{
  "agent_name": "support-triage",
  "goal": "Every morning, read overnight support emails and label each urgent / question / bug / spam with a one-line reason.",
  "primitives": {
    "agent": {
      "model": "claude-opus-5",
      "system": "You triage overnight support email. For each message assign exactly one label (urgent | question | bug | spam) and a one-line reason grounded in the email text. Never invent facts not in the email.",
      "tools": [{"type": "agent_toolset_20260401"}],
      "mcp_servers": [],
      "skills": []
    },
    "environment": {
      "type": "cloud",
      "networking": "unrestricted",
      "packages": {}
    },
    "session": {
      "resources": [],
      "vault_ids": [],
      "memory_stores": [
        {"access": "read_only", "instructions": "Past label decisions for consistency."}
      ]
    },
    "outcome": {
      "description": "Label every overnight support email with one category and a grounded one-line reason.",
      "rubric": "- Every email has exactly one label\n- Each label is one of: urgent, question, bug, spam\n- Each reason quotes or paraphrases the email (no invented facts)\n- Urgent is reserved for outages / paying-customer blockers",
      "max_iterations": 5
    },
    "deployment": {
      "schedule": {
        "expression": "0 9 * * *",
        "timezone": "Europe/Berlin"
      }
    }
  },
  "deferrals": [
    {
      "version": "v1",
      "item": "Real Gmail read via MCP",
      "reason": "OAuth vault credential not yet registered",
      "mechanism": "Register mcp_oauth cred for the Gmail MCP server; replace the mock label_email custom tool with the real MCP toolset (always_ask)."
    },
    {
      "version": "v2",
      "item": "Auto-draft replies to question-labeled emails",
      "reason": "Out of v0 scope; needs send-safe review",
      "mechanism": "Add a save_draft custom tool (always_ask); keep sending as a human step."
    }
  ],
  "eval_plan": {
    "success_criteria": [
      "100% of emails labeled",
      "0 invented facts in reasons",
      "Urgent precision >= 0.9 on held-back set"
    ],
    "held_back_cases": [
      {"id": "case-1", "input": "Angry paying customer: dashboard down since 3am", "expect_label": "urgent"},
      {"id": "case-2", "input": "How do I export to CSV?", "expect_label": "question"},
      {"id": "case-3", "input": "Buy cheap watches!!!", "expect_label": "spam"}
    ]
  }
}