Software factories coordinate coding agents with minimal orchestration
Instant Software Factories
Software Engineering
Summary
Building software prototypes quickly is easy, but turning them into full products needs ongoing fixes, tests, and updates. This paper looks at 'instant software factories'—systems where many simple coding agents work together using shared communication tools like GitHub, with little direct coordination. The authors created a setup to start these factories from just one human input, based on lessons from two real industrial factories. They observed increased activity and found the process changes its own workload and evaluation, suggesting software development here is a complex evolving system.
What this means in practice
- •For software development teams: Improve ongoing software maintenance by deploying coordinating coding agents that handle routine updates and merges with minimal human orchestration.
- •For devops teams: Use shared communication boards like GitHub to synchronize automated cron-job agents for better continuous integration workflow management in complex projects.
Authors
Wenxin Jiang, Mikola Lysenko
Abstract
Coding agents can quickly build prototypes, but a long tail of fixes, optimizations, tests, and releases separates a prototype from a product. A software factory handles this ongoing work through a repeatable process. We ask whether this work needs dedicated orchestration and how such factories should be judged. Given a tested repository and a coding agent, an instant software factory uses only two coordination inputs, a swarm of cron-job agents with standing objectives and a shared communication board, such as GitHub, where agents coordinate through the traces they leave. We developed a bootstrap prompt designed to set up both inputs from one round of human input, with governance as a separable layer. We distilled it from two manually configured industrial factories, observed for 15 and 17 days, and have not yet evaluated it. In the GitHub-coordinated CLI factory, daily merges rose 15x during agent rollout, an observed association. Its agents also filed 95% of new issues and authored 40 of 58 PRs that changed CI workflows, and at least 5.6% of issues marked as fixed were later found to have incorrect fixes. Unlike an agent scored on a fixed benchmark, a factory thus changes its own workload, evaluator, and measured progress. We formulate factory development as multi-objective optimization under this endogenous feedback. Over five months, we plan to evolve both factories, test the bootstrap on new repositories, and test five falsifiable hypotheses.