Polymer: Development Workflows as Software

2025-03-22

AI Summary

Early-stage software development—spanning requirements elicitation, testing, and deployment—is hindered by ill-defined tasks and dense manual intervention points, impeding automation. Traditional CI/CD pipelines address only post-coding phases, leaving semantic gaps between underspecified stages unbridged. Method: We propose “workflow-as-software,” a novel paradigm that models end-to-end development as programmable workflows. Leveraging large language models (LLMs) as universal semantic adapters, our approach automatically reconciles heterogeneous task semantics. It integrates domain-specific workflow orchestration, a lightweight domain-specific language (DSL), and semantic translation interfaces. Contribution/Results: Evaluated in production at Volvo, the method reduced test automation effort by 2–3 full-time engineers and compressed the end-to-end development-to-deployment cycle to two months. It marks the first demonstration of LLM-driven, fully automated software delivery across the entire lifecycle—from requirements to deployment—thereby extending automation beyond conventional CI/CD boundaries.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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 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.

Problem

• Automating manual initial phases of software development
• Addressing under-specified tasks and transition challenges
• Using LLMs to enable workflow automation efficiently

Innovation

• LLMs automate under-specified development tasks
• Polymer workflows reduce manual translation efforts
• Automated testing saves significant FTE resources