Q Answer-format search page
Why shell calls dominate on agent-building days
✦ AI editor's answer
Compile / test / batch loops do the work. When shell exceeds 50% of tool use, it's an 'agent-building day' signal. Skip that spend and there is no next-day automation.
Source: 5 notes from this publication + operator work logs
Source notes (5)
- In Practice2026-05-26
A day spent building agents — the hands only touched the shell
6,382Shell calls — half of all tool use that day› On days when agents are being built, shell dominates — compile/test/batch loops do the work, not IDE assists.
- Tooling2026-05-23
95 hands shared one desk
95Sessions on one workspace, zero conflicts› When multiple agents share one folder, what prevents conflict is not the model — it's a shared work-ledger convention.
- Failures & Cost2026-05-22
Commands that should have been refused
874Permission denials inside 8,780 failures› Run every AI shell call through automated redaction and a gate before publish — human review is always too slow.
- In Practice2026-05-21
Five failures, one survivor at 1:40 a.m. — fixing the two-headed character
11,147Failure events across the batch› When an AI image pipeline breaks, try removing helpers (ControlNet, regional prompter, post-process segmentation) one at a time before adding more.
- In Practice2026-05-20
One character took 13 phases to ship
13Phases to ship one character› Don't try to finish an AI training pipeline in one shot — split into cleanup → training → validation across 13 phases.
Related questions