{
  "listings": [
    {
      "slug": "aura-autopilot",
      "name": "Aura Autopilot",
      "company": "TribeVR Inc. (named in Aura's terms of service and privacy policy), trading as Ramen",
      "grade": "C",
      "fit": "caveat",
      "why": "Verify, goal and explore runs end in a report and exit 0 confirmed, 2 denied, 3 inconclusive or 1 not achieved; regress --json writes per-regression results headless for CI. Cost shows only after a run (acc-18, open), and acc-16 hit a registration failure before any run.",
      "source": "https://raw.githubusercontent.com/ramenvr/autopilot/main/CONTRIBUTING.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/aura-autopilot"
    },
    {
      "slug": "robot-framework",
      "name": "Robot Framework",
      "company": "Robot Framework ry (Robot Framework Foundation), business ID 2754775-1, Helsinki",
      "grade": "BB",
      "fit": "caveat",
      "why": "Per-test PASS, FAIL or SKIP with messages in output.xml or JSON matching result.json, distinct return codes, and no matching tests fails unless --RunEmptySuite. acc-14 saw TestSuite.run return 0 with no tests, closed not planned; no cost is reported, though local runs cost nothing.",
      "source": "https://robotframework.org/robotframework/latest/RobotFrameworkUserGuide.html",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/robot-framework"
    },
    {
      "slug": "uipath",
      "name": "UiPath",
      "company": "UiPath Inc.",
      "grade": "B",
      "fit": "unchecked",
      "why": "UiPath has a separate Test Cloud doc set that wasn't read, so test-set execution and result formats from outside are unknown.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/uipath"
    },
    {
      "slug": "autocua",
      "name": "AutoCua",
      "company": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)",
      "grade": "D",
      "fit": "no",
      "why": "No test runner, per-test result format or exit status for suites.",
      "source": "https://github.com/ComputerUseAgent/AutoCua/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autocua"
    },
    {
      "slug": "autohotkey",
      "name": "AutoHotkey",
      "company": "AutoHotkey Foundation LLC",
      "grade": "C",
      "fit": "no",
      "why": "No test runner, per-test result format or run report; an agent would have to build one in script.",
      "source": "https://github.com/AutoHotkey/AutoHotkeyDocs/blob/v2/docs/Scripts.htm",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autohotkey"
    },
    {
      "slug": "autoit",
      "name": "AutoIt",
      "company": "AutoIt Consulting Ltd",
      "grade": "D",
      "fit": "no",
      "why": "No test runner or per-test result format.",
      "source": "https://www.autoitscript.com/autoit3/docs/intro/running.htm",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autoit"
    },
    {
      "slug": "automation-anywhere",
      "name": "Automation Anywhere",
      "company": "Automation Anywhere, Inc.",
      "grade": "D",
      "fit": "no",
      "why": "No test runner or per-test result format among the Control Room API groups listed.",
      "source": "https://docs.automationanywhere.com/r/control-room-apis/cloud-control-room-apis",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/automation-anywhere"
    },
    {
      "slug": "beam-win",
      "name": "Beam (beam.win)",
      "company": "Noats, Inc.",
      "grade": "F",
      "fit": "no",
      "why": "No test runner, results or exit status.",
      "source": "https://beam.win/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/beam-win"
    },
    {
      "slug": "mage-vl-cowork",
      "name": "Mage-VL-Cowork",
      "company": "Microsoft",
      "grade": "C",
      "fit": "no",
      "why": "No test runner or result format; OSWorld scoring is Microsoft's evaluation harness, not a product feature.",
      "source": "https://huggingface.co/microsoft/Mage-VL-Cowork/raw/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mage-vl-cowork"
    },
    {
      "slug": "robocorp",
      "name": "Robocorp",
      "company": "Sema4.ai (full legal name not confirmed)",
      "grade": "B",
      "fit": "no",
      "why": "Supplies keyword libraries; test execution and result formats come from Robot Framework, listed separately.",
      "source": "https://rpaframework.org/libraries/windows/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/robocorp"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 8,
    "after": [
      "code.open-issue",
      "agent-observability.trace-run"
    ],
    "area": "developer",
    "asks": [
      "write tests for the desktop app",
      "run the regression suite",
      "playtest the new level and tell me what broke"
    ],
    "before": [
      "code.write-feature"
    ],
    "blockers": [
      "run start hangs pending when the sandbox fails",
      "account sign-up step before the first run",
      "exit code 0 when no test matched"
    ],
    "capabilities": [
      "desktop.scripting",
      "desktop.rpa",
      "mobile.control",
      "desktop.control"
    ],
    "category": "desktop-automation",
    "categoryName": "Desktop \u0026 mobile app control",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 2,
      "tagged": 13
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "aura-autopilot",
      "robot-framework"
    ],
    "id": "desktop-automation.test-suite-run",
    "listings": {
      "caveat": 2,
      "no": 7,
      "notRead": 3,
      "tagged": 16,
      "unchecked": 1,
      "yes": 0
    },
    "name": "Write and run a UI test suite or game playtest and report results",
    "status": "draft",
    "success": "A machine-readable result per test or goal (pass, fail, error) with the step and evidence for each failure, an exit status that is never success when nothing ran, and cost reported per run.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/desktop-automation.test-suite-run.json",
    "weight": 12,
    "weightBasis": "8 of 45 accounts (Robot Framework and Aura Autopilot issues)"
  }
}
