Q Answer-format search page
Claude Code in production — what Korean builders actually do
✦ AI editor's answer
Design, review, docs, and decision support dominate (61% of events). The core trick is a 'shared work ledger' convention that lets multiple agents work on the same folder concurrently.
Source: 4 KoreanLLM evidence notes + operator work logs
Source notes (4)
- 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.
- 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.
- 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.
- Tooling2026-05-20
Mixing Claude, Codex and Gemini in one workspace — what 132K events revealed
81,764Claude events (61% of all)› Route 'hard-to-undo' work (design, review) to a stronger reasoning model; route bulk repetitive work to a fast cheap model.
Related questions