Mahal Systems B-MoCA
Fits mobile agents that must survive device variation. Borrow the configuration randomizer and the rule-based success detector over system logs, app data and view hierarchy.
What it asks the agent to do
- do a daily phone task (alarm, settings, calls, apps) on a randomized device
- stay correct across different screen layouts, languages and icon themes
What to borrow from it
sandbox designgrading design
Caveats
Small, simple tasks; code is linked only from the project site; license not stated.
Details
| Workloads | mobile |
|---|---|
| Interaction | single turn |
| Environment | mobile |
| End state checked | Yes |
| Tools | Android emulator with randomized configuration, ADB, Appium |
| Grading | state diff, programmatic check |
| Size | 131 |
| Data | synthetic |
| Personal data | none |
| License | unknown |
| Harness | own repo |
| Status | active |