Tong Wu · 吴桐. Six roles across four countries — supply chain, process excellence, EU certification, teaching assistant, research, AI automation. The throughline isn't the industry; it's the speed at which I absorb a new system and ship in it. Every step stretched the next. 吴桐 · Tong Wu. 八年、四国、六个角色 —— 供应链、流程卓越、欧盟认证、助教、研究、AI 自动化。串起这一切的不是行业，是「进入新系统、立刻交付」的速度。每一段经历都为下一段拉伸了能力上限。
Three live products on npm under Novada Labs — the agent stack I needed when I was running ops at Amazon and the tooling didn't exist yet. 三个在 npm 上活跃维护的产品，在 Novada Labs 旗下 —— 当年在亚马逊跑运营时，我需要这些工具但市面上没有，于是自己写。
High-precision MCP search server for autonomous agents. Multi-source fusion, structured output, <200ms p50. 为自主智能体打造的高精度 MCP 搜索服务。多源融合、结构化输出、p50 延迟 <200ms。
Persistent memory layer for multi-agent stacks. Correction-based calibration so mistakes from one run inform the next. 多智能体的持久化记忆层。基于纠错的校准机制，让一次错误能改进下一次。
Quantitative framework I designed to score agent autonomy. Tests planning, recovery, and budget adherence under failure. 我设计的智能体自主性量化框架。在失败场景下测试规划、恢复和预算控制。
Operations at scale → automation → agent infrastructure. Each role was a deliberate step toward building the systems I now ship. 大规模运营 → 自动化 → 智能体基础设施。每一份工作都是有意识地朝着「我现在做的事」靠近。
Academic papers, custom code scripts, certifications, and professional references. PDFs open in a new tab. Code opens in an interactive viewer. 学术论文、自研脚本、证书与职业推荐信。PDF 在新标签页打开，代码在交互式查看器中打开。
Automation scripts integrating AI models — Tampermonkey for Amazon internal systems and a LangChain RAG PDF reader. 集成 AI 模型的自动化脚本 —— 亚马逊内部系统的 Tampermonkey 工具，以及一个 LangChain RAG PDF 阅读器。
Economics × technology intersections: UBI in the AI era and socio-economic impacts of the GPT ecosystem. 经济学 × 技术交叉研究：AI 时代的 UBI 与 GPT 生态的社会经济影响。
Six Sigma, Data Analytics, Python Automation, Machine Learning, and Business Analysis credentials. 六西格玛、数据分析、Python 自动化、机器学习、商业分析等专业证书。
Three concentric circles: AI & agent engineering at the core, strategic ops & supply chain as the moat, data intelligence as the connective tissue. 三个同心圆：核心是 AI 与智能体工程，护城河是 战略运营与供应链，连接组织的是 数据智能。
I read the I Ching the way some people read systems design — both teach you to see structure under noise. 我读《易经》，方式像别人读系统设计文档 —— 都是在训练「看穿表象、识别结构」的能力。
A 3,000-year-old binary state machine for decision-making under uncertainty. Surprisingly close to how a well-designed FSM agent reasons about the world. 三千年前的二进制状态机，用于不确定性下的决策。和一个设计良好的 FSM 智能体推理世界的方式惊人地接近。