Factory 用 linter 限制智能体写 useEffect，探讨代码规范强制执行
At @factory, agents can't add useEffect. The linter won't let them. @ross_cefalu on making opiniona...
Factory 的工程师讲了怎么用 linter 直接禁止智能体写 useEffect，把团队代码规范变成硬约束。比写一堆文档等人 review 靠谱，维护大代码库的团队可以看看这套思路。
在 AI Engineer Code Summit 第一天的工作坊上，Factory 的 ross_cefalu 介绍了如何用 linter 规则约束编码智能体。具体做法是：在 Factory 环境中，智能体无法添加 useEffect，因为 linter 会直接阻止这类代码通过，把团队的代码标准变成机器强制执行的规则。
这个思路的核心是把“靠 review 和口头约定维护代码规范”变成“靠工具链自动拦截”。传统上团队会写 CONTRIBUTING.md 或在 PR review 里反复纠正，而 Factory 选择让 linter 成为智能体的硬约束，智能体写出的代码必须先通过规范检查，规范执行从人的工作变成了基础设施的一部分。
这类做法对维护大型代码库的团队有直接参考价值：智能体生成的代码量增大后，规范一致性会取代单点 bug 成为主要痛点。与会者可以从 Day 1 workshop 中了解把团队标准落地为可执行约束的具体路径。
At @factory, agents can't add useEffect. The linter won't let them. @ross_cefalu on making opiniona...
At @factory , agents can't add useEffect. The linter won't let them. @ross_cefalu on making opinionated code standards easier to enforce with agents. From the Day 1 workshops at AI Engineer Code Summit.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Factory, agents, Linter, coding assistants.
Source attribution: curated from AI Engineer (@aiDotEngineer).
