There is no single correct way to assemble a software factory. Labs want us to trust agents more than we should. Tech influencers gloss over important, practical details. This workshop introduces several composable patterns for making a codebase more factory-like: to improve the throughput, quality, and verifiability of autonomous agent work in your project.
We will cover:
- Planning the work that gets handed over to a software factory
- Converting plans and specifications to durable internal docs (and rules) that don’t go stale
- Task decomposition for coding agents, and the tools that help with it
- Review strategies and tools that can manage massive PRs
- Agent-friendly QA setups that allow coding assistants to verify their work and fix bugs before human review
- When you can safely skip human review entirely
- The role of sandboxes (local and remote) for scaling and handling agent work on your codebase
This workshop has been presented at AI Coding Summit London, check out the latest edition of this Tech Conference.
