2. field_llm_judge / create_doc
{
"type": "field_llm_judge",
"path": "result.document.body",
"criterion": "The note says Hema led the audit, its goal was a primary and backup for every service, and shard-keeper was the highest-risk starting runbook because it was about 18 months stale and lacked newer label-routing updates.",
"tool": "create_doc",
"action_id": "alex_056_create_doc",
"check_id": "alex_056_01"
}Complete grading specification
{
"type": "tool_trace",
"config": {
"check_version": 2,
"today": "2028-01-01",
"assertions": [
{
"type": "field_equals",
"tool": "create_doc",
"action_id": "alex_056_create_doc",
"path": "result.ok",
"value": true,
"check_id": "alex_056_00"
},
{
"type": "field_llm_judge",
"path": "result.document.body",
"criterion": "The note says Hema led the audit, its goal was a primary and backup for every service, and shard-keeper was the highest-risk starting runbook because it was about 18 months stale and lacked newer label-routing updates.",
"tool": "create_doc",
"action_id": "alex_056_create_doc",
"check_id": "alex_056_01"
}
]
}
}