Toyota won and so did Agile, but in the process they became so well adapted to their context that it's not clear what they mean in an agentic world. Let's go back to basics.
A software factory produces software, sure, but specifically it delivers a steady stream of features, bug fixes, and optimizations. Call them all "updates". Updates flow out of the software factory.
But pushing code ceaselessly doesn't work once the bottleneck moves. We need the backwards flow, pull production for software.
Information flows backwards through the factory, pulling work. Tests are information; they pull code. Issues are also information; they pull tests. Features pull issues. Observability tools pull issues too. This flow is newer and theoretically less developed but it will be more important than the flow of updates.
The stations in the factory are things like design, coding, debugging, testing, reviewing, deployment, and metrics. Stations aren't independent. Don't optimize the stations, optimize the system, the hand-off between stations and the deployment of resources across them.
Optimize quality. We don't need code review agents, we need agents that write reviewable code. Quality means consistency. You need to decide what reviewable means and you need to enforce it. You need to define good design, of good code, of good tests. Don't pass defective code to the next station. Fix the process.
You must walk the floor. Look at agent traces. What commands do they run? What do they mess up? Do not blame your factory workers; yelling at Claude will not help. Every defect becomes a process improvement.