Ci | AI 驅動開發 (@ci.fullstack) on Threads

This page is public and can appear in search results. The audience and topic lines below are AI-inferred and may be wrong.
Claim this page → · Correct it, take it out of search, or remove it →

Ci / AI 驅動開發 is a creator on Threads in the 3K–4K follower range, publishing for Full-stack developers and AI engineering practitioners building AI-driven workflows, especially those experimenting with AI agents and automated development pipelines. Profile last checked 2026-06-28.

Observed facts (from the public profile):

Profile bio

全端工程師 ｜ AI Agent 實戰 iTHome 鐵人賽佳作｜JSDC・HWDC 講者 AI Agent / SDD / AI Development Workflow 實戰筆記 • AI 流程導入 • 合作邀約 👇 📧 contact removed

What this creator posts about, and who reads it (AI-inferred)

Recurring topics: AI Agent practical use and development process, AI's role positioning in DevOps, Human-in-the-loop production environment control, Transitioning from manual operations to AI supervision

Audience: Full-stack developers and AI engineering practitioners building AI-driven workflows, especially those experimenting with AI agents and automated development pipelines

Provenance: inferred by AI from public content, not stated by the creator — confidence 0.40 · read from 4 recent posts · updated 20 days ago.

Audience read from this creator’s own recent posts, not from platform-declared categories. It is our reading, and it can be wrong.

Recent content samples (what the inference above was drawn from)

每天發 AI 相關內容，追蹤剛破 1,000，好像該自我介紹一下 我是 Ci，寫了十幾年程式，從定義需求到上線都自己跑過，也帶過團隊 從去年開始出現在一些技術研討會，今年會繼續出現 去年鐵人賽連寫了兩個 AI 開發系列，其中一個拿到佛系分享佳作 其中一篇 Claude Code 教學，沒特別推廣，單篇累積近十萬瀏覽 後來投稿上了 Hello World Dev Conference 那時候我才意識到： 大家不是不想用…

我常常叫 Claude Code 去找檔案 跑測試 查一堆東西 然後畫面開始被 Bash、Read、IN、OUT 塞滿 我知道它很忙 但老實說我只想知道兩件事 還在跑嗎 有沒有出錯 Claude Code 今天加了 Focus view 我拿自己的每日情報管線實際跑一輪 原本塞滿畫面的過程 收起來後只剩一行 「9 tool calls · 1 failed」 它沒有讓 Claude 變快 但監工真的舒服很多 下面放怎麼開…

我真的把 Microsoft Skill Recorder 裝起來跑了 錄了 31 秒 給它看我怎麼把 GitHub Release 整理成一張研究素材卡 最後它真的吐出一份 2.8 KB 的 SKILL.md 結果第一版就看錯了 它把「建立一張新卡」 看成「閱讀既有卡片」 然後很有自信地往下生了 5 個 看起來合理 但其實走錯方向的步驟 下面放完整實測 也拆一下它到底怎麼把操作變成 Skill

OpenAI 的工程師面試 有人遇到一輪很新的 Agentic Coding beta 不是叫人關掉 AI 而是丟一

See the original post on Threads

Where this creator sits among comparable accounts

Compared with the 316 accounts in the same group (threads · nano · software):

This is a position, not a verdict. A percentile says where this account falls among comparable accounts on signals we can measure — it does not say this creator is a better fit for your campaign. We ran a blind benchmark and measured no reliable advantage in selection quality, and do not claim one.

Koinon Link indexes Threads creators in Software with grade, authenticity and contactability broken down — see the Threads × Software breakdown, or the Creator Index Report for the whole index.

Other Software creators on Threads

• Kanan Rahimov (@codervlogger) — ClawCloud and OpenClaw technical updates
• Lya / Software Engineer & AI (@codewithlya) — Programming
• Make Content Great Again (@contentplayer36) — Startup common tool stacks
• Daily AI Only (@dailyaionly) — Autonomous AI agents
• Daria Kut (@daria.nemirovskaya) — app development journey
• 𝑰𝒓𝒚𝒏𝒂 𝑩𝒖𝒄𝒉𝒂𝒌 / Brand Designer (@designbuchak) — Typography
• Umair (@developedbyumair) — AI agent development
• Data Science With Dennis / contact removed (@dswithdennis) — data science career pivots

Creators next to this one by follower tier in the same slice. Each link opens that creator’s public profile — what they post about and who reads it, with no contact details.

This page lists public profile information only. It carries no contact details and no authenticity score. If you are Ci / AI 驅動開發 and want this page removed, request removal.

Machine-readable representations

Structured twins of this page for AI and agents — every inferred field carries its source, confidence and freshness.

• /kol/threads/ci.fullstack.json
• /kol/threads/ci.fullstack.md

AI retrieval activity

What AI systems have actually done with this page. The two kinds are counted separately: being indexed is not the same as being used.