AI Coding Tools Are Great Until the Only Test Is a Device in Someone's Hand

说明与用途

AI 工具加速了模板、配置和测试的生成，但在处理小众 API、编辑器管理的文件和设备相关功能时需要严格的治理。

问题

AI coding tools perform well on projects with abundant public code and fast feedback loops, but their effectiveness drops sharply when applied to niche platform APIs, editor-owned file formats, or systems where the only real test is a physical device.

结果

AI tools accelerate boilerplate, config, test scaffolding, and codebase orientation, but require strict governance to avoid errors in platform-specific logic, editor-managed assets, and device-dependent behavior.

工作流

• 1. Write a detailed spec outlining fields, tools, and rules.
• 2. Prompt Claude Code with the spec to generate code, configs, or tests.
• 3. Review the diff as if a junior engineer wrote it, checking logic and edge cases.
• 4. Verify changes on the real target (device, staging deploy, or real test call).
• 5. Iterate with small, focused changes, keeping the loop tight.

证据

AI coding tools are excellent where there is a lot of consistent public code and a fast way to check the result. They get worse as you move toward niche platform APIs, editor-owned file formats, and systems where the only real test is a device in someone's hand.

来源

Spec first, prompt second. If I cannot write down what done looks like, the tool cannot either.

来源

Review every generated change as if a new junior engineer wrote it.

来源

Verify on the real target. A device, a real test call, a staging deploy.

来源