--- sourceDocument: Australia Better Together sourceDocumentLink: https://www.servicenow.com/docs/r/australia/better-together Release : - australia ft:locale : - en-US ft:publication_title : - Australia Better Together ft:clusterId : - btss bundleId : - btss workflow : - Technology --- # Building desktop automations from Task Mining data # Building desktop automations from Task Mining data {#ariaid-title1} Release version: Australia Updated July 7, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 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 Building desktop automations from Task Mining data This feature enables ServiceNow customers to automatically convert desktop processes captured via Task Mining into executable AI agents for desktop automation. It supports Excel-to-browser workflows where data from Excel is entered into browser forms. The process involves capturing desktop activities, creating automation blocks and AI agents, then testing and deploying these automations. Show full answer Show less ## Automation Workflow Stages * **Stage 1: Capture and refine (Task Mining)** -- Workstation users capture end-to-end desktop processes including screenshots and UI interaction metadata. Business analysts analyze and store these as tasks in Task Mining. * **Stage 2: Automate (Task Mining + Automation Center)** -- Business analysts identify automation opportunities and create automation requests. Technical users generate automation blocks and AI agents from these requests in Automation Center. * **Stage 3: Deploy (AI Agent Studio)** -- Technical users validate, test, and deploy AI agents using AI Agent Studio with the required admin role. * **Stage 4: Execute (AI Desktop Actions)** -- Authorized users invoke deployed AI agents from the ServiceNow Otto panel to run complete desktop automations without manual intervention. ## Example Use Case For example, automating employee onboarding involves reading new hire data from Excel, entering it into HR web forms, provisioning email accounts, and updating distribution lists. Task Mining captures these multi-application steps, and technical users convert them into an automated AI agent to run the entire workflow end-to-end. ## Progressive Refinement The process supports validation and refinement at each stage to ensure accuracy and reduce deployment risks by allowing early issue detection before full automation rollout. ## Persona and Roles * **Business analyst:** Reviews captured tasks and creates automation requests. Focuses on process documentation and data validation. * **Technical user:** Develops, tests, and deploys desktop actions and AI agents with necessary admin permissions. * **Authorized user:** Executes deployed desktop actions without needing development skills. ## Key Benefits * **Automated process documentation:** Automations are built directly from Task Mining data, eliminating manual baseline construction. * **Reduced clarification cycles:** Automation artifacts include detailed steps, data mappings, UI references, and guardrails, helping developers work efficiently. * **Self-service desktop action review:** Developers can validate desktop actions on their own machines to ensure process accuracy. * **AI agent pre-population:** AI Agent Studio is automatically populated with agent details sourced from task data, speeding up authoring. * **Reduced development time:** Predefined tool connections and configurations save time compared to building automations from scratch. ## Next Steps ServiceNow customers can explore creating automation requests in Task Mining, generating automation blocks in Automation Center, and building and deploying AI agents in AI Agent Studio. Additional resources cover setting up Task Mining projects, installing agents, categorizing activities, and executing desktop actions. Automatically convert desktop processes into executable AI agents: capture the task (desktop processes) in Task Mining, create desktop actions (automation blocks) and AI agent in Automation Center, and test and deploy the AI agent in AI Agent Studio. This feature currently supports only Excel-to-browser interactions, where data is copied from a Microsoft Excel file and it is entered into a form in a browser. Note: This feature uses generative AI to produce automation. AI-generated content, including automation blocks and agent instructions, may be inaccurate or incomplete. Review and validate AI-generated output before activating an agent. ## Automation workflow stages {#creating-desktop-actions-tm-ac__section_workflow_stages} [Stage 1: Capture and refine (Task Mining)](https://www.servicenow.com/docs/access?context=task-mining&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) : * Workstation users use the Task Mining agent to capture their desktop processes end-to-end, including interactions across multiple applications for the selected project. Agent captures screenshots and UI interaction metadata of steps users perform. * Business analyst runs a mining job on the project to generate an analysis of the collected data (desktop activities). * Captured desktop activities are stored as tasks in Task Mining. {#creating-desktop-actions-tm-ac__ul_h53_l53_vjc} [Stage 2: Automate (Task Mining + Automation Center)](https://www.servicenow.com/docs/Ob3smNs~cGax1sABAdh2kg "As a business analyst, review the task timeline for identifying task optimization opportunities and automation candidates. Then, submit an automation request from Task Mining to create an automation in Automation Center.") : * Business analysts review the task timeline to define specific optimization opportunities and automation candidates, and submit an automation request for the task in Task Mining. * Automation Center captures the structured data in an automation request for AI-powered step generation and automation block creation. * Technical users generate automation blocks (on-screen and background tasks) from the automation request in Automation Center. * Based on the automation request, an AI agent and desktop actions are created in Automation Center. {#creating-desktop-actions-tm-ac__ul_lyd_s3p_vjc} [Stage 3: Deploy (AI Agent Studio)](https://www.servicenow.com/docs/access?context=configure-next-best-action-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) : * Technical users with the sn_aia.admin role verify auto-generated agent name and description, agent steps, and desktop action tools in AI Agent Studio. * Technical users test and deploy the AI agent in AI Agent Studio. {#creating-desktop-actions-tm-ac__ul_fpf_332_wjc} [Stage 4: Execute (AI Desktop Actions)](https://www.servicenow.com/docs/access?context=use-agentic-desktop&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) : * Authorized users invoke deployed AI agents from the ServiceNow Otto panel, where the agent automatically executes the complete desktop automation process. * The agent runs both background tasks (such as fetching data from source files) and on-screen tasks (such as navigating web applications and entering form data) desktop actions in AI Desktop Actions on the Windows machine, completing the entire workflow without user intervention. {#creating-desktop-actions-tm-ac__ul_olt_j32_wjc} ## Example: Employee onboarding automation {#creating-desktop-actions-tm-ac__section_ad4_wxt_gkc} A human resources team needs to automate the employee onboarding process. Each new hire currently requires: 1. Reading new hire data from an Excel spreadsheet (background task) for creating an employee record in the HR system 2. Entering employee information into a web form (on-screen task) 3. Provisioning an email account in Microsoft 365 (on-screen task) 4. Adding the new hire to the team distribution list in Microsoft Outlook (on-screen task) This multi-application workflow is ideal for desktop automation. The team uses Task Mining to capture the actual onboarding steps performed by HR staff. Then, the technical user converts those steps into an automated agent that can execute the entire workflow end-to-end. ## Progressive refinement {#creating-desktop-actions-tm-ac__section_dqf_jbp_vjc} The workflow supports progressive refinement at each stage: 1. Validate Task Mining captured the right interactions. 2. Verify Automation Center extracted meaningful workflow components. 3. Validate on-screen task desktop actions on the AI Desktop Actions design workspace. 4. Verify the description and instructions of the AI agent and test it in AI Agent Studio. 5. Execute the complete workflow end-to-end in AI Desktop Actions execution workspace. {#creating-desktop-actions-tm-ac__ol_ekl_3bp_vjc} This staged approach reduces risk and enables early detection of issues before deploying full automations. ## Persona and roles {#creating-desktop-actions-tm-ac__section_personas_roles} The automation creation journey involves four key personas: {#creating-desktop-actions-tm-ac__table_xzn_lwc_vjc__entry__3} | Persona | Responsibilities | Key skill | |-|-|-| | Business analyst | Reviews tasks, edits captured steps, and creates Automation Request records in Task Mining. | Process documentation, data validation | | Technical user | Creates production-ready desktop actions and AI agents from the automation request in Task Mining. Reviews and approves desktop actions. Deploys agents to target instances and performs end-to-end testing in AI Agent Studio. Note: The sn_aia.admin role is required for editing and testing the AI agent. | Automation development, testing, deployment | | Authorized user | Business users, process owners, or operations team members with no automation development experience execute desktop actions in the Windows environment. Note: The now_assist_panel_user role is required for executing the desktop actions in AI Desktop Actions. | Executing desktop actions | [Table 1. Persona and roles] {#creating-desktop-actions-tm-ac__table_xzn_lwc_vjc} ## Key benefits {#creating-desktop-actions-tm-ac__section_key_benefits} Automated process documentation : By building automation skeletons directly from Task Mining data, ServiceNow eliminates the need to manually construct baseline automation logic. Reduced clarification cycles : Automation artifacts include desktop actions, task steps, input/output mappings, and guardrails.Developers receive a pre-configured structure that already contains: * Identified steps in the correct sequence * Relevant data mappings * UI element references * Initial tool connections {#creating-desktop-actions-tm-ac__ul_t31_h1p_vjc} Self-service desktop action review : Developers can open and validate desktop actions on their own Windows machine, ensuring captured intent matches actual process steps. AI agent pre-population : AI Agent Studio is automatically populated with agent name, specialty description, tools, and tool descriptions sourced directly from the task breakdown. Reduction in authoring time : This approach saves development time compared to building agents from scratch without predefined tool connections and configurations. ## What to explore next {#creating-desktop-actions-tm-ac__section_q14_v1f_wjc} * [Requirements and limitations](https://www.servicenow.com/docs/GMRSL9YFUwR8uQOzF24aww "Learn about requirements and limitations for this unified journey.") * [Create an automation request in Task Mining](https://www.servicenow.com/docs/Ob3smNs~cGax1sABAdh2kg "As a business analyst, review the task timeline for identifying task optimization opportunities and automation candidates. Then, submit an automation request from Task Mining to create an automation in Automation Center.") * [Create automation blocks from the automation request in Automation Center](https://www.servicenow.com/docs/kCeztAMUYFTkeNkQtDD7DA "Create automation blocks (on-screen tasks and background tasks) using the automation request created in Task Mining. These automation blocks are used to create desktop actions and AI agent in Automation Center.") * [Create an AI agent and desktop actions from Automation Center](https://www.servicenow.com/docs/TwOfBhEgPx7hQRefCVdBOw "After reviewing the automation blocks generated from an automation request, create an AI agent that executes desktop actions on a Windows machine.") {#creating-desktop-actions-tm-ac__ul_ltm_w1f_wjc} **Related topics** * [Create Task Mining project](https://www.servicenow.com/docs/access?context=create-task-mining-project&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) * [Create a Task Mining project](https://www.servicenow.com/docs/access?context=create-task-mining-projects&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) * [Install the Task Mining agent](https://www.servicenow.com/docs/access?context=install-agent&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) * [Categorize workstation activities to simplify analysis](https://www.servicenow.com/docs/access?context=define-default-categorization-rules&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) * [Task Mining agent](https://www.servicenow.com/docs/access?context=task-mining-agent-features-and-workarounds&version=australia&pubname=australia-now-intelligence&ft:locale=en-US) * [Defined desktop actions in AI Desktop Actions](https://www.servicenow.com/docs/access?context=desktop-actions-designer-workspace-ad&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Test and activate a desktop action in AI Desktop Actions](https://www.servicenow.com/docs/access?context=test-activate-desktop-action-ad&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Create an AI agent](https://www.servicenow.com/docs/access?context=configure-next-best-action-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Examples of executing desktop actions using AI agents](https://www.servicenow.com/docs/access?context=use-agentic-desktop&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US)