資料來源#
摘要#
Fiona Fung 對技術辯論的準則是:當代理式程式設計讓產出幾乎不花成本時,「在技術辯論中,程式碼勝出——建構很便宜,爭論很昂貴。」 當你能在安排白板會議所需的時間內產生三種真實實作,就不再爭論各種做法,而是開始比較它們。Claude Code 的相應規範是:製作原型並親自試用,而不是撰寫設計文件;減少深入的規劃文件,改以 PR 和原型進行討論。
產生三個 PR 的做法#
Fung 分享了一段親身經歷:剛開始使用 Claude Code 時,她和 Boris Cherny 討論重構做法。過去的直覺反應是:「我們去會議室用白板討論吧。」這次她改為:「多虧了 Claude,我產生了三個不同版本的 PR」——這讓技術辯論更有成效,因為她不只可以比較程式碼的實作方式,還能比較對呼叫端的影響。產出物(真實、可執行的 PR)承載的資訊比討論(白板上的抽象概念)更多,而現在製作它的成本很低。
以原型取代設計文件#
相同的成本變化也改寫了原型製作的方式。以前,原型製作會讓團隊分成兩派——一派認為它能快速取得回饋,另一派則認為這是走捷徑,最後卡在交付無法擴充的拋棄式程式碼。有了 Claude,第二種顧慮就沒那麼有力了:「原型製作是很好的起步方式,因為我們可以反覆迭代、從中學習,接著更快地把原型擴展到正式環境。」所以 Claude Code 的規範是:有個想法 → 製作原型 → 親自試用 → 再做決定。(參見 prototype:「用一次性的原型把設計具體化」的做法。)
減少什麼:設計文件#
團隊減少的是:「非常深入的規劃與設計文件。我們大多數的討論實際上都在 PR 或原型中進行。」這是 Verification as the New Bottleneck 帶來的後續影響——當工程產能不再稀缺,過去為了保護產能而存在的大量前期規劃,也就失去了理由。重構與架構整理過去常在「什麼時候才有時間做?」的預算角力中落敗,如今也不再是瓶頸。
必須兼顧的張力#
這項規範與知識庫中以規劃為先的概念形成良性的張力。Design Concept Grilling(Matt Pocock)和 Vertical Slice Tracer Bullets 主張,開始建構之前必須先對設計概念取得共識。兩者的調和方式是:「建構很便宜」並未取消設計思考,而是改變了設計思考發生的位置。你仍然需要品味與規格(Outsource Your Thinking, Not Your Understanding),但你是透過比較已建構的產出物來得出它們,而不是抽象地爭論。建構成本低,讓原型成為設計的媒介,而不是設計的替代品。(Karpathy 在 Vibe Coding vs. Agentic Engineering 中也取得相同平衡:規格仍由人類負責。)
延伸閱讀#
- Implementation Abundance Inverts Product Work — 同樣遵循「建構成本低,難題就會轉移」的邏輯,並將其延伸至整個產品流程(篩選 90 個平行建置版本)
- Fiona Fung —「建構很便宜,爭論很昂貴」
- Boris Cherny — 一起參與「產生三個 PR」重構討論的夥伴
- Verification as the New Bottleneck — 上游原因:產出成本低 → 為保護產能而規劃失去意義
- Design Concept Grilling — 良性的張力:先設計再建構,或先建構再決策(調和方式:原型本身就是設計媒介)
- Vertical Slice Tracer Bullets — tracer bullets 是同一種直覺的做法:「先建構一個精簡的真實版本來學習」
- Disposable Micro-Apps — Thariq Shihipar 製作的一次性 UI,遵循相同的「便宜的建構產出勝過抽象爭論」邏輯,並將它用於編輯計畫
- Outsource Your Thinking, Not Your Understanding — 建構很便宜,但仍由人提供品味與規格,評估三個 PR
- AI Native Product Cadence — 以原型取代文件,是精簡 PRD 節奏的一部分
- Prototype Over PRD — Dan Carey 將「建構產出勝過抽象爭論」的做法延伸至規格撰寫:跳過 PRD,從一場探討原因的對話出發,產生多種原型版本
尚待解答的問題#
- 什麼情況下「產生三個版本再比較」會變得浪費?決策的重要性達到什麼程度時,直接認真討論(或撰寫設計文件)仍比製作三種實作便宜?
- 如果設計討論都發生在 PR/原型中,未來的讀者要去哪裡找決策理由?「我們為什麼這樣選」的知識能否留存?還是也會遇上 Code as Source of Truth 的過時問題?部分已有答案:Where Does the Why Live?——答案是無法留存:埋在已合併 PR 中的討論,對未來讀者而言形同失聯,而且目前沒有任何候選位置能長期保存這些理由。尚未解決的是,部分補救方式(內容更豐富的計畫產出物、編譯後的知識庫)是否能在團隊規模下實際奏效。
衍生文章#
- The PRD-Replacement Spectrum at AI-Native Speed — 以建構來做決策是光譜中的中間位置;本頁提出的理由失聯問題,是光譜上第一項尚未解決的債務
- Where Does the Why Live? — 針對本頁的決策理由問題提供深入回答:在 PR 中討論會埋沒決策理由,而目前沒有任何候選位置能長期保存它
資料來源#
Cited by 17
- The PRD-Replacement Spectrum at AI-Native Speed×9
The orphaned rationale (job #3). If design lives in PRs and prototypes and the PRD is deleted after…
- Prototype Over PRD×5
Build to decide · Building Is Cheap Arguing Is Expensive (Fiona Fung) · Generate three real PRs and…
- Where Does the Why Live?×3
Design discussion gets buried in merged PRs — Building Is Cheap Arguing Is Expensive open question:…
- Open Questions Dashboard×2
Building Is Cheap Arguing Is Expensive: If design discussion lives in PRs/prototypes, where is the…
- Open Questions Backlog×2
Building Is Cheap Arguing Is Expensive: If design discussion lives in PRs/prototypes, where is the…
- Playbook Boundary Conditions: the Devil's-Advocate Substrate and the Prototype's Edge×2
Q1: Problem Solution Fit Discipline, Claude Character As Product, Harness Shrinkage As Models…
- Boris Cherny
Building Is Cheap Arguing Is Expensive — debated refactoring approaches with Fiona Fung by…
- Code as Source of Truth
Building Is Cheap Arguing Is Expensive — if code wins debates, the repo (not docs) is the source of…
- Design Concept Grilling
Building Is Cheap Arguing Is Expensive — productive tension: Fiona Fung's "generate three PRs and…
- Disposable Micro-Apps
Building Is Cheap Arguing Is Expensive — throwaway built artifacts as the unit of decision; cheap…
- Fiona Fung
Norms rewrote themselves — TDD lost its tax; refactoring stopped being a budget fight; design docs…
- Implementation Abundance Inverts Product Work
Building Is Cheap Arguing Is Expensive — the same "cheap building relocates the hard part" logic,…
- AI Coding Practice
Building Is Cheap Arguing Is Expensive — "In technical debate, code wins": generate three PRs vs…
- Outsource Your Thinking, Not Your Understanding
Building Is Cheap Arguing Is Expensive — generating PRs to settle a debate still requires…
- Verification as the New Bottleneck
Building Is Cheap Arguing Is Expensive — the upstream half: generation is cheap, so verification…
- Vertical Slice Tracer Bullets
Building Is Cheap Arguing Is Expensive — a tracer bullet is the "build a thin real thing to learn"…
- Vibe Coding vs. Agentic Engineering
Building Is Cheap Arguing Is Expensive — cheap generation is what lets prototypes settle technical…
Related articles
- Harness Shrinkage as Models Improve
Prompt scaffolding shrinks each model release; Cat Wu's pruning discipline; Boris Cherny "100 lines of code a year from…
- HTML as the New Markdown
Thariq Shihipar's thesis: as models improve, thousand-line markdown plans overwhelm the *human*; HTML artifacts (visual…
- Prototype Over PRD
Dan Carey's prototype-replaces-PRD method: record a why-not-what conversation, transcribe it, hand the transcript to Cl…
- Spec-Driven Development as the New Waterfall
Robert C. Martin reads the 2026 spec-driven-development movement as the 1970s big-design-up-front temptation returning…
- Verification as the New Bottleneck
Fiona Fung: coding is no longer the bottleneck — verification, review, maintenance are; shift-left; TDD loses its tax;…
