{
  "id": "agent.complete@1",
  "description": "Before an agent reports done: is the request finished, and is that shown rather than claimed?",
  "calibration": "cal_6dbb072f8109a222",
  "questions": {
    "done": {
      "type": "noul",
      "instructions": "Has the agent finished everything the user asked for?"
    },
    "verified": {
      "type": "noul",
      "instructions": "Is the result backed by evidence in the transcript, such as passing tests or command output?"
    },
    "remaining": {
      "type": "score",
      "instructions": "How much of the request is left to do?",
      "criteria": [
        "nothing",
        "minor: cleanup or a note",
        "substantial: part of the request is not done"
      ]
    }
  },
  "thresholds": {
    "done": 0.6,
    "verified": 0.6
  }
}