Duplicate an existing Natural Language Understanding (NLU) model to create a new one. Duplicating a model copies the settings and contents of the original model, including its default test set.
Export an NLU model -- Export a Natural Language Understanding (NLU) model to create a CSV file of the intents and utterances. You can then use the CSV file to edit, share, and import.
Add an NLU model to an update set -- Use update sets to move your Natural Language Understanding (NLU) models from one instance to another. Update sets include all records needed for your model to function on the target instance.
Delete an NLU model -- Delete a Natural Language Understanding (NLU) model permanently.
Build and train your model -- After creating a model, build the model's content by adding intents, entities, vocabulary, and test set utterances. Your NLU model content determines how the model responds to user inputs.
NLU intents -- Intents drive your models' responses by matching a system action to user inputs. Models with good intents help Virtual Agent and Search respond to your users accurately.
Create an NLU intent -- Create an intent for your Natural Language Understanding (NLU) model. Intents provide your model with a system action to perform when it receives user input.
Reusing intents from prebuilt NLU models -- Reuse Natural Language Understanding (NLU) intents by importing them from a prebuilt NLU model to other models. Reusing intents saves time when building your models.
Import an NLU intent -- As you create intents for your Natural Language Understanding (NLU) model, you can also import and reuse intents from other models in the same application scope. Reusing intents saves time when building new models.
Resolve intent issues -- Use the issue cards to identify intents that have conflicts, need reviewing, or need more utterances. Resolving intent issues ensures the intents in your Natural Language Understanding (NLU) models work properly.
NLU entities -- Entities provide your model with additional context when receiving user input. Add entities to your utterances and intents to improve the predictions of your Natural Language Understanding (NLU) model.
Create a simple entity -- Create one or more simple entities from words in your utterance examples. An entity is an object of, or context for, an action.
Create a mapped entity -- Create an entity mapped to a vocabulary source, or to a list of values you manually create for the entity. Mapped entities can help provide multiple values the model can use as context when interpreting utterances.
Create a pattern entity -- Create a pattern entity from a word or phrase with repeatable patterns, such as email addresses and phone numbers. These patterns help the system to recognize similar utterances based on the patterns.
Create a system-derived entity -- Create a custom entity that's derived from a default system entity such as date, time, duration, or location.
Create an open-ended entity -- Use an open-ended entity when you want to improve intent prediction accuracy. Open-ended entities help your model focus on the context of the utterances.
Import entities -- Reuse entities that you have created across your other Natural Language Understanding (NLU) models. Importing entities saves time and helps improve the intents in your model.
Using regular expressions in entities -- Learn how to use regular expressions in your NLU entities to establish patterns that help the system locate, match, and manage text.
NLU vocabulary -- Use NLU vocabulary items to help the system recognize the various ways your users express their requests. Use vocabulary sources to help the system recognize objects in tables or lists, such as names of conference rooms or catalog items.
Create a regular vocabulary item -- Add a word or phrase that your users might use, and match that vocabulary item to a synonym. Your model uses the synonym during intent prediction.
Create a pattern vocabulary item -- Use regular expression (regex) encoding to establish a pattern format for vocabulary items such as email addresses, phone numbers, and record naming conventions. You can create your own patterns for the vocabulary data in your instance.
Create a list vocabulary source -- Create a list of words or phrases to act as a vocabulary source. The values in the list source are replaced by the synonym if they are detected in a user utterance.
Create a table vocabulary source -- Use the values from a ServiceNow table as a vocabulary source. Your Natural Language Understanding (NLU) models use your provided synonym to interpret utterances that contain values from the chosen source fields of the table.
Sync a table vocabulary source -- Synchronize your table vocabulary sources to obtain the latest changes to the ServiceNow source table. Synchronizing your vocabulary sources ensures your NLU models have the latest values when predicting intents.
Pre-built vocabulary -- Use ServiceNow pre-built vocabulary for software and hardware terms so the system recognizes their multiple variations in utterances.
Test set creation and management -- Use the default test set of your NLU model to test the model's performance and accuracy. Manage your test set over time by building or updating its content in the NLU Workbench.
Train and try your NLU model -- Train and try your model iteratively so that its intents and entities are validated, compiled, and saved to your model.
Test panel feedback -- When testing your NLU model on the Try model section of the test panel, use this feature to provide feedback on the model's intent predictions.
Test and publish your model -- Assess the performance of your NLU model to identify areas for improvement. Then publish your model to make it available to other applications such as Virtual Agent.
Test your model -- Test your Natural Language Understanding (NLU) model against its default test set. Testing helps determine how your model is performing with the current content.
Publish your NLU model -- Publish your Natural Language Understanding (NLU) model to activate it and make it available for use in other applications that consume NLU.
Compare draft and published versions of your NLU model -- Compare a draft trained Natural Language Understanding (NLU) model to its most recent published version. Test and review the changes to make sure that your draft model will have increased performance.
Irrelevance detection in NLU -- Keep Virtual Agent chats focused with Irrelevance detection. Use the Irrelevance detection feature to train your NLU model to avoid making predictions for utterances that are not relevant.
Tune your model -- On your model's overview in NLU Workbench, open the Tune your model phase to review and incorporate user utterances from the Expert Feedback Loop.
NLU model settings -- Change your NLU model's name, description, or confidence threshold on the Settings page of the model overview.
Multilingual model management -- Use multilingual Natural Language Understanding (NLU) models for the system to understand user input in several languages. The NLU Workbench helps you manage and maintain a consistent structure for content across languages to provide a unified experience.
Model language grouping -- Language grouping makes it easier to manage your multilingual Natural Language Understanding (NLU) models. You can review existing language groups and designate new language groups.
Translate a multilingual model -- Add a language to an existing NLU model by translating it. Use one of several translation options to add a secondary model in a supported language.
Enable or disable a secondary model intent -- Enable and disable intents in your Natural Language Understanding (NLU) models to make them active or inactive. Disable intents while editors or admins edit, review, or update its content and translations.
Assign an NLU editor to a model -- Assign an editor to review your Natural Language Understanding (NLU) model translations and edit model content. Delegate the maintenance, testing, and optimization of model content to an editor.
NLU Workbench - Advanced Features -- NLU Workbench - Advanced Features expands the functionality of NLU Workbench to help you manage and improve your models.
Install NLU Workbench - Advanced Features -- You can install the NLU Workbench - Advanced Features application (com.snc.nlu.workbench.advanced) if you have the admin role.
Multi-model Batch Testing -- Test multiple Natural Language Understanding (NLU) models against a large set of utterances to evaluate the performance of the models. Add test sets, test multiple models, and see test results.
Create a test set -- To create or add to an NLU test set, you can upload a file of test utterances matched with correct intents. Use the test set to assess the performance of your model.
Run a multi-model batch test -- Test multiple Natural Language Understanding (NLU) models against a test set. Evaluate the quality of your models and refine them to improve intent prediction.
Cross-model Conflict Review -- Identify conflicting intents within or across models so you can take corrective actions, resolve such conflicts, and improve your NLU model performance.
NLU Model Performance -- Use NLU Model Performance to see how well your models predicted intents in Virtual Agent (VA) based on end-user confirmation.
NLU Expert Feedback Loop -- Provide feedback on Virtual Agent chat log utterances to help the system continuously learn and to better predict user input.
Issue Auto Resolution tuning options -- When you are tuning your Issue Auto Resolution model in NLU Workbench, you can adjust the output for several goals: precision, automation, or a balance of the two. Compare how your choice of tuning options affect match rate and coverage, before committing.
Intent Discovery -- Use the Intent Discovery application to help identify opportunities for incident deflection. For example, you can use it to identify which Virtual Agent conversations to activate next.
Install Intent Discovery -- You can install the Intent Discovery application (sn_nlu_discovery) if you have the admin role.If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence:
Natural Language Query -- Natural Language Query (NLQ) enables you to query the data in your instance by entering plain language requests into the user interface.
Exploring Natural Language Query -- NLQ is a ServiceNow AI Platform feature that is active by default. Use NLQ to query the data in your instance by entering plain language requests into the user interface.
Using Natural Language Query -- With Natural Language Query (NLQ), you can query data in your tables by entering requests in natural, everyday language.
Configuring NLQ -- Enhance your users' query experience by supplementing NLQ with words and terms used in your environment. Review your users' actual requests in the NLQ logs to find possible synonyms and shortcuts to add.
Create an NLQ synonym -- Add synonyms to improve the ability of NLQ to recognize the various ways your users request data. With synonyms, you can map commonly used words or terms to table columns.
Create an NLQ shortcut -- Create a semantic shortcut to help improve the ability of NLQ to recognize the various ways your users request data. Semantic shortcuts operate similarly to NLQ synonyms by mapping common words to columns, but for a selected table when certain conditions are met.
View NLQ logs -- Review NLQ logs to see how the system has handled your users' plain-language requests. Use log records from attempted requests to expand NLQ synonyms or shortcuts.
View NLQ Table Guesser logs -- Use the Table Guesser logs to review the CMDB tables that were picked by NLQ in response to plain-language queries.
NLQ Admin [nlq_admin] -- Natural Language Query (NLQ) is installed with these roles.
AI Desktop Actions -- ServiceNow AI Desktop Actions enables you to design, configure, and manage desktop actions that automate repetitive tasks in your desktop and web environment. AI agents can autonomously and semi-autonomously process instructions, generate execution plans, and run desktop actions across legacy systems, thick client applications, and web applications without APIs.
Explore -- Create desktop actions with AI Desktop Actions to automate repetitive tasks on your desktop and web environment using AI agents and agentic workflows.
Design workspace -- The Design workspace is an interactive environment within AI Desktop Actions that enables you to create desktop actions by recording and configuring user interactions with desktop applications. The workspace provides a visual canvas where you can design multi-screen automation workflows that capture business processes across different applications.
Action recorder -- With Action recorder, you can capture steps to automate repetitive tasks in AI Desktop Actions. You can save the steps that you perform on application elements as a reusable desktop action.
Execution workspace -- Execution workspace enables you to test, run, and monitor your desktop actions. It enables you to observe how your automations interact with desktop applications, including handling situations where human input is needed.
Adaptive desktop actions for web -- Adaptive desktop actions enables AI agents to automate repetitive tasks across web applications through a browser extension. The agent interacts directly with the browser by clicking, typing, and scrolling, without preconfigured APIs, scripts, or back-end logic.
Supporting information -- Get a quick overview of the important information that is related to the AI Desktop Actions application.
Configure -- You can enable the AI Desktop Actions application if you have the admin role.If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence:
Defined desktop actions -- Configure AI Desktop Actions to execute predefined automation sequences on your desktop. Defined path actions provide consistent, repeatable workflows for common desktop tasks.
Download installer -- Download the AI Desktop Actions installer so that you can install AI Desktop Actions on your Windows machine for designing and running desktop actions.
Download and install .Net Desktop Runtime -- Reduce setup time and prevent installation errors by downloading and installing .Net Desktop Runtime following the instructions.
Enable AI agents to securely access parameters -- Enable AI agents to securely access stored values, such as credentials and other input data, through Desktop Action Parameter records. Parameters protect sensitive values and provide dynamic inputs to desktop actions during agent execution.
Create a Desktop action parameter record -- Create a Desktop action parameter record to store a name that an AI agent references when accessing credentials or other values during desktop action execution.
Create a parameter value record -- Create a Desktop action parameter value record to store the value that an AI agent retrieves during desktop action execution.
Adaptive desktop actions -- Adaptive path desktop actions automatically adjust their behavior based on user context and system conditions. Configure these settings to optimize desktop action performance and user experience across different scenarios.
Install the Chrome extension -- Install the ServiceNow Web Automation Chrome extension to the Google Chrome browser. The browser extension enables AI agents to interact with web applications during task execution.
Configure allowed websites -- Specify a list of websites that AI agents configured with adaptive desktop actions are permitted to open and perform tasks.
Design defined-path desktop actions -- Desktop actions enable you to automate repetitive tasks on your desktop and web applications. This capability helps you streamline repetitive tasks, improve efficiency, and integrate desktop application workflows into your ServiceNow processes.
Record steps with AI -- Create desktop actions by recording steps with AI to automate repetitive tasks in AI Desktop Actions. AI validates anchor positions and generates screen contexts automatically after recording, reducing the risk of automation failures at runtime.
Record steps without AI -- Create desktop actions by auto-capturing steps to automate repetitive tasks in AI Desktop Actions. You can save the steps that you perform on the application elements as a reusable desktop action of type on-screen task.
Manually capture steps -- Extend the automation logic in a desktop action by manually capturing steps in AI Desktop Actions.
Add details -- Add desktop action details, such as name, description, and associated applications, and review inputs and outputs.
Test and activate -- Test the desktop action and then activate it so that it’s available as a tool in the AI Agent Studio. You can add this tool to the AI agents that execute desktop actions in your desktop environment.
Screen, anchor, and step properties -- Learn about the properties of screens, anchors, and steps. There are multiple types of steps and each step type has distinct properties. You can update the properties to modify the behavior of the steps.
Increase payload limit -- By default, maximum 10 MB of file size is allowed in a scripted REST API request payload. Increase the payload limit to 15 MB by creating system properties in the global scope.
Create AI agents -- Create an AI agent in AI Agent Studio to mimic human-like intelligence while executing desktop actions for repetitive tasks in web and desktop environment.
Add defined desktop action for desktop and web-based tasks -- Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can execute defined path desktop actions for repetitive tasks in desktop and web environment.
Add adaptive desktop action for web -- Configure and add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can perform dynamic steps in the web environment.
Create an agentic workflow -- Create an agentic workflow in AI Agent Studio so that AI agents can coordinate to automate web tasks that are dynamic in nature.
Test an AI agent or agentic workflow -- Test an AI agent or agentic workflow that uses adaptive desktop actions in AI Agent Studio to evaluate its performance.
Desktop action examples -- Learn the key concepts and workflow for creating end-to-end desktop actions and building automations for your desktop environments.
Example: Badge management automation -- Automate various tasks related to badge requests through desktop actions using AI Desktop Actions and AI agents.
Example: Shipping order processing -- Automate various tasks related to shipping management through desktop actions using AI Desktop Actions and AI agents.
Execute desktop actions -- These examples explain how to trigger AI Agents that execute automations you designed using desktop actions. The following topics walk you through the end-to-end execution flow so you understand how AI-driven execution works in your desktop environment.
Example 1: Defined desktop action - recorder -- As an HR representative, automatically process various badge requests by triggering AI agents that use desktop action tools from the Now Assist panel.
Example 2: Defined desktop action - manual capture -- As a shipping coordinator, enter shipping details automatically from Excel to the Shipping Management app by triggering AI agents that use desktop action tools from the Now Assist panel.
Example 3: Adaptive desktop action for web -- Trigger an AI agent that uses adaptive desktop actions from the Now Assist panel. These desktop actions perform tasks on an external website or web application.
Delete an AI agent chat log -- After you close an AI agent session, you can delete its chat if any sensitive information was captured. Deleting your chat log permanently erases the chat history of that session, including screenshots.
Reference -- Reference topics provide additional information about the roles and tables that are installed with the AI Desktop Actions application.
Components installed -- Several types of components are installed with activation of the sn_desktop_agents plugin, including user roles and tables.
System requirements and limitations -- Be aware of system requirements and a few limitations when you’re using the AI Desktop Actions application for defined desktop actions.
Glossary -- Learn about the terms and concepts that are unique to AI Desktop Actions.
A -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Action recorder -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Desktop session -- Learn about the terms and concepts that are unique to AI Desktop Actions.
E -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Execution status -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Execution workspace -- Learn about the terms and concepts that are unique to AI Desktop Actions.
M -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Manual capture -- Learn about the terms and concepts that are unique to AI Desktop Actions.
N -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Now Assist panel -- Learn about the terms and concepts that are unique to AI Desktop Actions.
O -- Learn about the terms and concepts that are unique to AI Desktop Actions.
On-screen task -- Learn about the terms and concepts that are unique to AI Desktop Actions.
P -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Parameter record -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Parameter Value record -- Learn about the terms and concepts that are unique to AI Desktop Actions.
S -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Screen -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Smart sizing -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Step -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Step in / Step out -- Learn about the terms and concepts that are unique to AI Desktop Actions.
T -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Tool -- Learn about the terms and concepts that are unique to AI Desktop Actions.
Predictive Intelligence -- Predictive Intelligence is a powerful interface to train machine learning models. With Predictive Intelligence, you can improve performance, efficiency, and flexibility to your systems across multiple business units.
Explore Predictive Intelligence -- ServiceNow Predictive Intelligence is a platform function that provides a layer of artificial intelligence that empowers features and capabilities across ServiceNow applications to provide better work experiences.
Predictive Intelligence frameworks -- Predictive Intelligence provides three different model frameworks in the Australia release: classification, similarity, and clustering. Each framework specializes in different types of predictions.
Create a word corpus -- Build a collection of words and phrases that functions as the vocabulary the system uses to compare your instance records based on their textual similarity. You can think of the word corpus as a dictionary that you want your machine-learning system to understand.
Quick start tests for Predictive Intelligence -- Validate that Predictive Intelligence still works after you make any configuration change such as applying an upgrade or developing an application. Copy and customize these quick start tests to pass when using your instance-specific data.
Activate a solution version -- Predictive Intelligence activates the most recent version of the solution when it completes training a solution. However, you can activate any previously trained solution version. Only one solution version can be active at a time, and only the active version is used when making predictions.
Export trained solutions to production -- Refine and test your ML solutions iteratively on a non-production instance, and then use update sets to export the changes to your production instance. This practice mitigates the risk of retraining solutions on your live production instance.
Configuring advanced settings for your ML solutions -- Learn about advanced settings for your Predictive Intelligence machine learning (ML) solutions. Apply optional technology and algorithms for classification, clustering, similarity, and regression capabilities.
Configure class recall for a classification solution -- Create and apply a class recall parameter to an ML solution prior to training its data. For example, you set and apply this solution parameter to 90% recall for all records in the Email class.
Configure TF-IDF for solutions -- Apply Term Frequency–Inverse Document Frequency (TF-IDF) encoding to classification, clustering, or similarity solutions for Predictive Intelligence.
Configure DBSCAN for a clustering solution -- Consider applying the Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to your clustering solution. DBSCAN is available as an alternative to the default clustering algorithm, k-means.
Configure HDBSCAN for a clustering solution -- Consider applying the Hierarchical Density Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm to your clustering solution. HDBSCAN is available as an alternative to the default clustering algorithm, k-means.
Configure include only top N labels -- Limit your classification model to use only the most common classes when training. You can specify the number of classes to use.
Remove others label -- Reduce noise in your classification model and enhance predictive accuracy by removing records with the label "others" from training data. These are records with a distribution frequency of under one percent.
Creating and training solutions -- Use one of the Predictive Intelligence (PI) frameworks to create and train machine-learning solutions. Each framework delivers a different solution type for training the system to predict, recommend, and organize data outcomes.
Create and train a classification solution -- Specify the records used to train a classification solution, what fields trigger a prediction, and how often you want to retrain your solution.
Exclude a class from prediction -- Exclude a class from prediction if its precision or coverage aren't satisfactory. Excluding a class prevents the classification model from predicting a particular output field value.
Exclude a class from solution training -- Exclude a class from solution training to prevent the model from ever making predictions for a particular output field class. For example, you can exclude a particular incident category from training if you plan to retire or change the category.
Tune a trained classification solution -- Tune the performance of a trained classification solution by configuring class level precision and coverage values.
Using Group By for classification -- Use APIs to simultaneously submit multiple classification solutions for training based on the Group By field.
Model Explainability -- Analyze the importance of each input field to your model's predictions using model explainability. Create a Workflow Classification model that includes a graphical analysis of feature importance by executing the provided script.
Create and train a similarity solution -- Create and train a machine learning solution to collect and compare your existing records to new similar records. For example, you can compare the text in an open Incident record to a resolved Incident record to reuse its resolution.
Update your similarity score threshold -- After you review the similarity examples provided by the system, update your solution similarity score threshold if you want the results returned by the solution to be more or less similar.
Apply purity on a clustering solution -- Apply purity to learn details about the composition of each cluster. For example, see what percentage of incidents in a cluster have the same value for Assignment Group. You can specify which fields to focus on, or you can let auto-purity display fields by default.
Analyze a cluster with Cluster Insight -- Analyze a cluster by a field available on the source table. With the Cluster Insight check box, you can add a filter condition on your input field when you review the list of results.
Create and train a regression solution -- Regression solutions have been deprecated. They could be used to predict numeric outputs, such as a temperature or a stock price.
View solution training progress -- View your solution training progress or statistics to determine if a solution is available, or how long the next training cycle might take to complete.
Review classification solution statistics -- The Solution Statistics dashboard in Predictive Intelligence has been deprecated in the Xanadu release. It provided precision and coverage statistics for each class in a classification solution.
Review solution similarity examples -- Review the similarity examples generated during solution training to determine whether the similarity score threshold meets your business requirements.
Using Predictive Intelligence -- Train and use Predictive Intelligence solutions to accomplish various tasks and that integrate with other ServiceNow products, such as Document Intelligence and Task Intelligence.
Using Machine Learning APIs -- Use ServiceNow Machine Learning (ML) APIs to train Machine Learning models and run inferences.
ML API class overview -- Use ServiceNow Machine Learning (ML) APIs to train Machine Learning models and run inferences.
Reviewing your ML solution training jobs -- Use the ML Solutions (ML Training Jobs view) module to monitor the training status and progress for Predictive Intelligence solutions. The module displays training jobs for both user interface and API solutions.
Using MLSolutionFactory scriptable objects -- MLSolutionFactory scriptable objects enable defining ML functionality. You can use the APIs to compose data-driven functionality, such as subclustering large clusters or clusters with multiple PRBs attached.
Testing and monitoring predictions -- Evaluate the coverage and precision of your machine-learning (ML) solutions by testing them. Once deployed, track their performance over time. Improve predictions by using performance information to refine your solutions.
Test a classification solution prediction -- Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer to test a classification solution prediction for incident categorization.
Test a similarity solution prediction -- Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer application to test a similarity solution prediction for resolved incident recommendations.
Track classification prediction results over time -- Use the Prediction Results dashboard to determine if classification solution predictions are improving over time. Identify solutions that need refining or retraining.
Reviewing prediction errors with the Observability Dashboard -- The Observability Dashboard offers a unified view and actionable insights for errors detected in Predictive Intelligence. Use this dashboard to visualize logged errors and gain information on prediction reliability and potential problem areas.
Predictive Intelligence Usage Analytics dashboard -- The Predictive Intelligence Usage Analytics dashboard is a central location to understand the effectiveness and overall value of all your Predictive Intelligence solutions. View metrics for model training successes and failures. Monitor prediction statistics including breakdowns by individual model.
Domain separation and Predictive Intelligence -- Domain separation is supported in the Predictive Intelligence application. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
Predictive Intelligence language support -- Predictive Intelligence provides international language support. Learn which languages are available to Predictive Intelligence solutions.
Predictive Intelligence properties -- The properties for Predictive Intelligence control certain parameters of its machine-learning solutions, solution training process, and caching.
Now Assist in Document Intelligence -- With ServiceNow Now Assist in Document Intelligence, you can use generative AI to get key information from digital documents into your automation workflows.
Explore -- With Now Assist in Document Intelligence, you can use generative AI to extract key information from your documents and images for use in your workflows.
Use cases -- In Now Assist in Document Intelligence, a use case is used to define the information you want generative AI to detect from a document.
Document Intelligence workspace -- Use the Document Intelligence workspace to review the generative AI predictions made by Now Assist for a document or image file. You can also identify missing information in the file.
Supporting information -- Get a quick overview of the important information that is related to the Now Assist in Document Intelligence application.
Configure -- If you have the admin role, you can configure the Now Assist in Document Intelligence feature, enabling agents to use its generative AI skills within their application workspace.
Activate a skill -- Activate the Now Assist in Document Intelligence skills that agents can use to help analyze and extract information from documents with generative AI.
Set up a use case -- Create a use case record to define a document you want to process with Now Assist in Document Intelligence.
Turn on Full automation mode -- Turn on Full automation mode to automatically complete and submit document tasks without an agent review. Full automation mode is turned off by default in use cases.
Change the use case LLM -- Choose the language models for a Now Assist in Document Intelligence use case.
Edit a use case -- Edit a use case to change the name, fields, tables, questions, and integrations.
Make a copy of a use case -- Make a copy of a use case to save time when you need to create a new use case with a similar structure.
Deactivate a use case -- Deactivate a use case that you don’t want to use for your documents.
Delete a use case -- Delete a use case when it is no longer needed for your documents.
Use -- If you have an agent role, you can use the Now Assist in Document Intelligence workspace to analyze and extract information from your documents with generative AI.
Review extracted information -- Use the Document Intelligence workspace to review the information that was extracted from a document or image file by Now Assist in Document Intelligence.
Reference -- The following topics provide additional information about the features and properties installed with Now Assist in Document Intelligence.
Components installed -- Components are installed with the activation of Now Assist in Document Intelligence.
Data extraction modes -- The extraction mode determines how Now Assist in Document Intelligence processes a document task.
Document and visual insights AI agent -- The document and visual insights AI agent gathers context from user input and document or image attachments, generates the requested information based on the content, and provides the information along with any relevant task details.
Document Intelligence in Now Assist Skill Kit -- Use the Document Intelligence tool to leverage extraction, question answering, and summarization capabilities for a skill created with Now Assist Skill Kit.
Field types -- The field type specifies the information that is retrieved from a document with Now Assist in Document Intelligence.
Forms -- Use forms to view and update Now Assist in Document Intelligence information.
Question form -- The Question form enables you to define a question you want to ask about the document.
Field form -- The Field form enables you to define a single field for extraction.
Table form -- The Table form enables you to define a table for extraction.
Limitations -- There are several important limitations to be aware of when you’re using Now Assist in Document Intelligence.
LLMs -- Now Assist in Document Intelligence uses large language models (LLMs) to perform generative AI and agentic AI capabilities.
Supported languages -- Now Assist in Document Intelligence supports text in multiple languages.
Document Intelligence -- Document Intelligence (DocIntel) is an AI solution that enables any organization to automate and accelerate the process of extracting data from documents. That data can easily be integrated into larger automation workflows to save time and resources.
Explore -- Document Intelligence helps you to quickly and accurately classify and extract information from documents using artificial intelligence (AI).
Configure -- Activate Document Intelligence on your instance and get started with basic configuration.
Set up DocIntel -- Review the following information before you start setting up Document Intelligence.
Install DocIntel -- You can install Document Intelligence (sn_docintel) and Document Intelligence Admin (sn_docintel_admin) if you have the admin role. The sn_docintel_admin application installs related ServiceNow Store dependencies if they aren’t already installed.
Upgrade to version 3.0 or later -- Document Intelligence 3.0 or later includes an updated database schema to support its transition from a scoped application to a ServiceNow AI Platform plugin.
Configure settings -- Use general settings to control how Document Intelligence displays information to users.
Set up document extraction use cases -- In Document Intelligence, a use case is used to define the structure of a type of document you want to process. It's made up of the use case record and its related fields, field groups, integrations, flows, and all the related machine learning (ML) models.
Create a use case -- Create a use case record to define a document you want to process in Document Intelligence. For example, invoices or driving licenses.
Create a field -- Set up fields as part of your use case. Document Intelligence uses fields to identify and extract data from documents. Fields can be grouped to help DocIntel extract data from documents with tables, check box lists, and other logical groupings of fields.
Deactivate a field -- Deactivate fields that you don’t want to use as part of your use case.
Configure data extraction modes -- Configure the extraction modes for use cases to define how Document Intelligence extracts fields from documents.
Manage document extraction use cases -- Manage your Document Intelligence use cases to efficiently support your document extraction requirements.
Duplicate a use case -- Make a copy of a use case to save time when you want to create a new use case that shares a similar structure to another.
Export a use case -- Export a document extraction use case for use in another ServiceNow instance by adding it to an update set.
Import a use case -- Import a document extraction use case for use in your ServiceNow instance.
Delete a use case -- Delete a use case when it’s no longer needed for your documents.
Set up document classification use cases -- A document classification use case is a set of categories used to classify your documents and their individual pages. It’s made up of the use case record and its related fields (classes), and all related machine learning (ML) models.
Create a use case -- Create a use case record to begin defining the classes or categories that you want to apply to a type of document or pages within the document.
Create a document class -- Create fields as part of your document classification use case. Document Intelligence uses fields to define the classes or categories to apply to documents.
Train a use case -- Train the document classification use case with user input from completed document tasks to improve Document Intelligence recommendations over time.
Delete a use case -- Delete a use case when it's no longer needed for your documents.
Manage field values -- View the field values gathered from your processed document tasks. Review the values and add any additional information.
Integrate -- Extend the capabilities of Document Intelligence to other ServiceNow applications. Other applications can take advantage of document classification and extraction using Document Intelligence.
Integrate with a custom application or workflow -- Configure an integration to trigger document task processing or value extraction. Integrations can be used to quickly set up flows with other applications.
Integrate with CSM -- Document Intelligence provides document extraction capabilities to Customer Service Management (CSM). Extract relevant information from email and case attachments, such as credit card numbers or customer addresses, and add that information to cases.
Integrate with FSO -- Document Intelligence provides document extraction capabilities to Financial Services Operations (FSO).
Integrate with APO -- Document Intelligence provides document extraction capabilities to Accounts Payable Operations (com.sn_ap_ic).
Integrate with Automation Center -- Use Automation Center to discover opportunities to automate document processing with Document Intelligence.
Use -- Use document tasks to process documents for classification and data extraction in Document Intelligence.
Create a document task -- Create a document task and upload single or multi-page documents that are in JPEG, PNG, or PDF formats to start extracting text or classifying documents.
Complete a document task -- After the document task processing is finished, complete the task by providing input or review to train the AI.
Extract fields -- Use the Document Intelligence workspace for field extraction, searching for recommendations, flagging fields, and identifying missing fields to complete document tasks.
Extract single fields -- Use the Document Intelligence workspace for field extraction, searching for recommendations, flagging fields, and identifying missing fields to complete document tasks.
Extract check box fields -- Use the Document Intelligence workspace for field extraction, searching for recommendations, flagging fields, and identifying missing fields to complete document tasks.
Extract table fields -- Use the Document Intelligence workspace for field extraction, searching for recommendations, flagging fields, and identifying missing fields to complete document tasks.
Classify documents -- Use the Document Intelligence workspace to label your documents. The workspace enables you to train the AI model by providing direct input and by validating or correcting the recommendations provided by DocIntel.
Classify documents and document pages -- Use the Document Intelligence workspace to label your documents. The workspace enables you to train the AI model by providing direct input and by validating or correcting the recommendations provided by DocIntel.
Monitor -- Track document extraction performance in Document Intelligence to understand its usage and effectiveness.
Use case performance dashboard -- Monitor Document Intelligence (DocIntel) performance at the use case and field levels in the use case performance dashboard.
View the use case performance dashboard -- Monitor Document Intelligence (DocIntel) performance at the use case and field levels in the use case performance dashboard.
Reference -- The following topics provide additional information about the features and properties installed with Document Intelligence.
Components installed with DocIntel -- Several types of components are installed with activation of the Document Intelligence plugin, including tables and user roles.
Confidence scores -- A confidence score is a measurement (percentage) of how reliable DocIntel is in providing a recommendation for a field. The higher the score, the more reliable the recommendation.
Data extraction modes -- Extraction modes determine how the data is extracted in the document task and how the task is processed. The mode changes the behavior of the fields in the Document Intelligence workspace.
Data normalization -- Certain types of data extracted from documents are converted into a standard format so that they appear the same across all fields.
Document field statuses -- The following is a list of the statuses for fields in DocIntel document tasks. These statuses apply to fields for both document classification and data extraction.
DocIntel forms -- Use forms to view and update Document Intelligence information.
Check box list form -- The Check box list form enables you to define a check box list for extraction.
Single field form -- The Single field form enables you to define a single field for extraction.
Single field group form -- The Single field group form enables you to define a related group of single fields for extraction.
Table form -- The Table form enables you to define a table for extraction.
Properties -- Document Intelligence (DocIntel) system properties control the behavior of the Document Intelligence application.
Roles -- Document Intelligence is installed with these roles.
Terminology -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
classification -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
confidence score -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
document class -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
document task -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
extraction -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
field -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
field group -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
field value -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
recommendation -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
unstructured document -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
use case -- Before getting started with Document Intelligence (DocIntel), it's important to understand some key concepts used in the application.
Document task statuses -- The following is a list of the statuses for DocIntel document tasks. These statuses apply to tasks for both document classification and data extraction.
Domain separation -- This domain separation overview relates to Document Intelligence. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can then control several aspects of this separation, including which users can see and access data.
Supported languages -- The Document Intelligence application provides support for documents in different languages.
DocIntel limitations -- There are several important limitations to be aware of when you’re using Document Intelligence.
Task Intelligence -- Task Intelligence uses machine learning to train solutions with your data and achieve important outcomes.
Exploring Task Intelligence -- Learn more about Task Intelligence and how machine learning models can learn from your data to make predictions and achieve important outcomes.
Configure Task Intelligence -- Configure and install the Task Intelligence Admin Console and its related applications.
Install Task Intelligence Admin Console -- You can install the Task Intelligence application (sn_ti_admin) if you have the admin role.If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence: The application includes demo data and installs related ServiceNow Store applications and plugins if they are not already installed.
Create a Task Intelligence model -- Create machine learning models to predict field values, analyze case sentiment, or detect case language.
Edit a Task Intelligence model -- Retrain your machine learning models or edit what they predict to better align with your business goals.
Assess a Task Intelligence model -- Assessing a machine learning model's performance helps determine how to use and train the model to achieve your desired outcomes.
ServiceNow AI Lens -- With ServiceNow AI Lens, which is a ServiceNow Now Assist application, you can use generative AI to scan, extract, comprehend, and synthesize data to optimize your workflows.
Explore -- ServiceNow AI Lens is a ServiceNow Now Assist application that uses generative AI to scan images and screens, extract information, understand visual data, and take action—such as automatically filling in forms with scanned information—to help improve your workflows.
ServiceNow AI Lens features -- Learn about the various ServiceNow AI Lens features to help you get started with analyzing and gathering insights from the visual data.
Landing page overview -- Learn about the ServiceNow AI Lens desktop application landing page.
Supporting information -- Get a quick overview of the important information that is related to the ServiceNow AI Lens application.
ServiceNow AI Lens skill -- This skill provides generative AI capabilities to read, understand, respond, and act on visual data such as hand-written texts, images, and websites and take powerful actions to boost productivity.
Configure -- If you have the admin role, you can enable the ServiceNow AI Lens application (sn_ai_lens) to extract and comprehend data for various workflows.
Activate the ServiceNow AI Lens skill -- Activate the ServiceNow AI Lens skill to start using generative AI to scan and analyze visual data such as scan artifacts such as images, scanned handwritten notes, Excel sheets, web pages and optimize your workflows.
Download the ServiceNow AI Lens installer -- Download the ServiceNow AI Lens installer so that you can install the ServiceNow AI Lens on your system for scanning visual data.
Set up auto-login for ServiceNow AI Lens -- Pre-configure your organization's ServiceNow instance URL so that it appears ready-filled when users launch the ServiceNow AI Lens desktop application, and enable auto-login so that users can skip signing in on subsequent launches.
Define default instructions -- Create a system property to define default instructions for ServiceNow AI Lens execution on a specific form.
Creating Lens actions -- As a Lens admin, you can create Lens actions in ServiceNow AI Lens to customize Lens behavior by providing default instructions, configuring context, and more.
Example: Auto-fill user records on a user table -- As a Lens admin, you can create Lens actions in ServiceNow AI Lens to customize Lens behavior by providing default instructions, configuring context, and more.
Use -- If you have a lens_user role, and have activated the ServiceNow AI Lens skill, you can use the ServiceNow AI Lens application to capture screens or upload files, extract and comprehend data from the captured screenshots or uploaded files, auto-fill form fields, or preview the extracted data.
Create a record in an instance -- Create a record in the ServiceNow instance by auto-filling the form fields with data that ServiceNow AI Lens extracts from captured screens, documents, and files.
Update a record from an instance -- Update a record in the ServiceNow instance by auto-filling the form fields with data that ServiceNow AI Lens extracts from captured screens, documents, and files.
Auto-fill catalog item form in the Service Portal -- Use ServiceNow AI Lens to extract data from documents and auto-fill catalog item forms in Service Portal. For example, auto-fill a new vendor onboarding form by extracting key details such as vendor name, address, contact email, and banking information from multiple documents, that includes Excel files, emails, images, and PDF documents.
Trigger ServiceNow AI Lens from the desktop app -- Trigger ServiceNow AI Lens from the desktop app by using a Lens action to preview the extracted data and initiate post processing or auto-fill a form.
Extract and analyze data with ServiceNow AI Lens in Virtual Agent -- Extract and analyze data from an image using ServiceNow AI Lens from a Virtual Agent conversation on a mobile device or a portal. ServiceNow AI Lens can scan an image and then gather insights or provide recommendations as per your instructions.
Reference -- Reference topics provide additional information about the roles and tables that are installed with the ServiceNow AI Lens application.
Components installed -- Several types of components are installed with the activation of the ServiceNow AI Lens plugin, including user roles.
Field types supported -- Learn about the field types that are currently supported with the ServiceNow AI Lens application.
Limitations -- Be aware of a few limitations when you’re using the ServiceNow AI Lens application.
Script include - AILensActionService -- Use the AILensActionService script include together with Lens actions to leverage ServiceNow AI Lens as a service for extracting information from the provided images and getting answers to your questions.
AILensActionService - AILensActionService() -- Use the AILensActionService script include together with Lens actions to leverage ServiceNow AI Lens as a service for extracting information from the provided images and getting answers to your questions.
Conversation Insights -- The ServiceNow Conversation Insights application is designed to deliver Inferred customer satisfaction (CSAT) scores, with underlying factors that can help improve CSAT actionability.
Exploring Conversation Insights -- Learn how Conversation Insights can help you to augment conversation insights with AI-based Inferred customer satisfaction (CSAT) scores and factors.
Install Conversation Insights -- If you have the admin role, you can install the Conversation Insights application (sn_aci).If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence:The application includes demo data and installs related ServiceNow Store applications and plugins, if they aren’t already installed.
Conversation Insights reference -- The following topics provide additional information about the features and properties installed with Conversation Insights.
Conversation Improvement Themes -- The Conversation Improvement Themes application helps to transform Conversation Evaluators evaluations that are part of AI Control Tower into long-term performance insights by analyzing conversation quality data over time.
Explore -- The Conversation Improvement Themes application helps to transform conversation evaluations into long-term performance insights.
Activate -- Activate the Conversation Improvement Themes application to analyze conversation quality.
Use -- View performance insights using the widgets in Conversation Improvement Themes.
Reference -- The following topics provide additional information about the features and properties installed with Conversation Improvement Themes.
Components installed -- Several types of components are part of Conversation Improvement Themes, including scheduled jobs, tables, system properties, and flows.
Trobleshooting -- Troubleshooting steps for errors that might occur in Conversation Improvement Themes.
Additional resources for AI products and solutions -- If you’re looking for AI best practices, troubleshooting, or other implementation guidelines, select a feature or resource type to discover ServiceNow resources on other relevant websites.