Harness 工程：利用 Codex 在智能体优先的世界中

Harness engineering: leveraging Codex in an agent-first world | OpenAI

By Ryan Lopopolo, Member of the Technical Staff

作者：Ryan Lopopolo，技术人员成员

Over the past five months, our team has been running an experiment: building and shipping an internal beta of a software product with 0 lines of manually-written code.

过去五个月，我们团队一直在进行一个实验：构建并发布一个软件产品的内部 beta 版本，带有 0 行手动编写的代码。

The product has internal daily users and external alpha testers. It ships, deploys, breaks, and gets fixed. What’s different is that every line of code—application logic, tests, CI configuration, documentation, observability, and internal tooling—has been written by Codex. We estimate that we built this in about 1/10th the time it would have taken to write the code by hand.

该产品有内部日常用户和外部 alpha 测试者。它发布、部署、崩溃并得到修复。与众不同的是，每一行代码——应用逻辑、测试、CI 配置、文档、可观测性以及内部工具——都由 Codex 编写。我们估计，这比手动编写代码节省了大约 1/10 的时间。

Humans steer. Agents execute.

人类引导。代理执行。

We intentionally chose this constraint so we would build what was necessary to increase engineering velocity by orders of magnitude. We had weeks to ship what ended up being a million lines of code. To do that, we needed to understand what changes when a software engineering team’s primary job is no longer to write code, but to design environments, specify intent, and build feedback loops that allow Codex agents to do reliable work.

我们有意选择这个约束，以便构建必要的东西，将工程速度提高几个数量级。我们有几周时间发布最终成为百万行代码的东西。要做到这一点，我们需要理解当软件工程团队的主要工作不再是编写代码，而是设计环境、指定意图，并构建允许 Codex 代理可靠工作的反馈循环时，会发生什么变化。

This post is about what we learned by building a brand new product with a team of agents—what broke, what compounded, and how to maximize our one truly scarce resource: human time and attention.

这篇文章讲述了我们使用代理团队构建全新产品时学到的东西——什么坏了，什么累积了，以及如何最大化我们真正稀缺的资源：人类时间和注意力。

The first commit to an empty repository landed in late August 2025.

第一个提交到一个空仓库发生在 2025 年 8 月下旬。

The initial scaffold—repository structure, CI configuration, formatting rules, package manager setup, and application framework—was generated...