// AI × DATA × DELIVERY × OPERATING SYSTEM
把业务需求，变成可持续运行的 AI 系统。 Turning business needs into AI systems that actually run.
▸ ▌
我有 7 年数据运营与项目交付经验（PMP 认证），核心优势是把业务需求转化为可落地的解决方案：从数据采集、分析到自动化系统搭建，兼具软件实施与客户交付背景，能独立跑通「需求 → 方案 → 交付」全流程。 I have 7 years of experience in data operations and project delivery (PMP certified). My core strength is turning business needs into working solutions — from data collection and analysis to building automated systems — backed by a software implementation and client delivery background, running the full loop from requirement to shipped result.
我熟练运用大模型（GPT / Claude / DeepSeek）、Codex 与 Python 构建 AI 应用与自动化管线：行业情报采集分析、每日资讯聚合摘要、审计数据清洗、报表服务产品化、内容生产与复盘 Agent……把 AI 能力转化为实际业务成果，而不止于「用工具提效」。 I build AI applications and automation pipelines with GPT / Claude / DeepSeek, Codex and Python: industry intelligence, daily briefings, audit data cleaning, reporting productization, content production and review agents — converting AI capability into business outcomes, not just "using AI tools to work faster."
我正在搭建自己的个人 AI 操作系统：用 AI 协助项目开发、内容生产、知识资产沉淀、质量审计和每周复盘，让能力不是停留在一次性输出，而是进入可维护的工作流。 I am building my own personal AI operating system: using AI to support product development, content production, knowledge assets, quality checks and weekly reviews, so capability becomes a maintainable workflow instead of a one-off output.
* 照片占位，之后替换 * Photo placeholder
2018.06 — 至今Present
主导公司数据支持全流程与经营分析：搭建覆盖人力、资产、产能、订单的数据监控体系，为近 200 人团队提供实时预警；引入大模型 + Python，把数据清洗、报表生成、分析报告撰写等重复流程自动化；负责部门级项目全流程跟进与跨部门协调；从 0 到 1 运营企业抖音官方账号（50+ 条作品，出镜主持与视频制作）。 Own end-to-end data operations and business analysis: built a monitoring system covering HR, assets, capacity and orders with real-time alerts for a ~200-person team; introduced LLMs + Python to automate data cleaning, report generation and analysis writing; run department-level projects with cross-functional coordination; grew the company's official Douyin account from zero (50+ videos as host, scriptwriter and editor).
2016.12 — 2018.05
早期「前向部署」式交付经验：直接对接客户、把产品落地到客户现场——软件定制与实施安装、SQL 数据导入、表结构设计与存储过程编写，以及客户培训与系统维护。 Early forward-deployed delivery experience — landing the product on-site with clients: software customization and implementation, SQL data imports, schema design and stored procedures, plus training and maintenance.
2015.12 — 2016.12
为政府部门及企业提供舆情监测服务：构建关键词体系、分析海量舆情数据，输出月度报告与突发事件专题报告。 Media monitoring for government and enterprise clients: keyword systems, large-scale sentiment analysis, monthly reports and incident-response briefs.
2012.09 — 2016.07
院学生会组织部副部长，负责学生事务文档管理及活动组织。 Deputy head of the student union's organization department — student affairs documentation and event organization.
这些项目不是一次性 demo，而是围绕真实工作流形成的系统：有输入、处理、输出、质量审计、发布或交付闭环。 These are not one-off demos. They are systems around real workflows: input, processing, output, quality checks, publishing or delivery.
多源自动采集（公开 API + 动态页面渲染）、反爬应对、自动去重与增量入库，累计处理 1500+ 条行业数据；用大模型对非结构化文本做结构化抽取与分类，自动生成趋势分析报告。 Multi-source collection (public APIs + rendered pages) with anti-bot handling, dedup and incremental storage — 1500+ records processed. LLM-powered structured extraction and classification, with auto-generated trend reports.
定时生成 AI 早报与金融商业晚报，再转成快讯视频、播客和发布文案；新增信源审计规则，检查官方 / 一手源覆盖、来源域名集中度和中国官方 / 交易所源，避免内容来源单调。 Scheduled AI morning and finance evening briefings, converted into short videos, podcasts and publish-ready copy; source-audit rules check first-party coverage, domain concentration and China official/exchange sources.
学习 + 减压二合一的移动优先网页应用：从 PRD、产品原则、呼吸引导、知识卡片、种星花园、重温机制到 Web Audio 与 localStorage，完整走了一次 AI 协作产品开发流程。 A mobile-first learning and decompression web app: PRD, product principles, breathing guide, knowledge cards, star planting, review, Web Audio and localStorage — a full AI-collaborative product development loop.
把原本每周需专人耗时一天的数据导出与批量处理流程完全自动化：从需求对接到全流程跑通约 2 天完成交付，重复性工作从「每周固定一天」变为自动执行，并预留监察预警等扩展能力。 Fully automated a weekly routine that used to cost one person-day per week — delivered end-to-end in about two days from first requirement talk, with monitoring and alerting hooks reserved for extension.
运用大模型对审计所需数据进行清洗、核对与审核，自动生成报表与凭证（如全年逐月单据），在保证合规与准确的前提下显著提升处理效率。 LLM-assisted cleaning, cross-checking and review of audit data, auto-generating statements and vouchers (a full year of monthly documents) — much faster while staying compliant and accurate.
把本地自动化报告工具（每日自动推送数据报告）产品化上线：搭建在线报表、支持团队成员自助取数——完成从「本地脚本」到「线上自助数据服务」的演进，把一次性工具沉淀为团队可持续使用的服务。 Took a local auto-reporting tool online as a product: web-based reports with team self-service access — evolving a one-off script into a sustained data service the whole team relies on.
围绕 PMX 报价、需求可行性报告、周期周报导出等内部流程，构建 API 拉取、Excel 解析、LLM 分析缓存、PDF 生成和本地看板。适合做脱敏案例，展示业务理解、数据处理和交付闭环。 Internal automation around PMX quotations, feasibility reports and recurring exports: API ingestion, Excel parsing, cached LLM analysis, PDF generation and local dashboards. A sanitized case study for business understanding and delivery.
输入一篇论文，自动产出竖屏科普视频：Claude 写脚本、edge-tts 配音、Playwright 渲染，端到端无人工。这也是我第一个开源项目——代码可直接查看。 Feed in a paper, get a vertical explainer video — Claude scripts it, edge-tts voices it, Playwright renders it, fully automated. My first open-source project — code is public.
把一批文档用大模型按自定义 schema 批量结构化：结构化输出保证合法 JSON、线程池并发、导出 CSV。换个配置就能变工单归类 / 情报打标 / 简历初筛。自带 mock 模式，不用 API key 也能跑通。 Batch-tag a folder of documents with an LLM — schema-driven structured output (guaranteed JSON), thread-pool concurrency, CSV export. Swap the schema to repurpose it; includes a no-API-key mock mode.
你正在看的这个网站，从设计、编码到部署全程与 AI 结对完成；现在它也是我的个人 AI 操作系统前台，持续承接项目、内容和知识资产。 This site was designed, coded and deployed in pair with AI; it now works as the front desk of my personal AI operating system, carrying projects, content and knowledge assets.
把模糊目标拆成 PRD、Prompt、验收清单和可执行步骤。Turn vague goals into PRDs, prompts, acceptance checks and executable steps.
用 GPT 做推演、方案和复盘，用 Codex 把页面、脚本、Agent 和文档落地。Use GPT for reasoning, planning and reviews; use Codex to ship pages, scripts, agents and docs.
把信源审计、格式检查、运行记录和每周复盘沉淀进 Git 与作品集。Turn source audits, format checks, run records and weekly reviews into Git-backed portfolio assets.
想聊聊合作或工作机会？欢迎随时联系。 Open to opportunities and collaborations — feel free to reach out.
karlyma102@gmail.com📍 广东中山📍 Zhongshan, Guangdong, China