Or he could've used a proper tool and saved time and money. Company brain should not live in markdown.
Here is a quick test I ran over @omnigraphdb vs Markdown + Git
And this is just reads! Imagine how sensitive can write fails be
00:14
It is becoming f*cking dangerous
A 23-year-old dev from China just ran 300 Claude Code agents in parallel and hooked them to a verification layer so none of them could bullshit him
He opens the live dashboard:
- 300 agents writing and checking at the same time
- Every output
