At peak, 4 agents were mid-tool-call in the same second. One run, one job - and a headcount no single-agent tool can log. 90 agents were hired across 1 hours; 2 different models split the work by role. A dedicated supervision lane spent 103 model calls doing nothing but checkups on the rest of the team.

Where this happened.

Source events.

Detected mechanically by the impossible_scale detector from 6 telemetry event(s):

  • 9e0e1d70-4835-42e1-bd7d-a6297450ca51
  • 375c7f32-c060-4e71-992a-7e9790b6fbd6
  • 0fbb4da2-b21c-432a-ae72-d09bcaea3060
  • 3355d170-2c67-4c28-b997-b3eb87576efb
  • 5e62e9d1-aa05-4bab-8321-731c3e102fe3
  • 3809a214-1dd4-4889-b58c-f07c9bfd8caf