toyota-kata-state-machine-skill

To enforce disciplined iteration, define a bounded improvement task and initialize a kata improvement board to run evidence-based experiments. This state-machine workflow prevents speculative redesign by gating decisions through defined artifacts and learning reviews.

Prevent uncontrolled redesign by applying an iterative improvement protocol that focuses on a single obstacle at a time. This approach replaces speculative changes with bounded experiments and measurable learning reviews.

A state-machine workflow structures incremental experimentation by moving tasks from Intake to Stop through defined states. This enforces artifacts like the improvement board and gates progress based on evidence from bounded experiments.

You need an evidence-based iteration protocol when improving systems through incremental experiments rather than large speculative changes. This approach is useful when gated decisions and measurable learning are required to improve reliability.

Yes, this protocol applies to any project where incremental experiments and measurable learning are needed to improve AI behavior, debugging, or process changes. You start by describing a bounded improvement task and initializing the board.

Your agent lacks a structured improvement protocol to enforce disciplined, evidence-based iteration. By applying a kata workflow with bounded experiments and gated learning reviews, you prevent premature redesign and ensure measurable progress.