🔶 94 位互联网知名工程师如何使用编程 Agent

OpenClaw，前 PSPDFKit 员工

Agent：OpenClaw（网页端）、Codex（应用端）。模型：GPT-6.1 Sol。

审查：Codex 审查每一次提交。

值得借鉴：$autoreview，在每次提交前运行。

Datasette、Django 联合创建者

Agent：Codex（应用端）、Claude Code（网页端）。模型：GPT-6 Sol、Claude Opus 5.5。

审查：跨模型审查：Claude 检查 GPT，GPT 检查 Claude。

值得借鉴：Showboat，让 Agent 演示自己的工作成果。

Claude Code 创建者

Agent：Claude Code（应用端）、Claude Tag。模型：Fable 5.1。

审查：只阅读关键代码的 diff。

值得借鉴：/go，测试、运行 /simplify、创建 PR。

nanochat 创建者，“vibe coding”一词的提出者

Agent：Claude Code（命令行）、Codex。模型：Claude Fable 5。

审查：在 IDE 中密切盯着 Agent。

值得借鉴：autoresearch，让 Agent 在夜间开展研究。

Ghostty 创建者、HashiCorp 联合创始人

Agent：Claude app（应用端）、Codex app（应用端）。模型：Claude Fable、GPT-6 Astra。

审查：人工审查每一行；Agent 负责验证，所有文字内容由他撰写。

值得借鉴：Harness engineering，在 Agent 每次犯错后改进运行框架。

Ruby on Rails、Omarchy 创建者

Agent：Codex（命令行）、Claude Code（命令行）、OpenCode（命令行）。模型：GPT-6.1 Sol、Claude Opus 5.5。

审查：先由第二个模型审查，然后他再阅读 diff。

值得借鉴：“Review this with claude”，让 Codex 发起对抗式审查。

Flask 创建者、Earendil 创始人

Agent：Pi（命令行）、Codex。模型：Sol、Fable。

审查：过程中持续引导，Agent 表示完成后再审查。

值得借鉴：/answer，用它代替计划模式。

T3 Stack、T3 Chat、T3 Code

Agent：Claude Code（应用端）、Codex（应用端）。模型：Opus 5.5、Muse Wonder。

审查：Opus 请 Wonder 审查代码；Agent 有把握时自行合并。

值得借鉴：T3 Code，他为各个 Agent 打造的 GUI。

Redis 创建者、DwarfStar（ds4）

Agent：Codex（命令行）、Claude Code（命令行）、ds4-agent（命令行）。模型：GPT-6 Astra / GPT-6.1 Sol、Fable。

审查：仍然审查 Redis 代码，但认为这大多没有意义。

值得借鉴：QA_BEFORE_RELEASES.md，每次发布都由 Agent 执行一轮质量检查。

Harpoon，直播使用 Vim

Agent：Cursor（IDE）、99（IDE）。模型：Grok 4.6。

值得借鉴：Field guide，让 Agent 写下自己学到的经验。

Gas Town、Beads、Vibe Coding

Agent：Claude Code（命令行）、Codex。模型：Claude Opus 5.5、Claude Fable 5.1。

审查：Fable 审查 Opus 的每一项改动；他本人不读代码。

值得借鉴：Seats，18 个长期运行的 Fable 工作 Agent。

Photo AI、Nomads.com

Agent：Claude Code（命令行）。模型：Claude Opus 5.5、Claude Fable 5.1。

审查：一步步推进，对 Agent 严格把控。

值得借鉴：tm，为每个网站创建一个 tmux 会话。

pi coding agent、libGDX

Agent：Pi（命令行）。模型：GPT-5.5。

审查：将每日产出限制在自己能够审查的范围内。

值得借鉴：每日代码上限，根据自己的审查能力设定。

Amp 联合创始人、解释器书籍作者

Agent：Amp（网页端）。模型：Claude Opus 5.5、GPT-6 Astra。

审查：抽查代码并审查架构，而非逐行阅读。

值得借鉴：“无可辩驳的证据”，用视频证明成果，而不是逐行阅读代码。

Superpowers、Keyboardio、K-9 Mail

Agent：Claude Code（命令行）、Evener、Muse。模型：Claude Opus、Claude Haiku。

审查：通过 Agent 会话进行对抗式审查。

值得借鉴：/par，让审查者相互竞争，关注 5 个要点。

2389.ai CEO、奥巴马 2012 年竞选活动 CTO

Agent：Claude Code（命令行）、Codex（应用端）。模型：Claude Fable 5.1、GPT-6 Astra。

审查：每项改动都经过一轮“全新视角”审查。

值得借鉴：“fresh eyes” review，让子 Agent 重新阅读代码。

TDD、极限编程、JUnit

Agent：Claude Code（命令行）、Codex（命令行）。模型：Gemini。

审查：独自审查，但更希望结对工作。

值得借鉴：TCR skill，测试失败时回滚代码。

Compound Engineering、Cora

Agent：Cursor、Claude Code（命令行）、Codex。模型：Claude Opus 5.5、Claude Sonnet 5.5。

审查：并行使用审查 Agent，不逐行阅读。

值得借鉴：/ce-compound，把每次修复转化为一条经验。

Total TypeScript，前 Vercel 员工

Agent：Claude Code（命令行）。模型：Claude Opus 5.5、Claude Opus 5。

审查：根据合并风险进行审查，使用双维度的 /code-review。

值得借鉴：/grill-me，在每次改动前使用。

Context、uniprof、Sentry AI 负责人

Agent：Claude Code（命令行）、Codex。模型：Claude Opus 5.5、GPT-5。

审查：审查计划和提示词，而不是一万行的 diff。

值得借鉴：Claudescope，在每个 PR 中附上对话记录链接。

Anthropic Claude Code 团队，前 Chrome 团队成员

Agent：Claude Code、Codex。模型：Fable。

审查：只对核心路径进行仔细的人工审查。

值得借鉴：/loop PR triage，每天对 Agent Skills 的 PR 进行分类处理。

Ralph loop 创建者

Agent：OpenCode（命令行）、Cursor（网页端）、Loom。模型：GPT-6.1 Sol、GLM / Kimi。

审查：未经人工审查即交付；只在高风险改动时停下来审查。

值得借鉴：The Ralph loop，让 Agent 在 bash while 循环中运行。

Amp 和 Sourcegraph 联合创始人

Agent：Amp（网页端）。模型：Amp Dial：medium。

审查：Agent 先审查，他再扫视 diff，寻找危险信号。

值得借鉴：“I'm feeling Pucky”按钮，他们有一半的工作由这个按钮启动。

OpenCode 联合创始人、SST

Agent：OpenCode。模型：Astra、Fable。

审查：通过子 Agent 请更聪明的模型审查。

值得借鉴：语音提示（Hex），用语音代替打字。

OpenAI Codex 团队，前 Cline 团队成员

Agent：Codex（应用端）。模型：GPT-6 Astra、GPT-5.3-Codex-Spark。

值得借鉴：“Chief of staff”线程，由它创建每个项目的线程。

Tailwind CSS、Refactoring UI

Agent：Amp（网页端）、Codex（应用端）、Claude Code（网页端）。模型：Claude Sonnet 4.5。

值得借鉴：所有繁琐的开源任务，都交给云端 Claude Code。

Vitest、Slidev、UnoCSS、VueUse

Agent：Claude Code、Cursor（IDE）。模型：Claude Sonnet 5.5、Claude Opus 5。

审查：关注结果：用 Storybook 查看 Agent 开发的 UI，每个 PR 都有 pulls.review 摘要，最后再看 diff。

值得借鉴：antfubot，让 Agent 以机器人的身份提交 PR。

Ladybird 浏览器、SerenityOS

Agent：Claude Code、Codex。模型：前沿模型。

审查：由不同模型进行多轮对抗式审查。

值得借鉴：Welfare checks，检查分布在 4 台机器上的工作 Agent 的状态。

DTrace、Oxide 联合创始人兼 CTO

Agent：Claude Code（命令行）、ChatGPT。模型：Claude Opus 4.8。

审查：先自行审查：负责的工程师审查 LLM 代码之前，其他人不得审查。

值得借鉴：This Old Repo，复活一款 20 世纪 90 年代的游戏。

Thoughtworks、harness engineering

Agent：Cursor（IDE）、Claude Code、Pi（命令行）。模型：Claude Sonnet、Claude Opus 4.8。

审查：按风险分级：根据概率、影响和可检测性决定阅读多少代码；传感器指出需要关注的位置。

值得借鉴：sensors check，一个供 Agent 轮询的边车组件。

GitHub Copilot 团队成员

Agent：GitHub Copilot（应用端）、Claude Code（网页端）。模型：Luna Max、Claude Opus 5.5。

审查：由另一模型家族进行橡皮鸭式审查；他本人已不再阅读代码。

值得借鉴：每个项目一个主 Agent，他只需提交 issue。

ripgrep、Rust regex、Jiff

Agent：Codex（命令行）。模型：GPT-5.6 Sol。

审查：标记自己用 LLM 编写的 PR，要求仔细审查，然后手动简化；Codex 审查也能发现 bug。

值得借鉴：“I wrote this PR with an LLM”，以此标记需要仔细审查的 PR。

Segment 联合创始人，前 Codex 团队成员

Agent：Codex（命令行）、Claude Code（命令行）。模型：Fable 5、GPT-5.6 Sol。

审查：抽查架构；Cursor Bugbot 和 Codex 审查每个 PR。

值得借鉴：/pr-pass，循环运行，直到 CI 和机器人检查通过。

Anthropic Claude Code 产品团队

Agent：Claude Code（应用端）、Claude Tag。模型：Claude Opus 5.5、Claude Fable 5.1。

审查：Claude 代码审查负责外围部分；代码负责人审查核心部分。

值得借鉴：为每个模型重新配置，每次新模型发布时重置配置。

《AI Engineering》作者

Agent：Codex、Claude Code。模型：Claude Fable。

审查：由第二个 Agent 审查计划；UI 工作在 PR 中附带截图作为证据。

值得借鉴：跨提供商运行器，让 Codex 和 Claude 相互启动。

Phoenix、Phoenix.new 创建者

Agent：Claude Code。模型：Claude。

审查：规则文件列明在宣称修复完成前必须运行的测试。

值得借鉴：notify msg，写在 CLAUDE.md 中，而不是作为 hook。

exe.dev、Tailscale 联合创始人

Agent：Shelley（网页端）。模型：OpenAI 模型。

审查：Agent 代码进入重要系统之前先阅读，diff 由 meat 精简。

值得借鉴：meat，将 diff 精简至重要部分。

ChatPRD 创始人、《How I AI》主持人

Agent：Codex（应用端）、Claude Code、Cursor（网页端）。模型：GPT-6 Astra、Claude Opus 5.5。

审查：跨模型审查：Opus 5.5 审查 GPT 的 PR，反之亦然；PR 也会经过人工审查。

值得借鉴：LGTM，PR 关闭助手，一个帮她清理 PR 队列的机器人。

danluu.com 文章作者，前 Centaur 员工

Agent：Codex（命令行）。模型：GPT-5.6 Sol。

审查：用大量随机化测试代替人工审查。

值得借鉴：具名角色审查小组，其中包括持反对意见的角色。

“How to Fix Your Context”、Plumb

Agent：Claude Code。模型：Claude Fable、GLM 5.2。

审查：不阅读 diff，而是逐一审查 Plumb 从每次提交中提取的决策。

值得借鉴：Plumb，在提交时审查决策。

HumanLayer CEO、《12-Factor Agents》

Agent：HumanLayer（IDE）、Codex、Claude Code。模型：GPT-5.6 Sol、Claude Fable。

审查：仍然阅读代码，每次审查一个 1,000 至 3,000 行的 PR。

值得借鉴：/show-me，使用图表，而不是大段文字。

Every CEO

Agent：Codex（应用端）、Claude Code。模型：GPT-6 Sol、Claude Fable。

审查：采用 vibe coding；不阅读代码库。

值得借鉴：“Want me to compound?”，每轮清理后都会询问是否沉淀经验。

OpenAI Codex 产品负责人

Agent：Codex（应用端）。模型：Codex 默认模型。

审查：阅读计划；Codex 审查几乎每个 PR。

值得借鉴：“Using a subagent in parallel, do X”，从一个始终运行的线程中发出指令。

Meta PyTorch 团队、ghstack

Agent：Claude Code（命令行）、Codex。模型：Claude Opus 5.5、Claude Fable 5。

审查：阅读每一行，通过提问和编辑进行引导。

值得借鉴：sl follow / sl adopt，重新整理并行 Agent 的提交栈。

《Game Engine Black Books》

Agent：Claude Code（IDE）、Antigravity（IDE）。模型：未注明。

审查：阅读所有代码；先由 LLM 提出批评意见。

值得借鉴：“Reload agent.md”，代码质量下降时重新加载。

Go 密码学、age、mkcert

Agent：Shelley（exe.dev）（网页端）、Claude Code（命令行）。模型：GPT-6 Astra、Claude Opus 4.8。

审查：在任何人工审查之前先进行 LLM 审查。

值得借鉴：filippo-agent，Agent 自己的 GitHub 账号。

YC CEO、gstack 创建者

Agent：Claude Code（应用端）、Codex（命令行）。模型：Claude Fable 5.1。

审查：每个分支都经过 CEO、Codex、开发者体验和工程审查。

值得借鉴：/plan-ceo-review，寻找“10 星级”产品。

Ansible、Raspberry Pi YouTube 频道

Agent：Claude（网页端）。模型：Claude Opus 5.5、Claude Fable 5.1。

审查：分阶段审查，就像技术负责人带领初级工程师。

值得借鉴：AI Disclosure，在 README 中注明具体模型。

Malleable software、Notion

Agent：Claude Code、Cursor（IDE）、Codex CLI（命令行）。模型：Claude Opus 5、Claude Fable 5。

审查：先阅读解释说明，再看完整 diff；代码交付前必须通过 5 道题的测验。

值得借鉴：/explain-diff，交付前附带一项测验。

tinygrad、comma.ai

Agent：OpenCode。模型：Kimi、Claude Opus。

审查：阅读并理解每一行。

值得借鉴：在 PR 标题中写上 (kimi)，为每个 PR 注明模型。

Bun 创建者，现就职于 Anthropic

Agent：Claude Code（命令行）、RoboBun。模型：Claude Fable 5。

审查：每个实现 Agent 对应两个对抗式 Claude 审查者，然后他阅读审查结果。

值得借鉴：对抗式审查，由两个 Claude 对每项改动提出反驳。

Symmathesy、Honeycomb

Agent：Claude Code。模型：Claude Opus 5.5、Claude Sonnet 5.5。

审查：审查 Agent 对照明确的正确性条件检查每个 PR；她自己的审查则用于改进系统。

值得借鉴：Capability Owners，为每项功能配备常驻 Agent。

Elixir、Tidewave 创建者

Agent：Codex、Tidewave（应用端）。模型：Sol 5.6。

审查：像审查其他代码一样审查 Agent 的 PR。

值得借鉴：对抗式审查 Agent，用于编译器和安全工作。

fast.ai、Answer.AI、ULMFiT

Agent：Claude Code（命令行）、Solveit（网页端）、Codex。模型：Claude Opus 4.5。

审查：以小步骤推进，他逐一跟进；Agent 修改他已发布的库之前必须先提出方案。

值得借鉴：claude-air，在连续 8 轮沉默后发出提醒。

Instructor 创建者、OpenAI 开发者体验团队

Agent：Codex（应用端）。模型：GPT-5.5、GPT-5.3-Codex-Spark。

审查：审查技能以同事的 PR 反馈为范本；记忆变更以 git diff 的形式审查。

值得借鉴：$ultragoal，将目标保存在可编辑文件中。

Testing Library、Epic Web

Agent：Grok Bot、Cursor（网页端）。模型：Grok 4.5、Fable。

审查：信任检查门槛和 AI 审查者，只看结果，不看 diff。

值得借鉴：/ship-pr，执行 Bugbot 循环、合并并通知 Discord。

Cloudflare Workers、Cap'n Proto

Agent：Claude Code（命令行）、Cloudflare OS（网页端）。模型：Fable 5.1、Sol。

审查：Sol 审查每次提交；他审查计划和代码。

值得借鉴：仓库中的 plans/ 目录，将计划提交到仓库以供代码审查。

Obsidian CEO

Agent：Claude Code（命令行）。模型：未注明。

审查：必须阅读记录下来的测试输出；测试用例在修复前必须失败。

值得借鉴：先失败的测试用例，在每次修复提取问题之前使用。

SpaceX 机器学习团队，前 Cursor、Vercel 员工

Agent：Grok Bot（应用端）、Cursor（网页端）。模型：Claude Opus 4.5、GPT-5.1-Codex-Max。

审查：审查大部分代码并进行测试；Bugbot 审查每个 PR。

值得借鉴：计划模式，在每次长时间运行 Agent 之前使用。

《Staff Engineer》作者、Imprint CTO

Agent：Claude Code、Agent Fleet、Codex。模型：GPT 5.4。

审查：清空上下文后，由同一运行框架先审查，随后由人类审查。

值得借鉴：/linear-project-loop，循环推进项目直至达成目标。

Digital garden、GitHub Next

Agent：Claude Code（网页端）、Codex、OpenCode。模型：Claude Opus 5、Claude Sonnet 4.6。

审查：观察 diff，在 IDE 中检查代码。

值得借鉴：maggie-design，将她的设计品味封装为一项技能。

rust-analyzer、TigerBeetle

Agent：Claude Code（命令行）。模型：Claude 3.7 Sonnet。

审查：自己把控结构，并运行代码。

OpenClaw, ex-PSPDFKit

Agents: OpenClaw (web), Codex (app). Model: GPT-6.1 Sol.

Review: Codex reviews every commit

One thing to take: $autoreview , before every commit.

Datasette, Django co-creator

Agents: Codex (app), Claude Code (web). Model: GPT-6 Sol, Claude Opus 5.5.

Review: Cross-model review: Claude checks GPT, GPT checks Claude

One thing to take: Showboat , agents demo their own work.

Created Claude Code

Agents: Claude Code (app), Claude Tag. Model: Fable 5.1.

Review: Reads diffs only for critical code

One thing to take: /go , test, /simplify, open PR.

nanochat, coined “vibe coding”

Agents: Claude Code (cli), Codex. Model: Claude Fable 5.

Review: Watches agents like a hawk in an IDE

One thing to take: autoresearch , overnight agent research.

Ghostty, HashiCorp co-founder

Agents: Claude app (app), Codex app (app). Model: Claude Fable, GPT-6 Astra.

Review: Hand-reviews every line; agents validate, he writes all prose

One thing to take: Harness engineering , after every agent mistake.

Ruby on Rails, Omarchy

Agents: Codex (cli), Claude Code (cli), OpenCode (cli). Model: GPT-6.1 Sol, Claude Opus 5.5.

Review: A second model reviews, then he reads the diff

One thing to take: "Review this with claude" , adversarial review from Codex.

Flask, Earendil founder

Agents: Pi (cli), Codex. Model: Sol, Fable.

Review: Steers as it goes, reviews when the agent says done

One thing to take: /answer , in place of plan mode.

T3 Stack, T3 Chat, T3 Code

Agents: Claude Code (app), Codex (app). Model: Opus 5.5, Muse Wonder.

Review: Opus asks Wonder for code review; agents merge when confident

One thing to take: T3 Code , his own GUI over every agent.

Redis creator, DwarfStar (ds4)

Agents: Codex (cli), Claude Code (cli), ds4-agent (cli). Model: GPT-6 Astra / GPT-6.1 Sol, Fable.

Review: Still reviews Redis code, calls it mostly pointless

One thing to take: QA_BEFORE_RELEASES.md , an agent QA pass per release.

Harpoon, Vim on stream

Agents: Cursor (ide), 99 (ide). Model: Grok 4.6.

One thing to take: Field guide , agent writes its own lessons.

Gas Town, Beads, Vibe Coding

Agents: Claude Code (cli), Codex. Model: Claude Opus 5.5, Claude Fable 5.1.

Review: Fable reviews every Opus change; he doesn't read code

One thing to take: Seats , 18 long-lived Fable officers.

Photo AI, Nomads.com

Agents: Claude Code (cli). Model: Claude Opus 5.5, Claude Fable 5.1.

Review: Step by step, keeps the agent on a short leash

One thing to take: tm , a tmux session per site.

pi coding agent, libGDX

Agents: Pi (cli). Model: GPT-5.5.

Review: Limits daily output to what he can review

One thing to take: Daily code limit , sized to what he can review.

Amp co-founder, interpreter book

Agents: Amp (web). Model: Claude Opus 5.5, GPT-6 Astra.

Review: Spot checks and architecture, not every line

One thing to take: “Irrefutable proof” , video proof, not line reads.

Superpowers, Keyboardio, K-9 Mail

Agents: Claude Code (cli), Evener, Muse. Model: Claude Opus, Claude Haiku.

Review: Agent sessions do adversarial review

One thing to take: /par , rival reviewers, 5 points.

CEO 2389.ai, CTO Obama 2012

Agents: Claude Code (cli), Codex (app). Model: Claude Fable 5.1, GPT-6 Astra.

Review: One fresh-eyes review pass per change

One thing to take: "fresh eyes" review , a subagent rereads the code.

TDD, Extreme Programming, JUnit

Agents: Claude Code (cli), Codex (cli). Model: Gemini.

Review: Reviews solo, would rather be pairing

One thing to take: TCR skill , red tests revert the code.

Compound Engineering, Cora

Agents: Cursor, Claude Code (cli), Codex. Model: Claude Opus 5.5, Claude Sonnet 5.5.

Review: Parallel review agents, no line-by-line reading

One thing to take: /ce-compound , turns each fix into a lesson.

Total TypeScript, ex-Vercel

Agents: Claude Code (cli). Model: Claude Opus 5.5, Claude Opus 5.

Review: Reviews by merge danger, two-axis /code-review

One thing to take: /grill-me , before every change.

Context, uniprof, Sentry AI lead

Agents: Claude Code (cli), Codex. Model: Claude Opus 5.5, GPT-5.

Review: Reviews the plan and prompts, not the 10,000-line diff

One thing to take: Claudescope , transcript link in every PR.

Claude Code at Anthropic, ex-Chrome

Agents: Claude Code, Codex. Model: Fable.

Review: Careful human review of core paths only

One thing to take: /loop PR triage , on Agent Skills, every day.

Creator of the Ralph loop

Agents: OpenCode (cli), Cursor (web), Loom. Model: GPT-6.1 Sol, GLM / Kimi.

Review: Ships without manual review; stops only for high-risk changes

One thing to take: The Ralph loop , an agent in a bash while loop.

Co-founded Amp and Sourcegraph

Agents: Amp (web). Model: Amp Dial: medium.

Review: Agent reviews first, he scans diffs for red flags

One thing to take: "I'm feeling Pucky" button , starts half their work.

OpenCode co-founder, SST

Agents: OpenCode. Model: Astra, Fable.

Review: Asks a smarter model to review, via subagents

One thing to take: Voice prompting (Hex) , instead of typing.

Codex at OpenAI, ex-Cline

Agents: Codex (app). Model: GPT-6 Astra, GPT-5.3-Codex-Spark.

One thing to take: "Chief of staff" thread , spawns every project thread.

Tailwind CSS, Refactoring UI

Agents: Amp (web), Codex (app), Claude Code (web). Model: Claude Sonnet 4.5.

One thing to take: Every tedious OSS task , fed to cloud Claude Code.

Vitest, Slidev, UnoCSS, VueUse

Agents: Claude Code, Cursor (ide). Model: Claude Sonnet 5.5, Claude Opus 5.

Review: Watches the result: Storybook for agent UI, a pulls.review summary on every PR, then the final diff

One thing to take: antfubot , agents ship PRs as a bot.

Ladybird browser, SerenityOS

Agents: Claude Code, Codex. Model: Frontier model.

Review: Adversarial review passes by different models

One thing to take: Welfare checks , on workers across 4 machines.

DTrace, Oxide co-founder and CTO

Agents: Claude Code (cli), ChatGPT. Model: Claude Opus 4.8.

Review: Self-review first: nobody else reviews LLM code until the responsible engineer has

One thing to take: This Old Repo , reviving a 1990s game.

Thoughtworks, harness engineering

Agents: Cursor (ide), Claude Code, Pi (cli). Model: Claude Sonnet, Claude Opus 4.8.

Review: Risk triage: probability, impact and detectability set how much she reads; sensors point her to where

One thing to take: sensors check , a sidecar the agent polls.

Works on GitHub Copilot

Agents: GitHub Copilot (app), Claude Code (web). Model: Luna Max, Claude Opus 5.5.

Review: Rubber duck review by a second model family; he no longer reads the code

One thing to take: A lead agent per project , he just files issues.

ripgrep, Rust regex, Jiff

Agents: Codex (cli). Model: GPT-5.6 Sol.

Review: Flags his LLM PRs for careful review, then simplifies them by hand; Codex review catches bugs too

One thing to take: "I wrote this PR with an LLM" , flagged for careful review.

Segment co-founder, ex-Codex

Agents: Codex (cli), Claude Code (cli). Model: Fable 5, GPT-5.6 Sol.

Review: Spot-checks the architecture; Cursor Bugbot and Codex review every PR

One thing to take: /pr-pass , loops until CI and bots pass.

Claude Code product, Anthropic

Agents: Claude Code (app), Claude Tag. Model: Claude Opus 5.5, Claude Fable 5.1.

Review: Claude code review clears the outer layers; code owners review the core

One thing to take: Fresh config per model , reset at every model launch.

AI Engineering author

Agents: Codex, Claude Code. Model: Claude Fable.

Review: A second agent reviews the plan; UI work comes with screenshot evidence on the PR

One thing to take: Cross-provider runner , Codex, Claude spawn each other.

Creator of Phoenix, Phoenix.new

Agents: Claude Code. Model: Claude.

Review: Rules file names the tests to run before claiming a fix

One thing to take: notify msg , in CLAUDE.md, not a hook.

exe.dev, Tailscale co-founder

Agents: Shelley (web). Model: OpenAI models.

Review: Reads agent code before it hits serious systems, trimmed by meat

One thing to take: meat , strips diffs to what matters.

ChatPRD founder, How I AI host

Agents: Codex (app), Claude Code, Cursor (web). Model: GPT-6 Astra, Claude Opus 5.5.

Review: Cross-model review: Opus 5.5 reviews GPT's PRs and vice versa; PRs also get human review

One thing to take: LGTM, the PR closer , a bot that clears her PR queue.

danluu.com essays, ex-Centaur

Agents: Codex (cli). Model: GPT-5.6 Sol.

Review: Heavy randomized testing instead of human review

One thing to take: Named-persona review panels , with contrarian personas.

"How to Fix Your Context", Plumb

Agents: Claude Code. Model: Claude Fable, GLM 5.2.

Review: Steps through the decisions Plumb extracts at each commit instead of reading the diff

One thing to take: Plumb , reviews decisions at commit.

HumanLayer CEO, 12-Factor Agents

Agents: HumanLayer (ide), Codex, Claude Code. Model: GPT-5.6 Sol, Claude Fable.

Review: Still reads the code, one 1k-3k PR at a time

One thing to take: /show-me , diagrams, not walls of prose.

CEO of Every

Agents: Codex (app), Claude Code. Model: GPT-6 Sol, Claude Fable.

Review: Vibe codes; doesn't read the codebase

One thing to take: "Want me to compound?" , asked after every sweep.

Codex product lead, OpenAI

Agents: Codex (app). Model: Codex default model.

Review: Reads the plan; Codex reviews nearly every PR

One thing to take: "Using a subagent in parallel, do X" , from one always-on thread.

PyTorch at Meta, ghstack

Agents: Claude Code (cli), Codex. Model: Claude Opus 5.5, Claude Fable 5.

Review: Reads every line, steers with questions and edits

One thing to take: sl follow / sl adopt , restack parallel agents.

Game Engine Black Books

Agents: Claude Code (ide), Antigravity (ide). Model: .

Review: Reads all the code; LLM criticizes first

One thing to take: "Reload agent.md" , when code quality drops.

Go cryptography, age, mkcert

Agents: Shelley (exe.dev) (web), Claude Code (cli). Model: GPT-6 Astra, Claude Opus 4.8.

Review: LLM review before any human review

One thing to take: filippo-agent , agent's own GitHub account.

YC CEO, creator of gstack

Agents: Claude Code (app), Codex (cli). Model: Claude Fable 5.1.

Review: Every branch gets CEO, Codex, DX and eng review passes

One thing to take: /plan-ceo-review , finds the 10-star product.

Ansible, Raspberry Pi YouTube

Agents: Claude (web). Model: Claude Opus 5.5, Claude Fable 5.1.

Review: Reviews in stages, like a tech lead with juniors

One thing to take: AI Disclosure , README names the exact model.

Malleable software, Notion

Agents: Claude Code, Cursor (ide), Codex CLI (cli). Model: Claude Opus 5, Claude Fable 5.

Review: Reads an explainer first, then the full diff; must pass a 5-question quiz before sending code on

One thing to take: /explain-diff , with a quiz before he ships.

tinygrad, comma.ai

Agents: OpenCode. Model: Kimi, Claude Opus.

Review: Reads and understands each line

One thing to take: (kimi) in the PR title , names the model per PR.

Creator of Bun, now at Anthropic

Agents: Claude Code (cli), RoboBun. Model: Claude Fable 5.

Review: Two adversarial Claude reviewers per implementer, then he reads the outputs

One thing to take: Adversarial review , 2 Claudes refute every change.

Symmathesy, Honeycomb

Agents: Claude Code. Model: Claude Opus 5.5, Claude Sonnet 5.5.

Review: A reviewer agent checks each PR against a stated correctness condition; her own reviews fix the system

One thing to take: Capability Owners , standing agents per feature.

Creator of Elixir, Tidewave

Agents: Codex, Tidewave (app). Model: Sol 5.6.

Review: Reviews agent PRs like any other code

One thing to take: Adversarial review agents , on compiler & security work.

fast.ai, Answer.AI, ULMFiT

Agents: Claude Code (cli), Solveit (web), Codex. Model: Claude Opus 4.5.

Review: Small steps he follows one by one; the agent must propose before touching his published libraries

One thing to take: claude-air , nudges after 8 silent rounds.

Instructor creator, OpenAI DX

Agents: Codex (app). Model: GPT-5.5, GPT-5.3-Codex-Spark.

Review: Review skills modelled on colleagues' PR feedback; memory changes reviewed as git diffs

One thing to take: $ultragoal , goal kept in an editable file.

Testing Library, Epic Web

Agents: Grok Bot, Cursor (web). Model: Grok 4.5, Fable.

Review: Trusts gates and AI reviewers, reads the outcome, not the diff

One thing to take: /ship-pr , Bugbot loop, merge, Discord.

Cloudflare Workers, Cap'n Proto

Agents: Claude Code (cli), Cloudflare OS (web). Model: Fable 5.1, Sol.

Review: Sol reviews every commit; he reviews the plan and the code

One thing to take: plans/ in the repo , checked in for code review.

CEO of Obsidian

Agents: Claude Code (cli). Model: .

Review: Recorded test output must be read; fixture must fail before the fix

One thing to take: Fail-first fixtures , before every extraction fix.

ML at SpaceX, ex-Cursor, Vercel

Agents: Grok Bot (app), Cursor (web). Model: Claude Opus 4.5, GPT-5.1-Codex-Max.

Review: Reviews most of the code and tests it; Bugbot reviews every PR

One thing to take: Plan mode , before every long agent run.

Staff Engineer, CTO at Imprint

Agents: Claude Code, Agent Fleet, Codex. Model: GPT 5.4.

Review: Same harness reviews first, context cleared; humans after

One thing to take: /linear-project-loop , loops a project to its goal.

Digital garden, GitHub Next

Agents: Claude Code (web), Codex, OpenCode. Model: Claude Opus 5, Claude Sonnet 4.6.

Review: Watches the diffs, checks code in an IDE

One thing to take: maggie-design , her design taste, as a skill.

rust-analyzer, TigerBeetle

Agents: Claude Code (cli). Model: Claude 3.7 Sonnet.

Review: Owns the structure, runs the code, does not vet the guts

One thing to take: Hand-typed skeletons , Claude fills in the bodies.

Founder, Takeoff AI

Agents: Codex (app), Claude Code (cli). Model: Claude Opus 5.5, GPT-6 Astra.

Review: Approves without reading the code

One thing to take: "You are AGI-pilled." , in every agent's system prompt.

Homebrew maintainer since 2009

Agents: Codex (cli), Claude Code (cli), OpenCode (cli). Model: Fable 5, OpenAI Codex 5.4.

Review: Reviews agent work before pushing it himself; depth depends on the code

One thing to take: AgentIDE , his own vibe-built agent IDE.

Instagram co-founder, Anthropic Labs

Agents: Claude Desktop (app). Model: Claude Opus 5.5, Claude Sonnet 5.5.

Review: Hands over whole goals and has Claude verify, then double-verify

One thing to take: iOS Claude pings Android Claude , to port each feature.

Ex-BuzzFeed data scientist

Agents: Zed Agent (ide), Codex (cli), Claude Code (cli). Model: GPT-6 Astra, GPT-5.6 Luna.

Review: Luna subagents re-check until all satisfied; he watches benchmark diffs

One thing to take: codex exec Luna subagents , 7–12 cheap critics per pass.

RLHF Book, Interconnects

Agents: Claude Code (cli), Codex. Model: Claude Fable 5, GPT 5 Pro.

Review: Lets agents catch their own mistakes, then checks the results himself

One thing to take: /gemini-feedback , Gemini critiques each diagram.

coverage.py

Agents: Claude Code (cli), GitHub Copilot (ide). Model: .

Review: A person owns and reviews every commit, Claude or not

One thing to take: Be introspective , Claude fixes its own rules.

PouchDB, emoji-picker-element

Agents: Claude Code, Codex (cli), Cursor Bugbot (web). Model: Claude Opus 4.7, GPT 5.5.

Review: Three agents hunt bugs in every PR; he triages the ranked report and guides the fixes

One thing to take: code-review-turbo , three-agent PR bug hunt.

Puzzmo, CocoaPods, Danger

Agents: Claude Code (ide), Claude Code on the web (web). Model: Fable.

Review: Reads all Puzzmo code; Claude reviews every PR too

One thing to take: /commit , human writes the headline.

Chrome DevTools, Lighthouse

Agents: Codex (web), GitHub Copilot coding agent (web), Jules (web). Model: Gemini 3 Flash (preview).

Review: Codex bot reviews every PR; he has Copilot fix the findings

One thing to take: paulirish-agent , a GitHub account for agents.

Build an LLM From Scratch author

Agents: Codex, Claude Code, Qwen Code (cli). Model: GPT-5.5, Qwen3.6-35B-A3B.

Review: Wants to see what the agent is doing; writes the code he cares about himself

One thing to take: Audit the agent first , before installing any harness.

CEO of Vercel

Agents: Claude Code. Model: Claude Opus 4.6.

One thing to take: gdp-ts , auth checks as type proofs.

Creator of Node.js and Deno

Agents: Claude Code, Codex. Model: Claude Opus 4.6.

One thing to take: Claw Patrol , firewall between agents and prod.

Writing on AI and big tech

Agents: GitHub Copilot app (app), Copilot CLI (cli). Model: GPT-6-Astra, Claude Opus 5.5.

Review: Skims each attempt for ~30 seconds, rejects most, then fully reviews the one he keeps

One thing to take: 30-second triage , rejects most agent attempts.

Gumroad founder

Agents: Claude Code, Codex. Model: Claude Fable 5, GPT-6.

Review: Does not just hit merge: QA, then asks a colleague to check

One thing to take: Fourth-wall check , enforced in CI on every PR.

Founder of Untangle

Agents: Devin (web), Codex. Model: Claude Opus 5.5, SWE 1.7.

Review: Agents review and land; he watches a test video first

One thing to take: !land playbook , refreshes skills on every PR.

Co-author of the Rust book, jj

Agents: Claude Code (cli), Codex (app). Model: Claude Fable, GPT Sol.

Review: Codex reviews Fable's PRs; humans stay responsible for what they submit

One thing to take: rue-overnight-hunt , bugs filed only with repros.

Latent Space, AI Engineer

Agents: Codex, Claude Code (cli), Devin (web). Model: Claude Opus 4.6.

Review: Devin Review bot comments on each agent PR, often after merge

One thing to take: $cassandra-creator , a standing dissent agent.

Fields Medal mathematician, UCLA

Agents: Claude Code. Model: Claude Opus 5.

Review: Checks results, doesn't read machine code

One thing to take: Five favorable conditions , before handing code to an agent.

Claude Code team, Anthropic

Agents: Claude Code (cli), Claude Tag. Model: Claude Fable 5, Claude Opus 5.5.

Review: Claude writes an HTML report and a quiz on the change; he merges only after passing it

One thing to take: Change quiz , must pass before merging.

FastAPI, Typer, SQLModel

Agents: Codex. Model: GPT-6 Astra.

Review: Reviews and adjusts all AI code by hand

One thing to take: AI Disclaimer , names agent and model in PRs.

Codex & ChatGPT at OpenAI

Agents: Codex (app). Model: GPT-5.6 Sol, GPT-6 Astra.

Review: Reviews what the agent presents; uses a fast model to understand code, never delegates understanding

One thing to take: Random-file bug hunt , automation, several times a day.

Val Town, Placemark, ex-Mapbox

Agents: Claude Code (cli), Pi. Model: Claude Sonnet 5, GLM 5.2.

Review: Careful human review of LLM fixes

One thing to take: Pi on GLM 5.2 , as the security bug hunter.

Shopify CEO, qmd

Agents: Claude Code, Pi (cli), Hermes Agent. Model: Claude Opus 5.5, GPT-6 Astra.

Review: Spec suite the agent must pass

One thing to take: qmd , local search, agents too.

DataScript, Fira Code

Agents: Claude Code, Codex. Model: Claude Opus 5.5.

One thing to take: Live nREPL for the agent , instead of app restarts.

Creator of Linux and Git

Agents: Claude. Model: Claude Opus.

Review: Opus writes verification scripts; the AI checks its own output

One thing to take: Pedals in a ring , a bench that tests itself.

Matasano, Latacora, Cryptopals

Agents: Claude Code (cli), Codex. Model: Claude Opus 5.5, GPT-5.5.

Review: Agents push PRs, only he merges

One thing to take: swiftui-app template , copied into every new app.

Clean Code author

Agents: Grok (cli), Codex (cli). Model: Grok.

Review: Does not read agent code: Codex reviews Grok's output, he inspects a UML diagram colored by CRAP and mutation scores

One thing to take: uml-viewer , colored by CRAP + mutation.

Co-founder, Cognition (Devin)

Agents: Devin (web). Model: Fable, GPT-5.5.

Review: Devin Review first, then asks Devin what to look at first

One thing to take: Daily customer-report Devin , escalates top feature asks.

Syntax podcast co-host

Agents: Claude Code (cli), Codex (app), OpenCode (cli). Model: Claude Opus 5.5, Codex models.

Review: Reviews after the fact: tests it works, checks for duplicated messes

One thing to take: vite-plugin-killer-instincts , hands the LLM a kill command.

pandas, Apache Arrow

Agents: Claude Code (cli), Codex (app). Model: Claude Fable, GPT-5.6 Sol.

Review: roborev reviews every commit; he checks structure

One thing to take: roborev , reviews every agent commit.

Anubis, xeiaso.net

Agents: Claude Code (cli), Codex, OpenCode. Model: Claude Opus 5.5, GPT-6.1 Sol.

Review: A second agent team reviews; /reviewbot on PRs

One thing to take: Assisted-by: footer , model + tool on every commit.

Co-founder and CEO of Warp

Agents: Warp Factories (web), Warp agent (app). Model: GPT 5.6 Sol.

Review: Engineer reviews the agent PR and ships it; QA video attached

One thing to take: Scorer + self-improvement agents , agents that fix agents.