--- sourceDocument: Australia Enable AI sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences Release : - australia ft:locale : - pt-BR ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Manually capture steps # Automate repetitive tasks by manually capturing steps in Agentic Desktop {#ariaid-title1} * Versão de lançamento: Australia * * Atualizado 12 de mar. de 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 6 min. de leitura Create desktop actions by manually capturing steps to automate repetitive tasks in Agentic Desktop. The steps that you define on one or more application screens are saved as a reusable desktop action of type UI block. ## Antes de Iniciar To access the Agentic Desktop functionality, perform the following steps: * Enable Agentic Desktop on your ServiceNow instance. For more information, see [Configure Agentic Desktop](https://servicenow-prod.fluidtopics.net/3VcWwOQSuz6Ew9ufsFD04w "You can enable the Agentic Desktop application (sn_desktop_agents) if you have the admin role."). * Download the Agentic Desktop installer to automate repetitive tasks across applications and systems. For more information, see [Download Agentic Desktop installer](https://servicenow-prod.fluidtopics.net/8a6cxzdJtIn~YN5M~hnP4w "Download the Agentic Desktop installer so that you can install Agentic Desktop on your Windows machine for designing and running desktop actions."). {#manual-create-desktop-action-ad__ul_urn_w5j_y2c} Confirm that the following system requirements are met: * Windows 11 operating system is used. * A .NET 9.0 runtime v9.0.10 and .NET 9 Desktop Runtime v9.0.10 is installed. * No extended monitors are connected. * Theme must match between the systems used for recording and execution. * Remote Desktop must be enabled on your machine and your account must be granted Remote Desktop access permissions before you start using the Agentic Desktop Execution workspace. {#manual-create-desktop-action-ad__ul_gcr_cv3_hhc} Familiarize yourself with the Design workspace and Action recorder. For more information, see [Agentic Desktop Design workspace](https://servicenow-prod.fluidtopics.net/Fu0GWG9zICohe3YooYNCBQ "The Design workspace is an interactive environment within Agentic Desktop 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.") and [Action recorder in Agentic Desktop](https://servicenow-prod.fluidtopics.net/JW~NZoUC2S4aanWViaxzIg "With Action recorder, you can auto-capture steps to automate repetitive tasks in Agentic Desktop. You can save the steps that you perform on the application elements as a reusable desktop action of type UI block."). Role required: sn_aia.admin ## Por Que e Quando Desempenhar Esta Tarefa You can simulate a user interaction in an automation by manually capturing screens and defining steps. Using the controls in the window, you can capture an area of an application window. You can then set one or more anchors, and define steps that represent the user interactions in that window. * Anchor: Anchors help specify the target area for the interaction by defining a static area from which steps can be defined at a relative distance. * Step: Steps are your sequential interactions of type click, select, type, scroll, and more. {#manual-create-desktop-action-ad__ul_sy4_bjd_3hc} Nota: If your automation requires manual inputs, such as entering an OTP or CAPTCHA, you must provide instructions to the AI Agent to wait for the user input during execution. Otherwise, the automation can't proceed. ## Procedimento 1. From your Windows system, launch the Agentic Desktop application. 2. On the login page, in the Add ServiceNow URL field, enter the ServiceNow instance URL. For example, https://\.service-now.com. 3. Select Proceed. 4. Log in to your ServiceNow account by entering your user name and password. Your account must have the sn_aia.admin role. 5. On the Agentic Desktop home page, select Create desktop action. 6. In the New desktop action dialog box, select Manual capture steps. 7. Enter a name and description for the desktop action. 8. Select Start capturing. The Design workspace is displayed. 9. Capture screens. 1. In the Design tab, select the Capture Options icon ![](). {#manual-create-desktop-action-ad__ad-manual-capture-step-1} {#manual-create-desktop-action-ad__ad-manual-capture-step-1} 2. Select Manual capture screens. The Agentic Desktop window is minimized and the Capture panel is launched. {#manual-create-desktop-action-ad__ad-manual-capture-step-2} {#manual-create-desktop-action-ad__ad-manual-capture-step-2} 3. Open the applications that you want to automate steps for. 4. Capture the area of the external application's window by selecting the Select icon on the Capture panel or pressing the Ctrl + Shift + C on the keyboard. Nota: If the Ctrl + Shift + C shortcut conflicts with another application on the your machine, such as Zoom, then you must use the Select button to initiate manual screen capture. For example, you can capture the area surrounding a button or a text field in a web browser. The cursor icon changes to the icon. {#manual-create-desktop-action-ad__ad-manual-capture-step-3} {#manual-create-desktop-action-ad__ad-manual-capture-step-3} 5. Drag the icon and select the required screen area. When you leave the icon, the selected area is captured as a screenshot in the Design workspace. If you are not satisfied with the captured screen, you can recapture the screen area by selecting the Capture image icon ![](). {#manual-create-desktop-action-ad__ad-manual-capture-step-4} {#manual-create-desktop-action-ad__ad-manual-capture-step-4} {#manual-create-desktop-action-ad__substeps_rh5_k1s_ghc} 10. Insert anchors. 1. Insert an anchor on the captured screen by selecting the Add anchor icon . An anchor is a reference point on the screen that helps the automation identify and interact with a nearby UI elements. During execution, the system uses computer vision to locate the anchor and then identifies the UI elements at a related distance from the anchor. Anchors improve the stability and accuracy of steps when the target element's location may shift or when the UI layout varies across sessions. Nota: Do not use dynamically changing UI elements as anchors. If an element changes its color, text, or state after an action (for example, after a click), select a different anchor that remains static on the screen. 2. Move the anchor to a part of the captured image that won't change. For example, move the anchor to a title or field label. If the area under the anchor doesn't exactly match the corresponding area of the captured image, the anchor isn't recognized, and the steps are not performed as intended. Choose a static area of the image for setting your anchor. You can add multiple anchors on each screen. Multiple anchors let you define the geographical relationship between anchor and target with greater accuracy when targeting different locations in the image. {#manual-create-desktop-action-ad__substeps_xt2_r1s_ghc} 11. Configure the steps. 1. From the Anchor control menu, select the Add step icon . 2. Select the type of step to perform for this step from the contextual menu. {#manual-create-desktop-action-ad__table_vtf_jds_ghc__entry__4} | Goal | Step | Type | Example | |-|-|-|-| | Enter text in a field | Set Text | Input | Enter any text data such as a user name, an address, a survey response, or in any situation where text entry is accepted. Nota: If you set a static value for this field, the automation uses it during execution and doesn't prompt you for input from the Now Assist panel. | | Simulate a mouse click | Click | Input | Click a button, open a menu, or perform any step typically performed by a mouse click. | | Simulate an alternative mouse action (for example, right-click, drag, scroll, or paste) | Mouse Click | Input | Perform various mouse device actions, such as right-click and select an object or scroll on a web page. | | Simulate a key press or a key function | Send Keys | Input | Perform keyboard shortcuts, such as copying text by entering Ctrl + C on fields and elements. Nota: If you set a static value for this field, the automation uses it during execution and doesn't prompt you for input from the Now Assist panel. | | Capture text from a window or web page | Get Text | Output | Receive text from the source area. | | Capture a table | Get Table | Output | Receive table from the source area when the text is in the table format. Nota: For the step to capture table data successfully, the data must already be in the table form. The step can't convert ordinary text to table data. | | Read text from an image | OCR Read Text | Output | Recognize text from images and return it in the standard text format. | [Tabela 1. Description of the actions] {#manual-create-desktop-action-ad__table_vtf_jds_ghc} You can add multiple steps representing your automation steps. {#manual-create-desktop-action-ad__substeps_hng_klr_khc} 12. Configure the properties for added screens, anchors, and steps. For more information, see [Screen, anchor, and step properties in Agentic Desktop](https://servicenow-prod.fluidtopics.net/0DRBoY7o6ChZ6toZBxxLUA "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."). 13. Provide names for all added screens, anchors, and steps. When you create these elements, you can edit the auto-generated name, but follow these naming guidelines. * Name fields must not be empty. * Name fields must contain only alphanumeric characters. Spaces and special characters are not permitted. * Each name must be unique at its respective parent level. * Each screen must have a unique name at the desktop-action level. * Each anchor must have a unique name at the screen level. * Each step must have a unique name at the anchor level. {#manual-create-desktop-action-ad__ul_om5_wnz_3hc} {#manual-create-desktop-action-ad__ul_sjm_tnz_3hc} ## O que Fazer Depois 1. Configure the details of your desktop action. For more information, see [Add details to desktop actions in Agentic Desktop](https://servicenow-prod.fluidtopics.net/4yMt9yc~TSXmrYYINWKLRg "Add desktop action details, such as name, description, and associated applications, and review inputs and outputs."). 2. Test and activate the desktop action so that it can be added as a tool to AI agents. For more information, see [Test and activate a desktop action in Agentic Desktop](https://servicenow-prod.fluidtopics.net/RqGSwWEICDLMAfhJsT3Qsw "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."). 3. Add the desktop action as a tool to AI agents in AI Agent Studio. For more information, see [Add a desktop action to an AI agent](https://servicenow-prod.fluidtopics.net/Ieo2VWTQR4Mlp9adasf8Bg "Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can perform desktop actions for repetitive tasks."). {#manual-create-desktop-action-ad__ol_slm_313_hhc} **Conceitos relacionados** * [Agentic Desktop Design workspace](https://servicenow-prod.fluidtopics.net/Fu0GWG9zICohe3YooYNCBQ "The Design workspace is an interactive environment within Agentic Desktop 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.") * [Examples of creating desktop actions](https://servicenow-prod.fluidtopics.net/CXO0VNaPRf~Sza3SUZ0_kQ "Learn the key concepts and workflow for creating end-to-end desktop actions and building automations for your desktop environments.") * [Examples of executing desktop actions using AI agents](https://servicenow-prod.fluidtopics.net/bpk9Wv2o69LdHwWx72hI~Q "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.") **Tarefas relacionadas** * [Automate repetitive tasks by auto-capturing steps in Agentic Desktop](https://servicenow-prod.fluidtopics.net/hUMkOkXVIItmDt0P~uwF1A "Create desktop actions by auto-capturing steps to automate repetitive tasks in Agentic Desktop. You can save the steps that you perform on the application elements as a reusable desktop action of type UI block.") * [Add a desktop action to an AI agent](https://servicenow-prod.fluidtopics.net/Ieo2VWTQR4Mlp9adasf8Bg "Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can perform desktop actions for repetitive tasks.") **Referência relacionada** * [Screen, anchor, and step properties in Agentic Desktop](https://servicenow-prod.fluidtopics.net/0DRBoY7o6ChZ6toZBxxLUA "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.")