The Software Factory: From Bug Report to Production Code — Davis Palmie, Factory
This talk introduces the concept of a 'software factory' as a system of agents designed to automate the transformation of bug reports and user feedback into production code. It argues that coding itself is not the bottleneck in software development, but rather review, debugging, documentation, and testing. The talk outlines key principles for building such a factory: model-agnosticism, sovereign deployment, and integration across the entire Software Development Life Cycle (SDLC). It suggests starting with narrow applications like incident triage and emphasizes the importance of agent readiness, governance, and incremental rollout. The speaker advocates for measuring outcome metrics such as signal-to-production time, interventions, and cost per PR, rather than focusing on token leaderboards.
More from the Software Factory Engineering trail
- From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot
- Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
- Let Anyone at Your Company Ship Internal Apps with AI — Garrett Galow, WorkOS
- Why AI Agents Should Have Their Own Sandbox — Philipp Schmid, Google DeepMind
- Redesigning How Software Gets Built With AI Agents — Sonar & McKinsey Panel