poteto@poteto

要怎麼更信任你的 agent 做的東西？把這篇貼文/連結複製給你的 @bot 或 agent！ 1. 程式碼庫改進：這其實就是好的軟體工程——更好的架構、更強的型別和不變量、清楚的邊界。agent 超愛照抄現有的東西、走最短路徑，所以要讓簡單的做法就是正確的做法。用程式碼從根本消滅問題，你就再也不用煩惱了。 2. 靜態分析：lint 規則、測試、CI、驗證（例如 TLA+）。都是提前抓問題、非常省 token 的方法。 3. 文字說明：註解、規則、AGENTS.md、skills——所有無法強制執行、需要 agent 自己判斷的東西。盡量少用，但一定要用 /create-verification-skill。 4. 人工審查：最難規模化。照 agent 提交程式碼的速度，幾乎不可能把每個 PR 都仔細看過，所以把力氣花在槓桿最大的地方：設計一個讓 agent 預設就做對的環境。 這就形成一個倒金字塔：大部分心力放在頂端，底部最少。程式碼庫改進是確定性的，所以更省 token，也讓你晚上睡得更安穩。 安裝 pstack，然後建立一個新的 Project： 1. 翻一遍我在 slack/聊天訊息和 code review 留言裡對 PR、程式碼、架構給過的回饋 2. 對我過去的對話紀錄用 /recall，學習我是怎麼引導 agent 的 3. /poteto-mode 對過去的 commit 用 /correct 和 /architect，找出 agent 最常踩的坑，然後提出一個方案，把我負責的程式碼重構得對 agent 更友善。遇到開放問題就用做原型來回答，不要丟回給我，並且用真實數據支撐這個方案。 4. 開始之前，先用 /sharpen + /in-your-own-words 跟我確認這段提示詞

how do you trust your agents' work more? copy this post/link and give it to your @bot or agent! 1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again. 2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time. 3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill. 4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default. this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night. install https://github.com/cursor/plugins/tree/main/pstack and create a new Project: 1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture 2. use /recall on my past transcripts to learn how i steer agents 3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data. 4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me