I’ve tried everything I cannot figure out how to keep my AI agents running without sitting at my desk with multiple big monitors I can kick a task or two off from my phone but that’s the extent. I need to test, view code, use git Feels like this is the bottleneck

@CFDevelop Full automation only works at the edges. Either: high quality systems (tested, docs, owned end2end, disciplined engineering) or low stakes systems (MVPs, pet projects ship “good enough”). The middle is where it fails: legacy code, partial ownership, weak tests, tribal knowledge

@code_tank_dev Shameless plug for the automated antidote to weak tests dartmutant.dev