GoKawiilstatewright
Agents are suggestions, states are laws.
State machine guardrails that control which tools your AI agent can use in each phase. Define a workflow once, enforce it across Claude Code, Codex, Cursor, opencode, and Pi. Full docs →
The problem
AI agents are powerful but brittle. Give a model 40+ tools and an open-ended problem and it barely gets out of the gate. The common fix is bigger models and longer prompts... it helps sometimes. Observability tells you what went wrong after the fact; it doesn't prevent it.
The approach
Instead of making the model bigger, make the problem smaller.
State machines constrain the tool and solution spaces so the model reasons in a focused context at each step. A planning state gets read-only tools. When the agent transitions to implementation, edit tools unlock with limited shell access (write-via-redirect and destructive ops are blocked even when Bash is allowed). Testing only permits designated test commands. If you call a tool that's not in the current phase, you get rejected with a message telling you what IS available and how to transition.
Works the same way on frontier models (fewer tokens to completion) and local models where 13B+ models start solving tasks they'd otherwise fail.
Research results
... continue reading