資料來源#
摘要#
在 Anthropic Labs 內部帶領產品的產品經理。他將 Claude Design 這項產品從構想一路推到上線（約三人、約十週）。他是 2026 年 5 月那場研討會演講「Designing with Claude: From prompt to production」的講者，這場演講是本 wiki 對「一場 Labs 賭注實際上是如何被打造出來」最詳盡的記述。身為一位「寫 [PRD] 寫了將近二十年」的 PM，Carey 如今改用原型來取而代之。
重要主張與立場#
- 原型勝過 PRD。「這對我來說實際上已經取代了 PRD……現在我只做原型。」談的是為什麼，而不是做什麼；錄音並轉錄；把逐字稿交給 Claude；請它生出幾種變化（參見 Prototype Over PRD）。
- 優化整個迴圈。「你為什麼要做這些 Claude 本來就能替你做的工作？你為什麼還沒打造自己的工具？」每一次優化都會回報 ×（每個專案 50–100 次迭代）（參見 Compounding Loop Optimization）。
- 去做那個差一點就能用的東西的原型。「你不會想去做那些已經能用的東西……下一個模型也許就直接修好你靠工程解決不了的問題。我們在 Opus 4.7 推出時就把 [Claude Design 的問題] 修好了。模型發布就像漲潮，會把所有船一起抬高」（參見 Build for the Next Model）。
- 抬高地板，而不是天花板。 一個工具應該為每個人提升技藝，而不只是替進階使用者增加控制項——這是在一週內把 Claude Design 的進階控制項砍掉所學到的教訓。
- 用夠小的循環迭代，好讓你快速發現自己錯了。「重點不一定是你能不能永遠跑得快；而是你能不能永遠用一個夠小的循環來迭代，好讓你非常快速地發現自己什麼時候錯了。」
明天可以嘗試的三件事（他的結語）#
- 跳過 PRD——把為什麼講過一遍、轉錄下來，請 Claude 生出三種原型變化。
- 在一個下午內打造你一直在等的內部工具——「搔自己的癢處」。
- 在 24 小時內走完一個真實的功能需求——這三件中最難的一件，因為它會暴露出你現有部署／審查流程中的每一個路障。
「我不會想一次做完這三件——一層一層疊上去。」
相關連結#
- Anthropic Labs — 在其中帶領產品
- Claude Design — 他領導的產品
- Anthropic — 雇主
- Prototype Over PRD — 他的招牌方法
- Compounding Loop Optimization — 他的運作紀律
- Build for the Next Model — 他的回顧式賭注，已被 Opus 4.7 驗證
- Cat Wu / Boris Cherny / Fiona Fung — 同為 Anthropic 產品／工程領導者，他們對 AI 原生節奏的記述，從 Labs 的角度與他的演講互相印證
資料來源#
- Designing with Claude: From prompt to production — 「Designing with Claude: From prompt to production」，YouTube（Claude 頻道），2026 年 5 月
Cited by 17
- AI Native Product Cadence
Cat Wu's 6mo→1mo→1day cadence at Anthropic: research-preview branding, mission-as-tiebreaker, evergreen launch room, li…
- Anthropic
AI safety company / vendor of Claude; mission-as-tiebreaker culture; ~30–40 PMs across teams; Mike Krieger leads Labs r…
- Anthropic Labs
Anthropic's internal incubator — a 'bet factory' of ~a dozen tiny teams exploring the model frontier with lean-startup…
- Build for the Next Model
Prototype the thing that almost works, not the thing that already works: bet that the next concrete model release (not…
- Building Is Cheap, Arguing Is Expensive
"In technical debate, code wins": generate three PRs vs whiteboard; prototype over design doc; reduce design docs
- Claude Design
Anthropic Labs product (research preview, ~April 2026) for collaborating with Claude on polished visual artifacts — des…
- Claude Opus 4.7
GA frontier model from Anthropic; direct upgrade to 4.6 at same price; literal instruction following, 1.0–1.35× tokeniz…
- Compounding Loop Optimization
Dan Carey's discipline of instrumenting and automating every recurring step of the build loop — because when internal t…
- Dogfooding as Product Discipline
Product sense is built by relentless first-hand use ("ant food"); Mr. Peanut catch; cross-source (Cat Wu vibe-checks, G…
- Engineer PM Convergence
Generalists across disciplines; product taste as bottleneck skill; Anthropic Claude Code team as case study; "just do t…
- 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…
- Entities — People, Orgs, Tools & Projects
Map of Content for all 32 entity pages. See Home for concept domains.
- The PRD-Replacement Spectrum at AI-Native Speed
Four positions (grill-then-PRD → lighter-PRD → build-to-decide → prototype-is-spec) are one spectrum once you decompose…
- Product Velocity as Moat
Shipping speed as differentiator + trust signal ("you'll scale with us"); a treadmill that must convert into durable lo…
- Prototype Over PRD
Dan Carey's prototype-replaces-PRD method: record a why-not-what conversation, transcribe it, hand the transcript to Cl…
- Where Does the Why Live?
Rationale (the 'why') is well-homed at authoring time — it's the recorded why-not-what conversation and the grilling se…
Related articles
- Claude Code
Anthropic's agentic coding product; created by Boris Cherny late 2024; TypeScript/React; CLI/desktop/web/mobile/IDE sur…
- Claude Design
Anthropic Labs product (research preview, ~April 2026) for collaborating with Claude on polished visual artifacts — des…
- AI Native Product Cadence
Cat Wu's 6mo→1mo→1day cadence at Anthropic: research-preview branding, mission-as-tiebreaker, evergreen launch room, li…
- Cat Wu
Head of Product for Claude Code and Cowork at Anthropic; primary articulator of AI-native product cadence and engineer-…
- Prototype Over PRD
Dan Carey's prototype-replaces-PRD method: record a why-not-what conversation, transcribe it, hand the transcript to Cl…