Combined AI Agent Studio release notes for upgrades from Yokohama to Australia
On this page
Combined AI Agent Studio release notes for upgrades from Yokohama to Australia
Consolidated page of all release notes for AI Agent Studio from Yokohama to Australia.
How to use this page
To help you prepare for your upgrade, we have combined the cross-family AI Agent Studio release notes onto one page. Read this summary of the new features, changes, and updated information for your product from Yokohama to Australia.
Tip: If there were no updates for a release notes section in a certain family release, we included a short note for your reference. For example, if a product did not have any updates in Tokyo, the row says “No updates for this release.”
Important information for upgrading AI Agent Studio to Australia
Before you upgrade to Australia, review these pre- and post-upgrade tasks and complete the tasks as needed.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
No updates for this release.
</td></tr><tr><td>
Australia
</td><td>
No updates for this release.
</td></tr></tbody> </table>## New features
Between your current release family and Australia, new features were introduced for AI Agent Studio.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
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.
Enhance AI agent learning through episodic memory, enabling AI agents to improve by learning from past successful interactions.
Create and update UI actions for workflow executions and display handling. You can specify conditions for the display of the UI actions.
Add Desktop action as a tool to an AI agent to perform desktop automation for repetitive tasks.
Support multilingual conversations for AI agents across languages.
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 how an AI agent or agentic workflow completes a task and if it enables users permission to access it.
-
-
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.
-
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.
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 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 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.
Use Enterprise Graph (Small) as a resource to create a Knowledge Graph tool for an AI agent in the AI Agent Studio.
The Add button on the AI agents tab is added as a drop-down providing different agent types for AI agent creation:
- **Chat** - **Voice** - **External**
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.
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.
Google Gemini and AWS Claude are available for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI.
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.
Choose to display AI agent output in Virtual Agent. You can also discover AI agents in Virtual Agent conversations.
Disable citations for specific agentic workflows or AI agents in AI Agent Studio where citations are not required or involve confidential information.
-
-
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
-
-
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.
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 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 AI Guardian in AI agents to automatically identify and block offensive messages that are sent by human agents.
Enable live agents to interact with multiple AI agent conversations through the Now Assist panel.
Analyze the performance, efficiency gain, and usage of AI agents through preconfigured dashboards.
</td></tr><tr><td>
Zurich
</td><td>
External agents now support custom HTTP headers in the External Agent Configuration [sn_aia_external_agent_configuration] table. Specify headers in JSON format to have them automatically included in API calls to external endpoints, regardless of the connection type. This is useful for passing metadata and authentication requirements that your external systems require.
AI specialists autonomously resolve high-volume requests through a single persona, know when to hand off work outside their scope, and improve over time from feedback and track record. Deploy the same foundation to every team, then configure each one in AI Agent Studio to fit that team’s specific needs. Contact your ServiceNow account manager for more information about accessing Autonomous Workforce.
The Knowledge Graph tool configuration in AI Agent Studio has a Conversation history toggle that is enabled by default. When enabled, the last 5 conversation turns from the active session are passed to the KG tool allowing users to ask follow-up questions that reference the previous results.
Runaway agent detection automatically disables an AI agent when the same record repeatedly triggers the same agent objective beyond a configured threshold, preventing unintended consumption of AI requests.
Auto-migrate all the AI Agent Studio skills from on-glide execution path to the off-glide execution path.
Enforce deny-by-default access control for AI agentic record types (gen_ai_agent, gen_ai_workflow, gen_ai_skill, Flow, flow_action) for newly activated ServiceNow instances. In previous releases, these types defaulted to allow access.
Automated agentic evaluations are now available for voice agents. You can generate conversations based on scenarios that are described or input manually to generate execution logs for voice agents for evaluation.
The AI-native experience for an AI agent is available exclusively with the installation of the Off Glide Conversation Server plugin (com.glide.cs.offglide).
Note: To use the AI agent in AI-native mode, make sure to test it so it works as expected.
Use the Premium Chat playground experience to test your agentic solutions.
Note: The AI-native playground experience is exclusively accessible when the Off Glide Conversation Server plugin (com.glide.cs.offglide) is installed. If the plugin is not installed, you will continue to access the standard testing playground.
Add widgets for tool outputs to provide an improved experience in AI-native mode.
Note: The display output widget options are exclusively accessible when the Off Glide Conversation Server plugin (com.glide.cs.offglide) is installed. If the plugin is not installed, you will continue to access the standard add tool form.
Automated evaluations support voice AI agents. Get a better picture of overall performance by evaluating previous executions against standardized metrics.
Enhance user experience for Secondary Agents by displaying the Agent card URL to admins for easy access and management so the admin can view, copy, and consume the URL easily.
Additionally, when adding an MCP tool, the name and description of the tool are populated automatically as per the details fetched from the server and the user can update the details.
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.
Enhance AI agent learning through episodic memory, enabling AI agents to improve by learning from past successful interactions.
Create and update UI actions for workflow executions and display handling. You can specify conditions for the display of the UI actions.
Add Desktop action as a tool to an AI agent to perform desktop automation for repetitive tasks.
Support multilingual conversations for AI agents across languages.
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 how an AI agent or agentic workflow completes a task and if it enables users permission to access it.
-
-
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.
-
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.
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 ServiceNow Otto in Virtual Agent.
The Service Portal Approval Info Record widget shows details about the approval request and a full record for an approval including the activity stream.
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 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.
Use Enterprise Graph (Small) as a resource to create a Knowledge Graph tool for an AI agent in the AI Agent Studio.
The Model Context Protocol Client enables guardian checks for offensive content when Notion is selected as the MCP server.
The Model Context Protocol Client application supports the latest MCP version.
Use Global Graph as a Knowledge Graph resource when creating a Knowledge Graph tool for an AI agent in the AI Agent Studio.
Enable users of the ServiceNow® AI Agent Studio to access tools that are hosted externally and published using an MCP server via the Model Context Protocol Client application.
Authenticate users with the MCP server to add the MCP tool to an AI agent.
Use ServiceNow AI agents inside third-party agentic AI systems. Using Agent2Agent protocol, you can discover and invoke AI agents in other agentic AI systems to access ServiceNow AI Platform instance capabilities.
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.
View and troubleshoot the agentic workflow and AI agent executions on AI Agent Studio via the Activity page.
-
Configure - Dynamic Orchestrator
Maps the appropriate agents for an agentic workflow with Dynamic Orchestrator for better performance and accuracy of the agentic workflow execution.
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.
Google Gemini and AWS Claude are available for generative AI skills and AI agents, in addition to Now LLM Service and Azure OpenAI.
The output transformation strategy for an AI agent output contains a new option called Custom. Using the custom output transformation strategy, the tool output gets transformed according to the LLM instructions.
-
Configure - AI Agent Background Channel
Invoke the agentic conversations from 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.
-
Configure - 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 don’t reach out to the user during fallback but send the execution output to the user.
</td></tr><tr><td>
Australia
</td><td>
Define access rules and tools in the Model Context Protocol Servers for security control before adding them as tools to an AI agent.
Add security controls and tools to external AI agents.
Test access to an AI asset to verify whether a user has access to an agentic AI asset - AI agent and agentic workflow. In case of access denial, use Access Analyzer to see the access results in Access Management.
The redesigned AI Agent Studio streamlines the creation, testing, and evaluation processes for agentic AI assets on your instance. Use identified automation opportunities to build AI agents quickly. Create test scenarios for evaluation to detect recurring patterns and opportunities for optimization.
The redesigned AI Agent Studio streamlines the creation and testing of external AI agents.
The Model Context Protocol Client application has been redesigned.
External agents now support custom HTTP headers in the External Agent Configuration [sn_aia_external_agent_configuration] table. Specify headers in JSON format to have them automatically included in API calls to external endpoints, regardless of the connection type. This is useful for passing metadata and authentication requirements that your external systems require.
AI specialists autonomously resolve high-volume requests through a single persona, know when to hand off work outside their scope, and improve over time from feedback and track record. Deploy the same foundation to every team, then configure each one in AI Agent Studio to fit that team’s specific needs. Contact your ServiceNow account manager for more information about accessing Autonomous Workforce.
The Knowledge Graph tool configuration in AI Agent Studio has a Conversation history toggle that is enabled by default. When enabled, the last 5 conversation turns from the active session are passed to the KG tool allowing users to ask follow-up questions that reference the previous results.
Runaway agent detection automatically disables an AI agent when the same record repeatedly triggers the same agent objective beyond a configured threshold, preventing unintended consumption of requests.
Auto-migrate all the AI Agent Studio skills from on-glide execution path to the off-glide execution path.
Automated agentic evaluations are now available for voice agents. You can generate conversations based on scenarios that are described or input manually to generate execution logs for voice agents for evaluation.
The AI-native experience for an AI agent is available exclusively with the installation of the Off Glide Conversation Server plugin (com.glide.cs.offglide).
Note: To use the AI agent in AI-native mode, make sure to test it so it works as expected.
Use the AI Native playground experience to test your agentic solutions.
Note: The AI-native playground experience is exclusively accessible when the Off Glide Conversation Server plugin (com.glide.cs.offglide) is installed. If the plugin is not installed, you will continue to access the standard testing playground.
Add widgets for tool outputs to provide an improved experience in AI-native mode.
Note: The display output widget options are exclusively accessible when the Off Glide Conversation Server plugin (com.glide.cs.offglide) is installed. If the plugin is not installed, you will continue to access the standard add tool form.
</td></tr></tbody> </table>## Changes
Between your current release family and Australia, some changes were made to existing AI Agent Studio features.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
The guided setups for creating an AI agent and agentic workflow have been updated.
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.
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.
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 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.
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.
Run AI agents and agentic workflows concurrently in AI Agent Background Channel and in Non-interactive mode.
The Global Graph resource for creating a Knowledge Graph tool has been renamed to Enterprise Graph.
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.
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.
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.
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.
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.
The sn_aia.enable_agent_tool_input_value_overrides system property is migrated to the [sn_aia_property] agent system property.
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.
Impersonation in Now Assist records transactions done by an AI agent in the name of the AI agent who executes the agentic workflow.
-
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.
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.
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.
</td></tr><tr><td>
Zurich
</td><td>
The Analyze task trends agentic workflow now includes citations for representative records associated with a pattern. Configure the workflow to include open tickets in its analysis by enabling the setting and running a Group Action Framework job to reindex with the new records.
The name of the button on the agent selection pop-up in the Discover and activate section of the external agents guided setup has been renamed to Selected.
Use GPT-5.4 as the default model for the Orchestrator when Azure OpenAI is the selected LLM.
The default third-party (3P) models have been upgraded to the latest versions - GPT 5.2 to GPT 5.4 to use AI Agents.
The new generative AI Config property records sys_generative_ai_config and sys_generative_ai_prompt_config have been introduced for the following model providers:
- Amazon Bedrock: claude-sonnet-4-6 - Azure OpenAI: gpt 5.4
The following platform agentic workflows had updates to their admin configurations and behavior in user-generated sessions.
- [Analyze task trends](https://www.servicenow.com/docs/access?context=incident-trends&family=zurich&ft:locale=en-US): Admin configurations for additional filters such as category and service have been added. - [Generate my work plan](https://www.servicenow.com/docs/access?context=generate-work-plan&family=zurich&ft:locale=en-US): Additional reasoning information for the generated work plan is now displayed after the plan is created. - [Identify ways to improve services](https://www.servicenow.com/docs/access?context=service-improvement&family=zurich&ft:locale=en-US): Admin configurations for additional filters such as category and service have been added.
The AI Native radio button in the Choose a testing mode section on the AI agent and agentic workflow manual testing playgrounds has been renamed to Premium Chat.
The glide.ai_record_activity.validation.feature.enabled system property enables UI rule validation (such as required fields) for AI‑initiated record updates. You can selectively apply this validation based on execution context using additional system properties. For example, glide.ai_record_activity.ai_detection.nap.enabled applies validation to record updates triggered from the ServiceNow Otto panel. Similar properties control validation for AI skills, Virtual Agent, and agent‑initiated actions, as listed in the Reference for Now Assist AI agents. This feature is opt‑in and disabled by default.
The agent to agent flow actions no longer inject an Authorization: Bearer header automatically. If your endpoint requires a Bearer token, include the prefix directly in the API Key credential value.
Use the A2A Protocol integration for creating external agents in the AI Agent Studio to connect with the ServiceNow AI Platform.
Several platform agentic workflows have seen updates to how they work and what configurations are available for AI admins. Analyze task trends and Identify ways to improve service now have post-analysis actions, including the option to download analysis and ask additional information. Generate my work plan can run as a scheduled job.
After an automated evaluation of an agentic AI asset, you can receive a list of issues and suggested optimizations to address those issues. Issues come with individual record node-by-node traces to pinpoint the exact source of problems. Optimizations are suggested, and you can apply them and run a reevaluation from a single guided flow.
Several platform agentic workflows have seen updates to how they work and what configurations are available for AI admins. Generate resolution plans now takes related records into account when planning next steps. Generate my work plan shows suggested next steps and reruns after work is done. Process images for new tasks now links to the created task record upon creation and includes certain metadata from the image.
Starting with Australia Early Access, AI 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: AI Usage - Overview & New Measurement Logic.
The guided setups for creating an AI agent and agentic workflow have been updated.
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.
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.
The base reflection prompt has been replaced with the ReAct Orchestrator prompt, introducing a Route scheduling mode when an agent needs assistance from another agent during execution.
Run AI agents and agentic workflows concurrently in AI Agent Background Channel and in Non-interactive mode.
The Global Graph resource for creating a Knowledge Graph tool has been renamed to Enterprise Graph.
The ticket status AI agent has been renamed to the request status AI agent. Request details include an AI-generated summary of the most recent comments on a request. Performance has been improved.
If you select Google as your web search provider for web search AI agent tools, Google uses Grounding with Google Search, offered under a Global Standard deployment, and data may be routed to places outside of regions specified on your ServiceNow AI Platform instance as a result. Consult your organization’s data policies before enabling AI agents with web search tools that use Google as the provider.
The Add button on the AI agents tab has been added as a drop-down menu providing different agent types for AI agent creation:
- **Chat** - **External** -
The new steps for the guided setups for AI voice agents and agentic workflows include additional help text and guidance for writing LLM instructions to help improve outcome and task completion.
The tab names on the AI Agent Studio testing page have been renamed. The Test scenario tab is renamed to Test AI reasoning and the Output tab is renamed to Chat responses.
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.
When adding a tool to an AI agent, you can select an existing tool instead of creating a new tool. After an existing tool is added, you can change it to suit the specific needs of an AI agent.
The sn_aia.enable_agent_tool_input_value_overrides system property is migrated to the Agent properties [sn_aia_property] table.
</td></tr><tr><td>
Australia
</td><td>
The redesigned AI Agent Studio reimagines the creation and deployment processes for agentic AI assets. New features include automated evaluations built in to the application and easy creation of AI agents for automation opportunities. See Configure AI Agent Studio settings for how to access the previous UI.
The Analyze task trends agentic workflow now includes citations for representative records associated with a pattern. Configure the workflow to include open tickets in its analysis by enabling the setting and running a Group Action Framework job to reindex with the new records.
The name of the button on the agent selection pop-up in the Discover and activate section of the external agents guided setup has been renamed to Selected.
Use GPT-5.4 as the default model for the Orchestrator when Azure OpenAI is the selected LLM.
The default third-party (3P) models have been upgraded to the latest versions - GPT 5.2 to GPT 5.4 to use AI agents and AI Agent Studio.
The new generative AI Config property records sys_generative_ai_config and sys_generative_ai_prompt_config have been introduced for the following model providers:
- Amazon Bedrock: claude-sonnet-4-6 - Azure OpenAI: gpt 5.4
The following platform agentic workflows had updates to their admin configurations and behavior in user-generated sessions.
- [Analyze task trends](https://www.servicenow.com/docs/access?context=incident-trends&family=australia&ft:locale=en-US): Admin configurations for additional filters such as category and service have been added. - [Generate my work plan](https://www.servicenow.com/docs/access?context=generate-work-plan&family=australia&ft:locale=en-US): Additional reasoning information for the generated work plan is now displayed after the plan is created. - [Identify ways to improve services](https://www.servicenow.com/docs/access?context=service-improvement&family=australia&ft:locale=en-US): Admin configurations for additional filters such as category and service have been added.
The AI Native radio button in the Choose a testing mode section on the AI agent and agentic workflow manual testing playgrounds has been renamed to Premium Chat.
The glide.ai_record_activity.validation.feature.enabled system property enables UI rule validation (such as required fields) for AI‑initiated record updates. You can selectively apply this validation based on execution context using additional system properties. For example, glide.ai_record_activity.ai_detection.nap.enabled applies validation to record updates triggered from the ServiceNow Otto panel. Similar properties control validation for AI skills, Virtual Agent, and agent‑initiated actions, as listed in the Reference for AI agents. This feature is opt‑in and inactive by default.
The agent to agent flow actions no longer inject an Authorization: Bearer header automatically. If your endpoint requires a Bearer token, include the prefix directly in the API Key credential value.
Use the A2A Protocol integration for creating external agents in the AI Agent Studio to connect with the ServiceNow AI Platform.
Several platform agentic workflows have seen updates to how they work and what configurations are available for AI admins. Analyze task trends and Identify ways to improve service now have post-analysis actions, including the option to download analysis and ask additional information. Generate my work plan can run as a scheduled job.
After an automated evaluation of an agentic AI asset, you can receive a list of issues and suggested optimizations to address those issues. Issues come with individual record node-by-node traces to pinpoint the exact source of problems. Optimizations are suggested, and you can apply them and run a reevaluation from a single guided flow.
</td></tr></tbody> </table>## Removed
Between your current release family and Australia, some AI Agent Studio features or functionality were removed.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
No updates for this release.
</td></tr><tr><td>
Australia
</td><td>
No updates for this release.
</td></tr></tbody> </table>## Deprecations
Between your current release family and Australia, some AI Agent Studio features or functionality were deprecated.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
The support for manually integrating external agents has been deprecated from Zurich Patch 8 release.
</td></tr><tr><td>
Australia
</td><td>
-
The support for manually integrating external agents has been deprecated from Australia Patch 1 release.
</td></tr></tbody> </table>## Activation information
Review information on how to activate AI Agent Studio.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Activation information
AI agents are available with activation of AI plugins from the ServiceNow Store. For more information about the prerequisites for using AI agents and AI Agent Studio, see Install ServiceNow Otto AI agents.
Important: AI agents and AI Agent Studio are available in the ServiceNow Store. For details, see the “Activation information” section of these release notes.
</td></tr><tr><td>
Australia
</td><td>
-
Activation information
AI agents and AI Agent Studio are available with activation of any AI plugin from the ServiceNow Store. For more information about the prerequisites for using AI agents, see Install ServiceNow Otto AI Agents.
Important: AI agents and AI Agent Studio are available in the ServiceNow Store. For details, see the “Activation information” section of these release notes.
</td></tr></tbody> </table>## Additional requirements
If any additional requirements were introduced or changed for AI Agent Studio we have noted them here.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Additional requirements
You must first install the supported application version of the ServiceNow AI Platform to be able to use AI agents and AI Agent Studio. For more information, see Install ServiceNow Otto AI agents.
Next Experience UI Framework must be enabled before you can use the ServiceNow Otto panel.
</td></tr><tr><td>
Australia
</td><td>
-
Additional requirements
You must first install the supported version of the ServiceNow AI Platform to be able to use AI agents and AI Agent Studio. For more information, see Install ServiceNow Otto AI Agents.
Next Experience UI Framework must be enabled before you can use the ServiceNow Otto panel.
</td></tr></tbody> </table>## Browser requirements
If any specific browser requirements were introduced or changed for AI Agent Studio we have noted them here.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Browser requirements
AI agents and AI Agent Studio support various browsers, including Google Chrome and Microsoft Edge. AI agents and AI Agent Studio aren’t supported in Internet Explorer.
</td></tr><tr><td>
Australia
</td><td>
-
Browser requirements
AI agents and AI Agent Studio support various browsers, including Google Chrome and Microsoft Edge. AI agents and AI Agent Studio aren’t supported in Internet Explorer.
</td></tr></tbody> </table>## Accessibility information
Review details on accessibility information for AI Agent Studio, such as specific requirements or compliance levels.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Accessibility information
Administrators can enable an optional voice input setting for the ServiceNow Otto panel in the . This feature gives users a voice-to-text input option to access the generative AI skills in the panel in any supported language. For more information, see Enable voice input for ServiceNow Otto panel.
After enabled, the Enable voice input for the ServiceNow Otto panel option is available in individual user accessibility preferences. See Configure Next Experience accessibility preferences for more information.
Voice-to-text input can help users with mobility impairments access generative AI skills without using a keyboard. This feature can also be useful to blind or low-vision users, neurodivergent users, non-native language speakers, or mobile users on the go, such as field service agents.
</td></tr><tr><td>
Australia
</td><td>
-
Accessibility information
Administrators can enable an optional voice input setting for the ServiceNow Otto panel in the AI Admin Hub. This feature gives users a voice-to-text input option to access the generative AI skills in the panel in any supported language. For more information, see Enable voice input for ServiceNow Otto panel.
After enabled, the Enable voice input for the ServiceNow Otto panel option is available in individual user accessibility preferences. See Configure Next Experience accessibility preferences for more information.
Voice-to-text input can help users with mobility impairments access generative AI skills without using a keyboard. This feature can also be useful to blind or low-vision users, neurodivergent users, non-native language speakers, or mobile users on the go, such as field service agents.
</td></tr></tbody> </table>## Localization information
If there are specific localization considerations for AI Agent Studio we have noted them here.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Localization information
AI agents and AI Agent Studio are built on the GPT-4o-based framework and supports localization according to the GPT-4o model.
</td></tr><tr><td>
Australia
</td><td>
-
Localization information
AI agents and AI Agent Studio are built on the GPT-4o-based framework and supports localization according to the GPT-4o model.
</td></tr></tbody> </table>## Highlight information
If there are specific highlight considerations for AI Agent Studio we have noted them here.
<table class=“custom-rows”><thead><tr><th class=“filter”>
Release
</th><th>
Release notes
</th></tr></thead><tbody><tr><td>
Yokohama
</td><td>
No updates for this release.
</td></tr><tr><td>
Zurich
</td><td>
-
Redesigned AI Agent Studio with streamlined setup and evaluation processes for agentic AI assets.
-
Custom headers in external agents configuration.
-
AI specialist configuration and deployment to harness coordinated agentic AI that reasons and executes end-to-end work.
-
Add or remove AI agents or tools from the built-in AI agents.
-
Detect and disable runaway AI agent triggers to prevent unintended consumption.
-
Support conversation history for Knowledge Graph tool.
-
Enforce deny-by-default ACLs for new agentic ACL types.
-
Enable AI Agent Studio skill migration to Mosaic.
-
Enable UI validation for agentic AI processes and generative AI skills.
-
Test an agentic solution in the playground in AI-native mode.
-
Add widgets for tool outputs to provide an improved experience in AI-native mode.
-
Review issues and apply suggested recommendations to agentic AI assets after automated evaluations.
-
Run improved Platform agentic workflows, including Analyze task trends, Generate my work plan, and Identify ways to improve services.
-
Run improved Platform agentic workflows, including Generate resolution plans, Generate my work plan, and Process images to tasks.
-
Get more insights into agentic AI asset performance with issue tracing and suggested optimizations from results pages.
-
Run improved Platform agentic workflows, including Generate resolution plans, Generate my work plan, and Process images to tasks.
-
Show Agent card URL when using secondary agents.
-
Review changes to usage measurement.
-
Japanese language support for voice assistants enables Japanese-speaking users to experience natural, culturally appropriate interactions with AI voice agents.
-
Execute agentic workflows, AI agents, and tools in AI Agent Studio with role masking.
-
Additional role configuration required for agentic workflows and AI agents included with your 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.
-
Consume Global Graph as a Knowledge Graph resource.
-
Check for offensive content with MCP guardian.
-
Support the latest MCP version from Zurich Patch 3.
-
Authenticate users with the MCP Server to add a Model Context Protocol tool to AI agents using the Model Context Protocol Client.
-
Create ACLs for AI agents and agentic workflows to customize who can discover and trigger AI agents and agentic workflows.
Zurich EA
-
Create and maintain versions of LLM instructions for AI agents and agentic workflows to help organize and iterate on prompts and test their effectiveness.
-
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 generative AI 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.
See AI Agent Studio for more information.
For the Platform AI release notes, see ServiceNow Otto release notes.
</td></tr><tr><td>
Australia
</td><td>
-
Redesigned AI Agent Studio with streamlined setup and evaluation processes for agentic AI assets.
-
Custom headers in external agents configuration.
-
AI specialist configuration and deployment to harness coordinated agentic AI that reasons and executes end-to-end work.
-
Add or remove AI agents or tools from the built-in AI agents.
-
Detect and disable runaway AI agent triggers to prevent unintended consumption.
-
Support conversation history for Knowledge Graph tool.
-
Enable AI Agent Studio skill migration to Mosaic.
-
Enable UI validation for agentic AI processes and generative AI skills.
-
Test an agentic solution in the playground in AI-native mode.
-
Add widgets for tool outputs to provide an improved experience in AI-native mode.
-
Run improved Platform agentic workflows, including Generate resolution plans, Generate my work plan, and Process images to tasks.
-
Get more insights into agentic AI asset performance with issue tracing and suggested optimizations from results pages.
See AI Agent Studio (legacy) for more information.
For the Platform AI release notes, see AI Admin Hub release notes.
</td></tr></tbody> </table>Parent Topic:Products combined by family
Keep exploring.
Find another answer, or bring this documentation into your own tools.