一句话：提出 Polymer 配方，用 LLM 把开发工作流写成软件以自动化开发早期阶段，在沃尔沃自动化测试中节省 2–3 个 FTE。
软件开发旨在自动化流程，但其从启动到部署的早期阶段仍以人工为主。原因有二：开发任务常欠规约；任务之间的转换又往往需要人工“翻译器”。二者相互强化：无法衔接时规约无意义，而写翻译器又需要规约。作者指出 LLM 改变了这一成本方程——它既能处理欠规约的系统，又擅长翻译，可作为“万能钥匙”自动打通此前成本过高而难以互连的任务与转换。据此论文提出 polymer（将开发工作流写成软件）这一配方，以进一步自动化开发早期阶段。作者报告在大型汽车制造商沃尔沃的落地：将 polymer 用于自动化测试，以约两个月的开发与部署成本节省 2–3 个 FTE，并给出 polymer 化工作流的开放挑战。
Software development builds digital tools to automate processes, yet its initial phases, up to deployment, remain largely manual. There are two reasons: Development tasks are often under-specified and transitions between tasks usually require a translator. These reasons are mutually reinforcing: it makes little sense to specify tasks when you cannot connect them and writing a translator requires a specification. LLMs change this cost equation: they can handle under-specified systems and they excel at translation. Thus, they can act as skeleton keys that unlock the automation of tasks and transitions that were previously too expensive to automatically interlink. We introduce a recipe for writing development workflows as software (polymer) to further automate the initial phases of development. We show how adopting polymer at Volvo, a large automotive manufacturer, to automate testing saved 2–3 FTEs at the cost of two months to develop and deploy. We close with open challenges when polymerizing development workflows.