Show HN: Andon – Toyota Production System for LLM Coding Agents
LLM coding agents (Claude Code, Codex, etc.) have structural weaknesses: blind retry loops, volatile learning, silent spec drift, and gate gaming. These aren't bugs in specific models — they're properties of goal-optimizing systems. ANDON applies Toyota Production System principles to address this: - Jidoka (autonomation): auto-detect failures and block forward-progress commands (git push, deploy) - Kaizen (continuous improvement): force Five Whys root cause analysis, then standardize prevention
阅读原始来源
来源记录
指标快照
points · 3 votes
2026-11-06 22:15:22.566Z
cumulative since publication
研究分析
项目记录
仓库：allnew-llc/andon-for-llm-agents。 来源描述：LLM coding agents (Claude Code, Codex, etc.) have structural weaknesses: blind retry loops, volatile learning, silent spec drift, and gate gaming. These aren't bugs in specific models — they're properties of goal-optimizing systems. ANDON applies Toyota Production System principles to address this: - Jidoka (autonomation): auto-detect failures and block forward-progress commands (git push, deploy) - Kaizen (continuous improvement): force Five Whys root cause analysis, then standardize prevention
采用记录与比较对象
来源票数: 3 votes (2026年11月6日 UTC; cumulative since publication)；前次同口径记录为 3（2026年11月6日 UTC），两个观测值不等于需求增长。 可供比较的近期同类记录：“google/skills” (GitHub Trending, 2026年11月6日)；“mattpocock/skills” (GitHub Trending, 2026年11月6日)。主题相近仅用于导航，未核验其是否属于同一需求或独立证据。
采用判断
应与它要替代的工具或人工流程比较。现有记录支持发现项目，尚不能确认可靠性、运行成本优势或商业采用。
尚未核验的门槛
尚未核验：许可证权限、硬件要求、安装步骤、维护状态，以及包含失败样例的代表性任务。
下一步试验
选择一个真实任务和现有替代方案，记录 commit、环境、输入、输出、耗时与失败行为；保留结果后再给出采用建议。