---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Configure AI Agent Studio

# Configure AI Agent Studio {#ariaid-title1}

Release version: Australia  
Updated June 6, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 5 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Configure AI Agent Studio

AI Agent Studio enables ServiceNow customers to configure AI agents, agentic workflows, and tools that allow AI agents to plan and execute tasks using record data and knowledge base content.
These agents combine business logic with instructions to large language models (LLMs) to determine the best next actions, enhancing automation and decision-making within your ServiceNow environment.
Keeping your record data and knowledge base current is essential for optimal results.
Show full answer Show less  

## Prerequisites

* Develop a clear plan to enhance AI agent performance and result quality, avoiding redundant agents.
* Identify the range of tasks your agentic workflows must cover and understand their general operation flow.
* Prepare agentic tools with well-written, clear descriptions to ensure effective agent use.

## Configurable Elements

Key elements to configure AI agents and workflows include:

* **Base Plan:** Initial instructions for AI Agent Orchestrator at the workflow level.
* **Role:** Defines the AI agent's identity, including reasoning prompts and an auto-generated proficiency description based on assigned roles and tools.
* **Instructions:** Clear, step-by-step operational directives written as an algorithm for the AI agent.

## Tool Configuration

Each tool in an agentic workflow should be configured with:

* **Functionality:** A single, clearly scoped purpose to avoid complexity and improve agent performance.
* **Description:** Natural language explanations detailing the tool's utility, applicable workflows, scenarios where it is unsuitable, and definitions of any specialized terms.
* **Error Messages:** Feedback to help AI agents learn from incorrect tool executions and maintain execution accuracy.

## Invoking AI Agent Conversations

Use the AI Agent Background Channel to invoke AI agent or workflow executions from the Workspace. This relies on the AI Agent Background Provider and the Custom Adapter Framework. Conversations are triggered via the `snaia.AiAgentRunttimeUtil().startAiAgentConversation(request)` API and logged in the Execution Plans table for review. Execution details, including tasks and tool usage, can be monitored on the AI Agent Studio Testing page.

## Execution Modes

* **Interactive Mode:** The AI agent requests additional user input when encountering fallbacks, then continues execution after receiving responses.
* **Non-Interactive Mode:** The AI agent does not solicit user input on fallback but adapts prompts dynamically. Execution results and errors are displayed in the Now Assist panel or Virtual Agent.

Execution mode is set per plan and can run concurrently in the background alongside chat panels for seamless operation.

## Multilingual Support

AI agents support multiple languages with capabilities to tune system prompts for native translations, implement dynamic translation strategies, and validate translation quality through both automated and manual methods, enhancing usability across diverse user bases.

## Skills Migration

AI Agent Studio skills can be migrated from the on-glide to the off-glide execution path (Mosaic) by enabling the "Off-Glide Enabled" setting in the Now Assist AI Agents application found in the OneExtend Capabilities table, streamlining skill management and execution.  
Configure AI agents, agentic workflows, and tools so that AI agents can plan and execute tasks using your record data and knowledge base content.

AI agents follow your instructions and act toward a specific goal by using the tools you configure for them. Using the context of your records and searchable content, AI agents plan and analyze tasks by combining business logic
with instructions sent to large language models (LLMs), which suggest the next best action to take.  
Note:  
Keep your record data and knowledge base up to date for best results.

## Prerequisites {#configuring-aia-new__section_prerequisites}

Before configuring AI agents, establish a clear plan to improve agent performance and result quality. A solid foundation minimizes redundant agents and maximizes the efficiency of existing ones.

* Identify the different kinds of tasks your agentic workflow must handle.
* Understand the general flow for your agentic workflow and agents.
* Prepare agentic tools with well-written descriptions.
{#configuring-aia-new__ul_prereqs}

## Configurable elements {#configuring-aia-new__section_configurable_elements}

Use the following elements to instruct agentic workflows and AI agents within the framework.

Base plan
:   Instructions to the AI Agent Orchestrator for the initial planning procedure. Configured at the agentic workflow level.

Role

:   A clear identity for the AI agent, comprising two elements:

    Agent reasoning
    :   When a role is added to each reasoning prompt, it gives the LLM a sense of identity for the content it generates.

    Agent proficiency
    :   An auto-generated, LLM-produced description of what an agent is capable of, derived from the role, instructions, and the descriptions of its assigned tools.

Instructions
:   Clear directives for the AI agent. Write instructions as a step-by-step algorithm that describes the operational flow the agent should follow.

## Tool elements for agentic workflows {#configuring-aia-new__section_m43_f4c_k2c}

Each tool in an agentic workflow is defined by three elements: its functionality, its description, and its error messages.

Functionality

:   Functionality defines what an AI agent contributes to the agentic workflow. Configure each tool with a single, clearly scoped purpose. Multipurpose tools degrade agent performance for two reasons:

    * They are harder for the AI Agent Orchestrator to reason through. When a tool can serve more than one purpose, the orchestrator must determine which purpose applies, which increases runtime.
    * The tool description must account for every usage scenario, making it harder to write accurately and completely.

    {#configuring-aia-new__ul_acw_xwc_k2c}  
    Note:  
    Configure each tool as the solution to a single problem. Avoid tools that can operate in different modes.

Tool description

:   Tool descriptions are natural language statements that explain the utility a tool provides. Clear scope and limits help verify tools are selected for appropriate scenarios. A strong tool description includes all
    of the following:

    * What the tool does.
    * The specific agentic workflows and tasks where the tool applies.
    * Scenarios where the tool is explicitly not useful, especially cases where an AI agent might incorrectly select it.
    * Definitions of any terms used. For example, if a tool assigns a role to a user, explain what "role" means in the context of that instance.
    {#configuring-aia-new__ul_qtj_5xc_k2c}

Error messages

:   AI agents learn through trial and error. Error messages give an agent feedback on incorrect tool executions, helping it reach more valid conclusions in subsequent steps. Understanding where a tool can fail helps
    keep execution on track.

## Invoke Conversations with the AI Agent Background Channel

The AI Agent Background Channel lets you invoke AI agent or agentic workflow execution from the Workspace. Use it with the AI Agent Background Provider, which is based on the Custom Adapter Framework from Virtual Agent. For more information, see [Configure a provider for your custom chat integration](https://www.servicenow.com/docs/access?context=create-provider-va-cccif&version=australia&pubname=australia-conversational-interfaces&ft:locale=en-US).

To add conversational capabilities to your own provider application and obtain a new inbound ID, create a channel identifier in the Provider Channel Identities table \[sys_cs_provider_application\]. For more information, see [Create a channel identifier for your custom chat integration](https://www.servicenow.com/docs/access?context=create-channel-id-va-cccif&version=australia&pubname=australia-conversational-interfaces&ft:locale=en-US).

To start a conversation, trigger the flow using the sn_aia.AiAgentRunttimeUtil().startAiAgentConversation(request) API in the Script Include (sys_script_include) of the AIAgentBackgroundProvider, then
select Run Script. When the script execution status shows Success, the conversation begins in the order of utterances defined in the script.

Conversations invoked for AI agent execution are logged in the Execution Plans \[sn_aia_execution_plan\] table. Open the conversation record to confirm the device type as AI Agent Background. Open the execution record to review the Execution Tasks, Messages, and Tool Executions.

You can also review the complete execution steps on the AI Agent Studio Testing page. Copy the execution plan record's sys_id and test it there. On the Chat responses tab, the AI agent decision logs show agent details and the tools used
to resolve the issue.

## Interactive and non-interactive execution modes {#configuring-aia-new__section_yl3_1zr_zfc}

AI agents operate in one of the two execution modes, which determine how the agent handles fallback scenarios during execution.

Interactive
:   The AI agent reaches out to the user for information when a fallback occurs, then re-triggers the flow after receiving a response.

Non-interactive

:   The AI agent does not contact the user at any fallback stage. Instead, it uses a dynamic prompt approach through the ReAct layer, where the prompt adapts based on the execution mode. Fallback options don't collect
    user input. The output of the AI agent or agentic workflow is still presented to the user, and any execution failure displays a message in the Now Assist panel or Virtual Agent.

The execution mode is set in the Execution Mode field in the Execution Plans \[sn_aia_execution_plan\] table and is determined at runtime.

AI agents and agentic workflows can run concurrently in the AI Agent Background Channel and in non-interactive mode. Background execution allows AI agents to operate alongside any chat panel, such as the Now Assist panel or Virtual Agent.

## Multilingual support {#configuring-aia-new__section_ydj_hjj_hhc}

AI agents support multiple languages to improve translation quality. You can:

* Tune system prompts for native-language translations.
* Implement dynamic translation strategies when native support is unavailable.
* Validate translation quality through automated and manual evaluations.
{#configuring-aia-new__ul_yfy_s3j_hhc}

## AI Agent Studio skills migration {#configuring-aia-new__skills-migration}

You can automatically migrate all AI Agent Studio skills from the on-glide execution path to the off-glide execution path by enabling the Off-Glide Enabled setting. This migrates skills to Mosaic.

1. Navigate to the OneExtend Capabilities \[sys_one_extend_capability.list\] table.
2. Find the Now Assist AI Agents application.
3. Set Off-Glide Enabled to true.
4. Select Save.