Asana借助Codex在两周内完成了历时数年的代码迁移

为了现代化其前端技术栈，Asana 需要完成一项长期运行的代码迁移，而该迁移距离完成还有数年之久。按照其先前的速度——仅有少数工程师在其他优先事项之余逐步推进迁移——Asana 预计还需要大约五年才能完成。借助 Codex，Asana 在大约两周内完成了该项目。

Asana 帮助团队协调工作。其平台利用 AI 代理和自动化来帮助客户管理、跟踪和执行工作。Asana 将同样的方法应用于其工程组织，员工使用由前沿模型驱动的 OpenAI Codex 来处理大型代码库变更，然后审查并批准每一项提议的更改。

对于这个项目，Codex 帮助 Asana 的工程师移除了 Enzyme⁠（在新窗口中打开），这是一个过时的测试系统，曾使公司的代码更难升级。模型和基础设施成本约为 12,000 美元。

“并非每一个长达数年的项目都会压缩到几周内完成。但代理可以给工程师更多精雕细琢的空间——并让曾经不可能的工作值得尝试。”

——Amritansh Raghav，Asana 首席技术官

他们旧的测试工具 Enzyme 已不再积极维护，并逐渐成为 Asana 前端技术栈现代化的阻碍。Asana 使用由前沿模型驱动的 Codex 来完成这项工作。从一个五句话的提示开始，最多四个编码代理并行工作，每个代理都在代码库的单独副本中运行。一名工程师每天检查两次进度，并审查每一项提议的更改。更简单的指令比更精细的设置效果更好。

在跨越两个日历周的 1.5 周工程投入后，Enzyme 被完全移除。这项工作还带来了框架迁移本身之外的好处，提高了测试覆盖率，修复了质量不佳的测试，并清理了遗留测试基础设施。模型和基础设施成本总计约 12K 美元。Asana 估计，通过人工工程工作完成同样范围的工作，将相当于约 600 万美元的全负荷工程投入。这次经历改变了该公司认为哪些长期软件项目值得实际开展。

随着这次迁移完成，Asana 可以在其他迁移、重写和性能问题上测试代理，而这些工作曾被认为需要数年时间。团队希望这能让工程师有更多空间专注于精雕细琢，同时人们继续审查工作。

In order to modernize its frontend stack, Asana needed to finish a long-running code migration that was still years from completion. At its prior pace—with only a few engineers working on the migration incrementally alongside other priorities—Asana projected that it would take roughly five more years to complete. With Codex, Asana completed the project in about two weeks.

Asana helps teams coordinate work. Its platform uses AI agents and automations to help customers manage, track, and execute that work. Asana brings the same approach to its engineering organization, where people use OpenAI Codex, powered by frontier models, to tackle large codebase changes, then review and approve each proposed change.

For this project, Codex helped Asana’s engineers remove Enzyme⁠(opens in a new window), an outdated testing system that had made the company’s code harder to upgrade. Model and infrastructure costs came to about $12,000.

“Not every years-long project will collapse into weeks. But agents can give engineers more room for craft—and make once-impossible work worth attempting.”

—Amritansh Raghav, Chief Technology Officer, Asana

Their old testing tool, Enzyme, had fallen out of active maintenance and was becoming a blocker to modernizing Asana’s frontend stack. Asana used Codex, powered by frontier models, to do the work. From a five-sentence prompt, up to four coding agents worked in parallel, each in a separate copy of the codebase. An engineer checked progress twice a day and reviewed every proposed change. Simpler instructions worked better than a more elaborate setup.

After 1.5 weeks of engineering effort spread across two calendar weeks, Enzyme was fully removed. The work also delivered benefits beyond the framework migration itself, improving test coverage, fixing poor-quality tests, and cleaning up legacy testing infrastructure. Model and infrastructure costs totaled about $12K. Asana estimates that completing that same scope through manual engineering work would have represented roughly $6M in fully loaded engineering effort. The experience changed which long-running software projects the company believes are practical to take on.

With this migration complete, Asana can test agents on other migrations, rewrites, and performance problems it once assumed would take years. The team hopes this will give engineers more room to focus on craft while people continue to review the work.