Documentation
Kata is a practice for a team of coding agents. The team works one cycle a day, and each section below covers one part of that cycle. Start with the setup guide. Then choose the guide for the task you have now.
Set Up the Team (Teams Using Agents)
Run a Continuously Improving Agent Team (Teams Using Agents)
Run a Continuously Improving Agent Team
Run the daily Plan-Do-Study-Act cycle with an agent team. Every shift leaves evidence, and every finding goes back into the loop as a pushed fix or a pushed spec.
Choose and Scope Your Agent Roster
Decide which agent personas run in your repository, and write the scope constraints that turn an out-of-scope finding into a spec instead of an unreviewed fix.
Keep Team Memory and Coordination Apart
Memory holds an agent's own state, and coordination needs a specific receiver and an artifact that receiver opens. Learn where the line is, and what breaks when a team buries a handoff in the wiki.
Run the Daily Storyboard and Coaching Session
Run the team storyboard meeting and the one-on-one coaching session with the five Toyota Kata questions, so that every experiment starts from measured data instead of an impression.
Turn Study Findings into Fixes and Specs
Classify every Study finding once, then route it to a fix branch, a spec branch, a Discussion, or a close. Fix branches and spec branches never mix, and a local commit never completes a finding.
Take a Change from Spec to Shipped (Teams Using Agents)
Take a Change from Spec to Shipped
Take one change through the full sequence: spec, design, plan, implementation, independent review, merge, and release. Each phase produces one artifact that answers one question.
Set the Approval Gates and Trust Boundary
Decide what your agents may approve and what a human must approve. Then make the approval signal travel from a human action to the state file that the agents read at merge time.
Kata ships skills and agent profiles, but no command of its own. Three other standards supply the parts under it, and each one has its own site.
-
Gemba is the runtime.
Kata skills call the
gemba-*commands to run a session, read a trace, keep memory, and chart a metric. The Gemba site documents every command. - Jidoka is the instruction architecture. Use it when you write or repair an agent profile, a skill file, or a checklist.
- Monorepo is the repository structure. It defines the root files and the directory tree that an adopting repository uses.