Niches · Desktop & mobile app control
Write and run a UI test suite or game playtest and report results
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
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.
How agents ask for it: write tests for the desktop app
, run the regression suite
, playtest the new level and tell me what broke
Does the job, with a limit 2
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Aura Autopilot C TribeVR Inc. (named in Aura's terms of service and privacy policy), trading as Ramen | 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 |
| Robot Framework BB Robot Framework ry (Robot Framework Foundation), business ID 2754775-1, Helsinki | 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 |
Couldn't check 1
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| UiPath B UiPath Inc. | UiPath has a separate Test Cloud doc set that wasn't read, so test-set execution and result formats from outside are unknown. |
Doesn't do this job 7
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| AutoCua D Ashish Yadav and contributors (ComputerUseAgent on GitHub) | No test runner, per-test result format or exit status for suites. source |
| AutoHotkey C AutoHotkey Foundation LLC | No test runner, per-test result format or run report; an agent would have to build one in script. source |
| AutoIt D AutoIt Consulting Ltd | No test runner or per-test result format. source |
| Automation Anywhere D Automation Anywhere, Inc. | No test runner or per-test result format among the Control Room API groups listed. source |
| Beam (beam.win) F Noats, Inc. | No test runner, results or exit status. source |
| Mage-VL-Cowork C Microsoft | No test runner or result format; OSWorld scoring is Microsoft's evaluation harness, not a product feature. source |
| Robocorp B Sema4.ai (full legal name not confirmed) | Supplies keyword libraries; test execution and result formats come from Robot Framework, listed separately. source |
3 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- run start hangs pending when the sandbox fails
- account sign-up step before the first run
- exit code 0 when no test matched
Around it
Before: code.write-feature. After: code.open-issue, agent-observability.trace-run.
Where this comes from
Weight 12 of 100 in Desktop & mobile app control: 8 of 45 accounts (Robot Framework and Aura Autopilot issues)
The same as data: /api/v1/use-cases/desktop-automation.test-suite-run.json, or the MCP tool get_use_case with id desktop-automation.test-suite-run. Other jobs in this category: /api/v1/niches?category=desktop-automation.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.