{
  "format": "agent-article-v0",
  "article_id": "EA-050",
  "canonical_url": "/tools/ea-050-desktop-agent-ai-rpa",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EVD-EA-050-URL-800526331074",
    "EVD-EA-050-URL-3CAB0D84B00C",
    "EVD-EA-050-URL-4DDE3CD11E3A",
    "EVD-EA-050-URL-3ED7A6CAE4A3",
    "EVD-EA-050-URL-C5F3CD81FD74",
    "EVD-EA-050-URL-580B8A0A8C2D",
    "EVD-EA-050-URL-D7F007864A6D",
    "EVD-EA-050-URL-51BC8AA1690C",
    "EVD-EA-050-URL-FFBEF51B3785",
    "EVD-EA-050-URL-DD3C5207FF0D",
    "EA-050-R11-RESEARCH",
    "EA-050-R11-WEB-READBACK"
  ],
  "unknown_ids": [
    "EA-050-UNKNOWN-01",
    "EA-050-UNKNOWN-CURRENTNESS"
  ],
  "operational_object_ids": [],
  "provider": [
    "Microsoft"
  ],
  "models": [],
  "plans": [],
  "surfaces": [],
  "regions": [],
  "current_status": "UNKNOWN",
  "observation_status": "SPEC_ONLY",
  "freshness": "UNKNOWN",
  "last_verified": null,
  "supersedes": [],
  "superseded_by": [],
  "provenance": [
    "COMM-051-EA0050",
    "SRC-EA-050-URL-800526331074",
    "SRC-EA-050-URL-3CAB0D84B00C",
    "SRC-EA-050-URL-4DDE3CD11E3A",
    "SRC-EA-050-URL-3ED7A6CAE4A3",
    "SRC-EA-050-URL-C5F3CD81FD74",
    "SRC-EA-050-URL-580B8A0A8C2D",
    "SRC-EA-050-URL-D7F007864A6D",
    "SRC-EA-050-URL-51BC8AA1690C",
    "SRC-EA-050-URL-FFBEF51B3785",
    "SRC-EA-050-URL-DD3C5207FF0D",
    "WEBBODY-EA0050-R8-0191A0E1"
  ],
  "article_sources": [
    {
      "id": "EVD-EA-050-URL-800526331074",
      "evidence_class": "RESEARCH",
      "title": "1) official product docs | \"Automate web and desktop apps with computer use\" | Microsoft |",
      "href": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/computer-use",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-800526331074"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "1) official product docs | \"Automate web and desktop apps with computer use\" | Microsoft | https://learn.microsoft.com/en-us/microsoft-copilot-studio/computer-use"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-3CAB0D84B00C",
      "evidence_class": "RESEARCH",
      "title": "2) official product docs | \"Configure where computer use runs\" | Microsoft |",
      "href": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/configure-where-computer-use-runs",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-3CAB0D84B00C"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "2) official product docs | \"Configure where computer use runs\" | Microsoft | https://learn.microsoft.com/en-us/microsoft-copilot-studio/configure-where-computer-use-runs"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-4DDE3CD11E3A",
      "evidence_class": "RESEARCH",
      "title": "3) official product docs | \"Run unattended desktop flows\" | Microsoft |",
      "href": "https://learn.microsoft.com/en-us/power-automate/desktop-flows/run-unattended-desktop-flows",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-4DDE3CD11E3A"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "3) official product docs | \"Run unattended desktop flows\" | Microsoft | https://learn.microsoft.com/en-us/power-automate/desktop-flows/run-unattended-desktop-flows"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-3ED7A6CAE4A3",
      "evidence_class": "RESEARCH",
      "title": "4) official product docs | \"Robots\" | UiPath Orchestrator |",
      "href": "https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/about-robots",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-3ED7A6CAE4A3"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "4) official product docs | \"Robots\" | UiPath Orchestrator | https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/about-robots"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-C5F3CD81FD74",
      "evidence_class": "RESEARCH",
      "title": "5) official product docs | \"Configuring automation capabilities\" | UiPath Orchestrator |",
      "href": "https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/configuring-automation-capabilities",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-C5F3CD81FD74"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "5) official product docs | \"Configuring automation capabilities\" | UiPath Orchestrator | https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/configuring-automation-capabilities"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-580B8A0A8C2D",
      "evidence_class": "RESEARCH",
      "title": "6) official platform spec/docs | \"UI Automation Specification\" | Microsoft Windows |",
      "href": "https://learn.microsoft.com/en-us/windows/win32/winauto/ui-automation-specification",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-580B8A0A8C2D"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "6) official platform spec/docs | \"UI Automation Specification\" | Microsoft Windows | https://learn.microsoft.com/en-us/windows/win32/winauto/ui-automation-specification"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-D7F007864A6D",
      "evidence_class": "RESEARCH",
      "title": "7) official security docs | \"UI Automation Security Overview\" | Microsoft |",
      "href": "https://learn.microsoft.com/en-us/dotnet/framework/ui-automation/ui-automation-security-overview",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-D7F007864A6D"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "7) official security docs | \"UI Automation Security Overview\" | Microsoft | https://learn.microsoft.com/en-us/dotnet/framework/ui-automation/ui-automation-security-overview"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-51BC8AA1690C",
      "evidence_class": "RESEARCH",
      "title": "8) official failure report | \"Fix: Power Automate desktop Windows credential dialog issues\" | Microsoft |",
      "href": "https://learn.microsoft.com/en-us/troubleshoot/power-platform/power-automate/desktop-flows/windows-credentials-dialog-issues",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-51BC8AA1690C"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "8) official failure report | \"Fix: Power Automate desktop Windows credential dialog issues\" | Microsoft | https://learn.microsoft.com/en-us/troubleshoot/power-platform/power-automate/desktop-flows/windows-credentials-dialog-issues"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-FFBEF51B3785",
      "evidence_class": "RESEARCH",
      "title": "9) primary research + author-maintained implementation | \"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments\" | Xie et al. / xlang-ai |",
      "href": "https://github.com/xlang-ai/OSWorld",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-FFBEF51B3785"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "9) primary research + author-maintained implementation | \"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments\" | Xie et al. / xlang-ai | https://github.com/xlang-ai/OSWorld"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-EA-050-URL-DD3C5207FF0D",
      "evidence_class": "RESEARCH",
      "title": "10) primary research implementation | \"OS-Blind: The Blind Spot of Agent Safety\" | lime-nlp |",
      "href": "https://github.com/limenlp/OS_Blind",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "SOURCE_PACKET_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-EA-050-URL-DD3C5207FF0D"
      ],
      "supporting_locators": [
        "EVIDENCE TABLE",
        "10) primary research implementation | \"OS-Blind: The Blind Spot of Agent Safety\" | lime-nlp | https://github.com/limenlp/OS_Blind"
      ],
      "scope": "EVIDENCE TABLE",
      "provenance_status": "SOURCE_PACKET_REFERENCE_PROJECTED"
    },
    {
      "id": "EA-050-R11-RESEARCH",
      "evidence_class": "RESEARCH",
      "title": "EA-050 監査済みresearch / canonical revision binding",
      "supports": [
        "- Desktop automation has at least two execution paradigms: (A) selector/UIA/action-graph based deterministic RPA and (B) screenshot/vision/reasoning based CUA. They can share host/session/credential infrastructure but should not share the same reliability assumptions.\n- Windows UI Automation provides structured control semantics; CUA can act when selectors/APIs are unavailable or UI changes, but model reasoning introduces probabilistic action selection. Future Core should therefore prefer API/structured automation where available, deterministic UI automation next, and CUA as a bounded fallback or explicitly governed execution path rather than treating CUA as a drop-in replacement.\n- unattended foreground automation is an identity-and-session problem, not merely a model capability problem. Microsoft and UiPath both require execution infrastructure and user/session credentials or equivalent non-human identity configuration for foreground UI interaction.\n- Dedicated execution machines/VMs are operationally meaningful. Microsoft explicitly recommends dedicating a machine for computer use; same-machine jobs queue sequentially. Shared interactive desktops create interruption, state leakage, contention and attribution problems.\n- OS privilege boundaries remain effective constraints. Windows UIA cannot simply cross protected/high-integrity UI by default. AI reasoning does not remove UAC/uiAccess boundaries.\n- conventional RPA is not immune to platform drift: a 2026 Windows security update broke credential-dialog automation. Therefore deterministic selectors are more reproducible than CUA, but not invariant to OS/security changes."
      ],
      "limit": "canonical監査・revision bindingの存在を示す。外部ソースcurrentnessが本文またはcontrol-planeで確定していない場合は、currentnessをUNKNOWNのまま保持する。",
      "origin_class": "AUDITED_CANONICAL_RESEARCH_PACKET",
      "source_or_experiment_ids": [
        "COMM-051-EA0050"
      ],
      "supporting_locators": [
        "COMM-051-EA0050",
        "EA-050-R5-LEGACY-MIGRATION-20261008-R1",
        "content/staging/EA-050.md"
      ],
      "scope": "監査済みEA本文・canonical revision・既存Source Graph relationの範囲。欠損currentnessは推測で閉じない。",
      "provenance_status": "AUDIT_PASS_CANONICAL_BINDING"
    },
    {
      "id": "EA-050-R11-WEB-READBACK",
      "evidence_class": "IMPL",
      "title": "EA-050 Web body identity / canonical readback",
      "supports": [
        "canonical staging bodyのSHA-256一致とR9 canonical ledger readbackをProduction projectionの入力として検証する。"
      ],
      "limit": "body identity/readbackは本文claim自体の真偽や外部ソースの最新性を追加保証しない。",
      "checked_at": null,
      "origin_class": "IMPLEMENTATION_READBACK",
      "source_or_experiment_ids": [
        "WEBBODY-EA0050-R8-0191A0E1"
      ],
      "supporting_locators": [
        "WEBBODY-EA0050-R8-0191A0E1",
        "content/staging/EA-050.md",
        "EA-050-R5-LEGACY-MIGRATION-20261008-R1"
      ],
      "scope": "R9/R10 canonical readback後のProduction生成時body identity。",
      "provenance_status": "CANONICAL_READBACK_BODY_HASH_MATCH"
    }
  ],
  "research_sections": [
    {
      "heading": "WHY_THIS_MATTERS_TO_UPDATE",
      "text": "EnterpriseのGUI自動化は、従来RPAの決定論的selector/UI Automationと、Computer-Using Agent（CUA）の視覚・推論ベース操作が同じdesktop surfaceへ収束しつつある。両者は失敗様式、権限境界、credential/session要件、監査可能性、コスト構造が異なるため、公開後アップデートでは「AI-RPA」を単一機能として扱わず実行層を分離する必要がある。"
    },
    {
      "heading": "SCOPE_ROUTING",
      "text": "Enterprise AI Core / provider mapping / organization overlay / governance / benchmark / implementation / non-LLM component"
    },
    {
      "heading": "CLAIM_OR_RESEARCH_QUESTION",
      "text": "1. Desktop Agentと従来RPAを同一の運用モデルで扱えるか。\n2. unattended GUI executionで最低限分離すべきidentity/session/machine/privilege境界は何か。\n3. GUI agent benchmarkの成功率を業務自動化の信頼性へ外挿できるか。\n4. deterministic UI automationとvision/reasoning CUAをどう組み合わせるのが安全か。"
    },
    {
      "heading": "EVIDENCE TABLE",
      "text": "1) official product docs | \"Automate web and desktop apps with computer use\" | Microsoft | https://learn.microsoft.com/en-us/microsoft-copilot-studio/computer-use | updated 2026-07-03 / accessed 2026-09-14 | Copilot Studio computer use; OpenAI CUA / Claude Sonnet 4.5/4.6 / Claude Opus 4.6; billing 5 or 15 Copilot Credits per step | locator: Licensing / model table / overview | VERIFIED_SPEC + PRODUCT_VOLATILE | support/context\n2) official product docs | \"Configure where computer use runs\" | Microsoft | https://learn.microsoft.com/en-us/microsoft-copilot-studio/configure-where-computer-use-runs | updated 2026-08-03 / accessed 2026-09-14 | Power Automate for desktop >= 2.61.132.25266 for BYOM; dedicated machine recommendation; sequential queue on same machine | locator: Bring-your-own-machine / Run scheduling and queuing | VERIFIED_SPEC + PRODUCT_VOLATILE | support/limit\n3) official product docs | \"Run unattended desktop flows\" | Microsoft | https://learn.microsoft.com/en-us/power-automate/desktop-flows/run-unattended-desktop-flows | accessed 2026-09-14 | managed Windows user session; target-device session constraints; RDP permission required; authored vs unattended screen-resolution divergence | locator: unattended run behavior and session requirements | VERIFIED_SPEC + PRODUCT_VOLATILE | support/limit\n4) official product docs | \"Robots\" | UiPath Orchestrator | https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/about-robots | accessed 2026-09-14 | Automation Cloud current docs; unattended foreground UI requires host-machine credentials; background Session 0 can run without user credentials | locator: With credentials / Without credentials | VERIFIED_SPEC + PRODUCT_VOLATILE | support/context\n5) official product docs | \"Configuring automation capabilities\" | UiPath Orchestrator | https://docs.uipath.com/orchestrator/automation-cloud/latest/user-guide/configuring-automation-capabilities | accessed 2026-09-14 | robot accounts as non-human identities; roles authorize Orchestrator resources; unattended execution bound to infrastructure | locator: Enabling unattended automation on a robot account | VERIFIED_SPEC + PRODUCT_VOLATILE | support\n6) official platform spec/docs | \"UI Automation Specification\" | Microsoft Windows | https://learn.microsoft.com/en-us/windows/win32/winauto/ui-automation-specification | accessed 2026-09-14 | Windows UI Automation element tree exposes controls/properties/patterns from desktop root | locator: UI Automation Elements / UI Automation Tree | VERIFIED_SPEC | context\n7) official security docs | \"UI Automation Security Overview\" | Microsoft | https://learn.microsoft.com/en-us/dotnet/framework/ui-automation/ui-automation-security-overview | updated 2025-06-17 / accessed 2026-09-14 | uiAccess=false by default; protected UI/high-integrity interaction requires explicit trust/signing/manifest conditions | locator: User Account Control / Manifest File | VERIFIED_SPEC | limit/security\n8) official failure report | \"Fix: Power Automate desktop Windows credential dialog issues\" | Microsoft | https://learn.microsoft.com/en-us/troubleshoot/power-platform/power-automate/desktop-flows/windows-credentials-dialog-issues | updated 2026-03-20 / accessed 2026-09-14 | Jan/Feb 2026 Windows security updates caused credential-dialog automation failures; cloud unattended runs cannot use the local-admin workaround | locator: affected KBs / Workarounds | SOURCE_REPORT + PRODUCT_VOLATILE | counter/failure\n9) primary research + author-maintained implementation | \"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments\" | Xie et al. / xlang-ai | https://github.com/xlang-ai/OSWorld | NeurIPS 2024; repo accessed 2026-09-14 | OSWorld / OSWorld-Verified; real computer tasks across Ubuntu/Windows/macOS | locator: README / public evaluation / citation | RESEARCH + OSS_PRACTICE | benchmark/context\n10) primary research implementation | \"OS-Blind: The Blind Spot of Agent Safety\" | lime-nlp | https://github.com/limenlp/OS_Blind | accessed 2026-09-14 | 300 human-crafted tasks, 12 safety categories; environment-embedded and agent-initiated harms | locator: Dataset Overview | RESEARCH + OSS_PRACTICE | counter/security"
    },
    {
      "heading": "FINDINGS",
      "text": "- Desktop automation has at least two execution paradigms: (A) selector/UIA/action-graph based deterministic RPA and (B) screenshot/vision/reasoning based CUA. They can share host/session/credential infrastructure but should not share the same reliability assumptions.\n- Windows UI Automation provides structured control semantics; CUA can act when selectors/APIs are unavailable or UI changes, but model reasoning introduces probabilistic action selection. Future Core should therefore prefer API/structured automation where available, deterministic UI automation next, and CUA as a bounded fallback or explicitly governed execution path rather than treating CUA as a drop-in replacement.\n- unattended foreground automation is an identity-and-session problem, not merely a model capability problem. Microsoft and UiPath both require execution infrastructure and user/session credentials or equivalent non-human identity configuration for foreground UI interaction.\n- Dedicated execution machines/VMs are operationally meaningful. Microsoft explicitly recommends dedicating a machine for computer use; same-machine jobs queue sequentially. Shared interactive desktops create interruption, state leakage, contention and attribution problems.\n- OS privilege boundaries remain effective constraints. Windows UIA cannot simply cross protected/high-integrity UI by default. AI reasoning does not remove UAC/uiAccess boundaries.\n- conventional RPA is not immune to platform drift: a 2026 Windows security update broke credential-dialog automation. Therefore deterministic selectors are more reproducible than CUA, but not invariant to OS/security changes."
    },
    {
      "heading": "LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE",
      "text": "- Vendor statements that CUA \"adapts\" to UI changes are product claims, not guarantees of task correctness across arbitrary layouts.\n- OSWorld/OSWorld-Verified evaluates bounded benchmark tasks; scores do not establish production SLA, security, or success on organization-specific apps.\n- Desktop agents can act correctly at the GUI level yet violate hidden workflow/business rules; application semantics must be separately validated.\n- State hazards include modal dialogs, focus theft, resolution/DPI variance, localization, screen locking, concurrent user sessions, stale credentials, pop-ups, remote-desktop differences and application updates.\n- Security hazards include credential phishing, data exfiltration, destructive OS actions, malware/code execution, deceptive agreements and prompt/instruction content rendered inside applications. OS-Blind demonstrates these as evaluation categories; it does not prove prevalence in any particular product deployment.\n- A robot/service identity with correct infrastructure permissions can still hold excessive application-level permissions. Orchestrator/machine authorization and target-application authorization are separate gates."
    },
    {
      "heading": "AVAILABILITY_GATES",
      "text": "- Microsoft Copilot Studio computer use: GA announced May 2026; requires generative orchestration; model choice and Copilot Credit billing are current/product-volatile. BYOM requires supported Power Automate for desktop version and machine registration/configuration.\n- Microsoft unattended desktop flows: Windows edition/session/RDP/NLA/Entra configuration constraints apply; sovereign cloud/hosted capacity limitations vary by feature.\n- UiPath: foreground unattended UI requires appropriate machine login credentials and configured robot/non-human identity; background Session 0 differs materially.\n- Protected Windows UI: uiAccess/signing/install-location/UAC conditions can block automation even when ordinary application UI is accessible."
    },
    {
      "heading": "IMPLEMENTATION_STATE",
      "text": "MATURE for deterministic enterprise RPA; DEPLOYED/GA but rapidly evolving for CUA-assisted desktop automation. Recommended implementation pattern for future book: task router -> API/connector path when available -> deterministic RPA/UIA path -> governed CUA fallback; all paths terminate in common identity/policy/audit controls. Separate attended, unattended-foreground, background/session-0, and hosted/dedicated-machine profiles."
    },
    {
      "heading": "BENCHMARK_OR_EVAL",
      "text": "Use OSWorld/OSWorld-Verified for cross-application capability evaluation and OS-Blind for safety evaluation. Do not merge capability score with safety score. For organization acceptance, create a private evaluation corpus from real applications with: deterministic completion checks, forbidden-action checks, business-rule assertions, recovery/retry behavior, resolution/localization variants, and clean-state reset between runs."
    },
    {
      "heading": "SECURITY",
      "text": "least-privilege robot identity; dedicated machine/VM; prohibit unnecessary admin/uiAccess; policy-gate credential/system/security-setting changes; treat on-screen text as untrusted input for CUA."
    },
    {
      "heading": "PRIVACY",
      "text": "screenshots/video/action traces may capture sensitive desktop content; retention/access/redaction policy required separately from model prompts.\nAUDIT: log task request, initiating human/service identity, robot/agent identity, machine/session, model/version when applicable, observations, intended action, executed action, result, approval/override and artifact changes. Screenshot-only replay is insufficient without structured action/result metadata."
    },
    {
      "heading": "COST",
      "text": "deterministic RPA cost is largely infrastructure/license/run-time; CUA adds per-step model/agent consumption. Microsoft currently documents 5 Copilot Credits per standard computer-use step and 15 for premium models; re-check at publication."
    },
    {
      "heading": "OPERABILITY",
      "text": "machine image/version pinning, queue depth, stuck-session recovery, credential rotation, selector drift detection, model regression tests and rollback are first-class operations concerns."
    },
    {
      "heading": "SAFE_WORDING_FOR_FUTURE_BOOK",
      "text": "「Desktop Agent／AI-RPAは、従来RPAをAIで置き換えた単一カテゴリではない。API、structured UI automation、vision/reasoning computer useは異なる失敗様式を持つ実行経路であり、同じidentity・policy・machine isolation・audit境界の下で使い分ける。GUI操作が可能であることは、業務ルール上正しいこと、権限上許可されること、再現可能であることを意味しない。」"
    },
    {
      "heading": "UPDATE_WORK_HANDOFF",
      "text": "1. 公開後本文では「desktop execution hierarchy」をCore化し、API > structured deterministic automation > governed CUAという優先経路を候補にする。\n2. provider mappingではMicrosoft Copilot Studio/Power AutomateとUiPathを、機能比較ではなくidentity/session/machine/queue/audit軸でマッピングする。\n3. publication時にMicrosoft computer-use GA、model lineup、credit rate、Power Automate minimum version、UiPath current Automation Cloud docsを再確認する。\n4. 企業向けTEST_PROFILEを作る場合は専用VM、無害なsynthetic app/data、non-admin test identity、network allowlist、clean snapshot restoreを用い、real credentials/production tenantは使わない。"
    },
    {
      "heading": "OPEN_UNKNOWN",
      "text": "provider横断でCUA action trace schemaを標準化できるか、business-rule violationを一般化して検出する評価標準、各providerのscreenshot/action retentionとtenant-controlled redaction差分、CUAとdeterministic RPAの自動fallback/rollback品質。"
    },
    {
      "heading": "STOP_CONDITION",
      "text": "EA-050初回Packetとして、Core構造、current provider実装例、OS privilege/session failure、benchmark/safety反証、availability/cost gates、後続再確認点が揃ったため停止。次回はEA-051へ進む。\n\n---"
    },
    {
      "heading": "AUDITED_BOUNDARY",
      "text": "Desktop Agent/AI-RPA is layered execution design; API, deterministic UI automation and vision/reasoning CUA have distinct failure modes. Model lists, credits, hosted-machine details and tenant availability remain PRODUCT_VOLATILE. GUI action capability does not establish business-rule correctness, authorization or reproducibility. Preserve all OPEN_UNKNOWN."
    }
  ],
  "human_url": "/tools/ea-050-desktop-agent-ai-rpa",
  "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-050-desktop-agent-ai-rpa",
  "json_url": "/agent/article.json?path=%2Ftools%2Fea-050-desktop-agent-ai-rpa"
}