Make AI agents follow instructions reliably and prove what they did. State machine engine with evidence chains, multi-agent delegation, human gates, and auditable execution — via MCP or CLI.
| Tool name | Description | Destructive? |
|---|---|---|
| submit_human_response | ✓ no | |
| get_workflow_protocol | ✓ no | |
| execute_step⚠ | ⚠ yes | |
| list_workflows | ✓ no | |
| create_workflow | ✓ no |
| start_run⚠ | ⚠ yes | |
| get_run_state⚠ | ⚠ yes | |
| append_trace | ✓ no | |
| start_run_batch⚠ | ⚠ yes |