Now Assist AI agents release notes
Summarize
Summary of Now Assist AI agents release notes
The ServiceNow® Now Assist AI agents application, introduced in the Yokohama release, enables AI-powered agents to perceive environments, make decisions, and proactively act to achieve goals with minimal human oversight. This application supports automation and enhancement of case, incident, and task resolution through AI agents and agentic workflows, improving operational efficiency and customer interactions.
Show less
Now Assist AI agents integrates with multiple AI model providers including Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. It supports multilingual conversations, dynamic orchestration for improved workflow accuracy, and includes comprehensive analytics to track performance and customer satisfaction.
Key Features
- Agentic Workflows: Complex task execution plans formerly called "use cases," now enhanced to automate and resolve incoming cases and incidents.
- AI Agent Studio: Centralized environment to create, test (manual and automated), duplicate, and manage AI agents and agentic workflows with version control for LLM instructions.
- Role Masking and Security Controls: Restrict access and execution of AI agents and workflows based on configured roles to protect data and meet business requirements.
- Interactive and Non-Interactive Modes: AI agents can interact directly with users or operate silently by sending execution outputs without user interaction.
- Integration with Virtual Agent and Now Assist Panel: AI agents can be accessed and managed through Virtual Agent conversations and the Now Assist panel, supporting multiple simultaneous conversations.
- Knowledge Graph and Tool Enhancements: Use Enterprise Graph resources, desktop automation tools, and custom output transformation strategies to tailor AI agent behavior and outputs.
- Analytics and Monitoring: AI Agent Analytics dashboard provides insights into agent performance, customer satisfaction, and usage metrics to optimize AI interactions.
- Dynamic Orchestrator: Maps appropriate AI agents to workflows, enhancing performance and accuracy.
- Now Assist Guardian: Automatically detects and blocks offensive messages in AI agent interactions.
- Voice Input and Accessibility: Optional voice-to-text input for the Now Assist panel supports diverse user needs including mobility impairments and multilingual usage.
Practical Application and Configuration
- Creating and Managing AI Agents: Customers can create AI agents to handle tasks such as data gathering, decision-making, and automating repetitive processes using various tools like catalog items, conversational topics, and web search.
- Agentic Workflow Execution and Supervision: AI agents execute workflows within the Now Assist panel, Core UI, and workspaces, providing detailed execution histories and supervision information.
- Security and Access Control: Configure ACLs to control who can discover and trigger AI agents and workflows, and specify user impersonation modes.
- Testing and Evaluation: Use manual and automated testing options in AI Agent Studio to validate AI agent behavior and workflow outcomes before deployment.
- Email Notifications: Configure alerts for unexpected AI agent or workflow behavior to ensure prompt corrective actions.
- External AI Agent Integration: Connect third-party AI systems via Agent2Agent protocol or manual integration for extended capabilities.
Important Considerations
- Now Assist AI agents require installation of the supported Now Assist ServiceNow version and activation via the ServiceNow Store.
- Browser support includes Google Chrome and Microsoft Edge; Internet Explorer is not supported.
- Data policy compliance is necessary when enabling web search tools using Google as a provider due to potential data routing outside specified regions.
- Usage measurement for Now Assist transitioned to a burn-down model aligned with contract anniversary dates starting with Yokohama Patch 5.
Related ServiceNow Features
- Now Assist Panel: Provides conversational AI assistance to summarize and resolve issues efficiently.
- Generative AI Controller: Facilitates integration of third-party large language models into workflows.
- AI Search: Enhances search capabilities across Service Portal, Now Mobile, and Virtual Agent.
- Now Assist Skill Kit: Enables creation and publishing of custom AI prompts and skills for tailored generative AI experiences.
The ServiceNow® Now Assist AI agents application provides solutions that can perceive the environment, decide, and proactively act to achieve specific goals without the need for constant human oversight. Now Assist AI agents is a new application in the Yokohama release.
Now Assist AI agents highlights for the Yokohama release
- Review changes to Now Assist usage measurement.
- Execute agentic workflows, AI agents, and tools in AI Agent Studio with role masking.
- Additional role configuration is required for agentic workflows and AI agents included with Now Assist applications.
- Run and review agentic workflow executions on forms in the Core UI and workspaces.
- Framework extensibility with a new condition builder.
- Support multilingual conversations.
- Create and maintain versions of LLM instructions for AI agents and agentic workflows to help organize and iterate on prompts and test their effectiveness.
- Follow updated guided setup steps for agentic workflows and AI agents with additional guidance for successful instructions sent to the LLM.
- Duplicate existing script, record operations, and search retrieval tools to reduce the work needed to create unique AI agents.
- Monitor new analytics in the AI Agents Analytics dashboard to track valuable insights in customer satisfaction with AI interactions.
- Use Google Gemini and Anthropic Claude on AWS as AI model providers for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI.
- View the agentic workflow and AI agent activity on your AI Agent Studio.
- Map the right agents for agentic workflow execution with Dynamic orchestrator in Virtual Agent for better performance and accuracy.
- Create different types of AI agents.
- Custom output transformation strategies for an AI agent.
- Execute AI agents and agentic workflows from workspace or Core UI.
- Run AI agents and agentic workflows in a non-interactive execution mode.
- Use cases in Now Assist AI agents are now called agentic workflows.
- Choose either Azure OpenAI or Now LLM Service as your preferred large language model (LLM) for AI agents and agentic workflows in the AI Agent Studio settings.
- Use Virtual Agent for AI agent interactions.
- Execute agentic evaluation runs to evaluate agentic workflows based on execution log data to compare against benchmarks and monitor performance.
- Improve the quality of LLM responses by passing information between tools.
- Hide citations for an agentic workflow or AI agent.
- Transactions done by an AI agent for an agentic workflow are recorded in the name of the AI agent.
- Enable AI agents to store and retrieve memories with categories.
- Use Knowledge graph and File retrieval as tools in creating an AI agent.
- Define agentic workflows with an execution plan for automatically resolving the incoming cases and incidents.
- Use the Now Assist panel to communicate with the agent during issue resolution.
- Clone existing AI agents and agentic workflows to save time and avoid manual configuration.
- Enable Now Assist Guardian to automatically identify and block offensive messages.
- View the usage and performance of your AI agents with the AI agent analytics dashboard.
- Enable multiple conversations for AI agents on the Now Assist panel.
See Now Assist AI agents for more information.
For the Platform Now Assist release notes, see Now Assist release notes.
Now Assist AI agents features
- Yokohama Patch 11
- Configure role masking for AI agents and agentic workflows
- Role masking restricts access to specific roles based on configuration to verify that agentic workflows, AI agents, and tools run within the boundaries of the roles configured to meet their business needs while reducing the risk of unauthorized access to the agents and the agentic data.
- Add AI agent learning
- Enhance AI agent learning through episodic memory, enabling AI agents to improve by learning from past successful interactions.
- Select channels and access for an agentic workflow
- Create and update UI actions for workflow executions and display handling. You can specify conditions for the display of the UI actions.
- Add a desktop action to an AI agent
- Add Desktop action as a tool to an AI agent to perform desktop automation for repetitive tasks.
- Configuring Now Assist AI agents
- Support multilingual conversations for AI agents across languages.
- Manually test the execution of an AI agent and Manually test the execution of an agentic workflow
- The testing page on AI Agent Studio has two testing options:
- Manual test
- Automated evaluation
Observe the different versions of an AI agent behavior in manual tests and in automated evaluations using the Manual tests and Automated tests tabs.
- Test user access to an AI agent and Test user access to an agentic workflow
- Test how an AI agent or agentic workflow completes a task and if it enables users permission to access it.
- Model Context Protocol Client
-
- Authorization upgrades to support segregation of Resource Server and Authentication Server through Protected Resource Metadata (PRM).
- Use the mcp_guardian_check property to enable guardian checks for MCP Client when there’s an MCP tool call.
- Supervise the pagination with mouse device support to show large number of services from an MCP server through the sn_mcp_client.cursor.max_iterations system property.
- Add a title field for human-friendly display names that can be used as a programmatic identifier.
- Use in-product experiences for agentic workflows on forms
- In the Core UI and workspaces, you can use UI and declarative actions to run agentic workflows. You can also see the presence, progress, and output of agentic workflows performed on a record. The execution details for each agentic workflow include who is supervising the workflow, estimated and total time taken, processing messages, and step history.
- Review and approve requests and tickets with the Approval Assistance AI agent
- You can use the new approval assistance AI agent to view all pending approval requests and access detailed information about them. You can then approve requests and tickets and make updates to them from Now Assist in Virtual Agent.
- Configure email notification alerts for AI agent and agentic workflow executions
- Configure alert email notifications for unexpected or undesired behavior from AI agents and agentic workflows. You can configure the thresholds for triggering the alerts on the Agent Properties table, and you can add or update the recipients of the email notifications from the Notifications table.
- Create an external AI agent
- Create new external AI agents that connect to third-party agentic AI systems. Use Agent2Agent protocol or integrate agents manually to configure them in AI Agent Studio to use in the ServiceNow agentic AI system.
- Add a Knowledge Graph to an AI agent
- Use Enterprise Graph (Small) as a resource to create a Knowledge Graph tool for an AI agent in the AI Agent Studio.
- Yokohama Patch 6
- AI Agent Studio
- View and troubleshoot the agentic workflow and AI agent executions on AI Agent Studio.
- Configuring Now Assist AI agents - Dynamic Orchestrator
- Maps the right agents for an agentic workflow with Dynamic Orchestrator for better performance and accuracy of the agentic workflow execution.
- View analytics for customer satisfaction with AI interactions
- Multiple new metrics have been added to the AI Agent Analytics dashboard, accessible from the AI Agent Studio to provide insight into average customer satisfaction and customer satisfaction with the best and worst performing agentic workflows and agents.
- New third-party AI model provider options available for all Now Assist applications
- Google Gemini and AWS Claude are available for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI.
- Add tools and information to an AI agent
- The output transformation strategy for an AI agent output now contains a new option called Custom.
With Custom output transformation strategy, a Transformation Instructions field with a text area is enabled for the user to provide their specific instructions for refining the output as per the agentic workflow. The instructions will also ensure that the transformation is done as per the user's need.
- Configuring Now Assist AI agents - AI Agent Background Channel
- Invoke the agentic conversations from the Workspace or Core UI via the AI Agent Background channel, that is associated with the AI Agent Background Provider, to execute the AI agents and agentic workflows.
- Configuring Now Assist AI agents - Interactive and non interactive AI agents
- Run AI agents and agentic workflows execution in one of the following ways:
- Interactive Mode: AI agents reach out to the user for information during fallback.
- Non interactive Mode: AI agents do not reach out to the user during fallback but send the execution output to the user.
- Yokohama Patch 3
- Select Virtual Agent as a display option for AI agents
- Choose to display AI agent output in Virtual Agent. You can also discover AI agents in Virtual Agent conversations.
- Disable citations in AI Agent Studio
- Disable citations for specific agentic workflows or AI agents in AI Agent Studio where citations are not required or involve confidential information.
- Create an AI agent
-
- Long term memory: Add or delete categories for AI agents to store and retrieve memories.
- Additional tools available while creating an AI agent.
- Knowledge graph
- File retrieval
- Evaluate agentic workflows and AI agents
- In Now Assist Skill Kit, you can execute evaluation runs for your agentic workflows. You can select evaluation plans and the execution log datasets to judge whether your agentic workflows are consistently completing tasks and using the correct tools.
- Yokohama Patch 1
- Create an AI agent
- Create an AI agent to assist your live agents while resolving cases, incidents, or tasks:
- Create AI agents to gather data, make decisions, and complete tasks that would otherwise need to be done by a human.
- Add one of the following tools or information sources for the AI agent to execute:
- Catalog item
- Conversational topic
- Flow action
- Now Assist skill
- Record operation
- Script
- Search retrieval
- Subflow
- Web search
- Create an agentic workflow
-
Create an agentic workflow with an execution plan to solve complex tasks with Now Assist. You can also do the following tasks:
- Clone an existing agentic workflow to avoid manual configuration.
- Create triggers when creating an agentic workflow that calls the AI agent when a condition or objective is observed.
- Test an agentic workflow before execution.
- Resolve record-based cases with AI agents.
- Enable Now Assist Guardian in AI agents
- Enable Now Assist Guardian in AI agents to automatically identify and block offensive messages that are sent by human agents.
- Multiple conversations in Now Assist AI agents
- Enable live agents to interact with multiple AI agent conversations through the Now Assist panel.
- AI Agent Analytics dashboard
- Analyze the performance, efficiency gain, and usage of AI agents through preconfigured dashboards.
UI changes
- Yokohama Patch 11
- Create an AI agent
- The guided setups for creating an AI agent and agentic workflow have been updated.
- Define security controls for an agentic workflow and Define security controls for an AI agent
- New security configuration UI pages have been added in the AI Agent Studio application to configure security controls for agentic workflows and AI agents for role masking.
- Yokohama Patch 6
- Follow new guided setups for agentic workflows and AI agents
- The new steps for the guided setups for AI voice agents and agentic workflows includes additional help text and guidance for writing LLM instructions to help improve outcome and task completion.
- Manually test the execution of an AI agent
- The tab names on the AI Agent Studio testing page have been renamed. The Test scenario tab is renamed to Test AI reasoning tab and the Output tab to Chat responses tab.
- Now Assist AI agents - The phrase "use case" has been updated to "agentic workflow".
- In AI Agent Studio, the phrase "use case" in the UI has been replaced with the phrase "agentic workflow" on all screens.
- Tools visible when testing AI agents
- When testing an AI agent, individual tool processes are now visible in the testing window, enabling you to track tool use, successes, or failures when trying out new AI agents.
- Use data picker for value overrides in AI agent tools
- When creating or modifying tools for AI agents, you can now use a data picker in value override fields. This helps ensure that information in records fields is transferred between tools.
Changed in this release
- Yokohama Patch 11
- Changes to Now Assist usage measurement
- Starting with Yokohama Patch 5, Now Assist usage measurement is transitioning from a 365-day look-back model to a 365-day burn-down model, with usage resetting at the contract anniversary date. For more information, refer to KB KB2704710: Now Assist Usage - Overview & New Measurement Logic.
- Some Now Assist skills are turned on by default
- The new default behavior works as follows:
- New customers: When you install a Now Assist product, designated skills are turned on automatically.
- Existing customers who are upgrading (starting with Yokohama Patch 11): Any previously unconfigured skill is turned on automatically (the skill was never configured and turned on, then turned off again). Previously configured skills that were turned on, then off, remain inactive.
- Configure ACLs for AI agents and agentic workflows
- Configure the access control lists for who can discover and trigger AI agents and agentic workflows in their guided setups in AI Agent Studio. You can determine whether an AI agent or agentic workflow behaves as a dynamic user or as an AI user. You can also specify if an AI agent or agentic workflow can be available to all authenticated users or publicly available.
- Platform Request status AI agent
-
The request status AI agent provides an AI-generated summary of the most recent comments from the AI agent or other people working on a ticket. You can add attachments to an open ticket or incident to support a request action. To find more information about an open ticket, you can ask the request status AI agent follow-up questions based on previous answers from the agent.
- Configuring Now Assist AI agents
- Run AI agents and agentic workflows concurrently in AI Agent Background Channel and in Non-interactive mode.
- Add a Knowledge Graph to an AI agent
- The Global Graph resource for creating a Knowledge Graph tool has been renamed to Enterprise Graph.
- Confirm your web search tool provider data policies
- If you select Google as your web search provider for web search AI agent tools, Google will use Grounding with Google Search, offered under a Global Standard deployment, and data may be routed to places outside of regions specified on your ServiceNow instance as a result. Consult your organization's data policies before enabling AI agents with web search tools that use Google as the provider.
- Yokohama Patch 6
- Add version control to instructions sent to the LLM
- You can review multiple versions of instructions sent to the LLM when designing your AI agents or agentic workflows. You can choose which version is active to help with testing or evaluating the success of an AI agent or agentic workflow to compare against other versions. Versions are named and ordered by time created for organizational purposes.
- Duplicate and edit existing tools when creating new AI agents
- When adding a tool to an AI agent, you can select an existing tool instead of creating a new tool from scratch. After an existing tool is added, you can make changes to suit the specific AI agent’s needs.
- Now Assist AI agents reference
- The sn_aia.enable_agent_tool_input_value_overrides system property is migrated to the [sn_aia_property] agent system property.
- Yokohama Patch 3
- Monitor more AI agent analytics in the AI Agent Analytics dashboard
- Two new pages have been added to the AI Agent Analytics dashboard, giving administrators more indicators, visualizations, and breakdowns to track AI agent performance and usage.
- Exploring Now Assist AI agents
- Impersonation in Now Assist records transactions done by an AI agent in the name of the AI agent who executes the agentic workflow.
Activation information
Now Assist in AI agents is available with activation of any Now Assist plugin from the ServiceNow Store. For more information about the prerequisites for using Now Assist, see Install Now Assist AI agents.
Additional requirements
You must first install the supported Now Assist version of ServiceNow to be able to use the Now Assist AI agents. For more information, see Install Now Assist AI agents.
Enable the Next Experience UI Framework before you can use the Now Assist panel.
Browser requirements
Now Assist AI agents supports various browsers, including Google Chrome and Microsoft Edge. Now Assist AI agents isn’t supported in Internet Explorer.
Accessibility information
- Voice Input for Now Assist AI agents
- Administrators can enable an optional voice input setting for the Now Assist panel in the Now Assist Admin console. This feature gives users a voice-to-text input option to access the Now Assist skills in the panel in any supported language. For more information, see Enable voice input for Now Assist panel.
Localization information
Now Assist AI agents is built on the GPT-4o-based framework and supports localization according to the GPT-4o model.