--- sourceDocument: Australia Workflow Data Fabric sourceDocumentLink: https://www.servicenow.com/docs/r/australia/integrate-applications Release : - australia ft:locale : - en-US ft:publication_title : - Australia Workflow Data Fabric ft:clusterId : - crint bundleId : - crint workflow : - Creator --- # Limitations of AI # Limitations of ServiceNow Otto for RPA Hub {#ariaid-title1} Release version: Australia Updated July 31, 2025 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 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 Limitations of ServiceNow Otto for RPA Hub The limitations described pertain to the RPA bot generation skill in ServiceNow Otto for RPA Hub, specifically in the Australia and Yokohama release versions. These constraints impact how automation workflows are generated and configured, affecting the use of AI Search, large language models (LLM), and component compatibility within the RPA Desktop Design Studio environment. Show full answer Show less ## Key Limitations * **AI Search and LLM Timeout:** The RPA bot generation relies on AI Search and LLM APIs, which are subject to timeout limits and rate limiting. This can affect the responsiveness and completeness of automation workflow generation. * **Component Scope Restrictions:** The initial versions support only a limited set of components. Components outside this supported list do not appear in generated workflows, for example, the Capture component for screenshots is not included initially. * **Plugin Version Compatibility:** The RPA feature uses Yokohama version plugins. If the LLM suggests methods not present in the loaded plugin version (e.g., Washington DC plugins), those methods show as unknown components, which may disrupt workflow creation. * **Usage of Existing Connectors:** When creating new activities that use connector methods (like Microsoft Excel's AddNewWorksheet), the system reuses existing global connector objects of the same type, prioritizing the most recent one. * **Dynamic Configuration Unavailable:** In the Yokohama release, dynamic configuration of supported components is not available. Users must manually configure component inputs, such as setting cell values in Excel connectors, through the configuration interface. * **Automation of Windows, Java, or Browser Apps:** For these applications, only generic UI actions (SetValue, GetValue, Click) from the Universal App connector are suggested, and users need to manually configure these actions including screen captures and element selection. * **Expression-Based Components:** Components requiring expressions (e.g., Decision, Expression) do not have their expressions auto-populated and require manual input. * **Hallucinated Components:** If the LLM returns methods that do not exist in RPA Desktop Design Studio, these appear as unknown components in the workflow, potentially leading to incomplete or incorrect automation design. ## Practical Implications for ServiceNow Customers * Expect to manually configure several aspects of the automation workflows, especially for components outside the supported scope or when working with Windows, Java, or browser applications. * Be aware of plugin version mismatches that may cause unknown components to appear, requiring verification and possible adjustment of plugin versions used. * Prepare for rate limits and timeouts when using AI Search and LLM-based automation generation, which may impact workflow creation speed and completeness. * Understand that advanced components requiring expressions need manual configuration as automatic expression population is not supported. Overall, these limitations highlight the need for manual intervention and careful plugin management when leveraging ServiceNow Otto's RPA Hub capabilities, ensuring customers can effectively design and deploy automated workflows within the current constraints. The limitations of the RPA bot generation skill are as follows. AI Search and LLM timeout : The RPA bot generation skill relies on AI Search and large language models (LLM) to understand the user instructions and flow creation. The timeout limits and rate-limiting behavior of these APIs collectively apply to the RPA bot generation skill. For more information about AI search system properties, see [AI Search system properties](https://www.servicenow.com/docs/access?context=system-properties-ais&version=australia&pubname=australia-platform-administration&ft:locale=en-US). For more information about API rate limits, see . For more information about configuring rate limiting for providers, see [Configure rate limiting for providers](https://www.servicenow.com/docs/access?context=configure-rate-limit&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Component scope in Yokohama release : The initial version supports few components. Components outside this scope don't appear in the generated automation workflow. For example, if you provide an instruction, such as Capture a screen shot and save it in the location at 'C:\Users\Screens', the generated automation workflow might not contain the Capture component because it isn't included in the initial version components list. For more information about the list of supported components, see [Supported components and connectors for Now Assist for RPA Hub in Yokohama release](https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB1808191). Plugin version compatibility : The feature uses Yokohama version plugins. If the large language model (LLM) returns a method that doesn't exist in the loaded plugin version, then such methods are displayed as unknown components in the generated automation workflow. For example, if you're using Washington DC version plugins within an existing automation project and provide an instruction to set or get values from an application, then the SetValue, GetValue, or Click methods of the Universal App connector are displayed as unknown components in the generated automation workflow. In the following example, to get the weather information, data reader components are required. Since they are not available in the current scope, they appear as UNKNOWN components in the automation preview.Figure 1. Unknown components in the Automation preview If you select Next in the previous screen, the automation appears as follows on the Design surface.Figure 2. Unknown components on the Design surface Usage of existing connectors in new activity using AI or build automation context menu options : During the automation workflow creation, if a method, such as the AddNewWorksheet method of Microsoft Excel connector is created, RPA Desktop Design Studio checks for an existing global object of the same connector type and uses the most recent one. In the following example, the Badging Data Microsoft Excel connector is used.Figure 3. Microsoft Excel connectors in Global Objects Dynamic configuration : Dynamic configuration for supported components isn't available in the Yokohama release. You can configure components manually. For example, you must give inputs in the configuration window for the Microsoft Excel connector's SetCellValues method. Select the settings icon (![Settings icon.]()) to view the configuration window. : Data in the parameter values might not be populated in the large language model (LLM) generated components.Figure 4. Configuration window for SetCellValues method Automation for Windows, Java, or browser applications : For automating Windows, Java, or browser-based applications, RPA Desktop Design Studio suggests generic UI actions such as SetValue, GetValue, or Click. These actions are a part of the Universal app connector. You must configure these actions manually, including capturing screens and adding elements via the field window. For more information about these methods, see [Universal app connector](https://www.servicenow.com/docs/ae0jSojTRSi8fjYuCM8aIQ "Create automations for your Windows, Java, and web applications by using the Universal App Connector (UAC) of RPA Desktop Design Studio. Configure the application screens and their elements from a single, unified connector instead of using the individual connectors of these applications."). Expression-based components : For components that require expressions, such as Decision or Expression, and so on, expressions in these components aren't automatically populated in the Australia release. Hallucinated components : If the large language model (LLM) returns a method that doesn't exist in the RPA Desktop Design Studio, then such methods are displayed as unknown components in the generated automation workflow.