NetEase Zhixin launches CodeWave SDD multi-agent software delivery platform
NetEase Zhixin released CodeWave SDD, an enterprise AI Coding product that organizes role-specific agents across requirements, design, architecture, development, testing and deployment. It uses specification-driven development and an enterprise Harness environment. NetEase Zhixin says the platform has been used in projects at more than 100 companies and can increase delivery capacity by three to five times. It also reports first-pass rates of about 90% for P0 test cases and 80% for P1 and P2 cases. The reports provide no independent validation for these figures, and test-case first-pass rates do not equal overall project delivery success rates.
The reports frame CodeWave SDD as a shift from AI coding tools that assist individual developers toward systems that organize multiple agents across the software-delivery workflow. The release therefore addresses requirements, testing and deployment as well as code generation, while the claimed productivity and test metrics remain unverified.
过去两年，AI Coding 几乎成为软件开发者的标配。无论是代码补全、函数生成，还是 Bug 修复、代码重构，AI 都在不断提高开发人员的工作效率。
但一个值得注意的现象是，开发者写代码的速度越来越快，企业的软件项目交付效率却未必同步提升。
美国软件工程数据分析与研发效能管理公司 Faros AI 分析了超过 1 万名开发者、1255 个软件工程团队的工作流数据，涵盖版本控制、代码审查、任务管理和 CI/CD 等系统。
尽管开发者完成了更多任务，研究却没有发现 AI 采用率与企业层面关键交付指标改善之间存在显著相关性。更有意思的是，PR 合并数量增加了 98%，代码审查时间却增加了 91%。 这反映出一个可能的瓶颈转移：代码生成加速之后，审查、测试和集成未必能跟上。