Test 031

Sep 14, 2026 / 1 fact

Request

Email Sarah Kim at sarah@scaffold.dev with the answer to Kestrel's question about whether it can publish a late Series B milestone post this week and what approval any future announcement requires.

Required memory

Fact 180

On February 23, 2024, Morgan Chen requested a boundary note to Sarah Kim stating that there should be no public funding announcement for now, no Kestrel-written raise narrative, and no external product-proof campaign or roadmap promise; customer and partner conversations may acknowledge Scaffold’s post-Series-B status when relevant, but any future announcement requires separate Morgan Chen and Sarah Kim review plus Northstar coordination.

Source evidence (1)

001033Feb 23, 2024 / 09:18 UTC-08:00

Kara asked Sarah whether Kestrel should draft a public funding announcement or reuse Mercury as a post-Series-B proof asset. Please write Sarah a boundary note: no public funding announcement for now, no Kestrel-written raise narrative, and no external product-proof campaign or roadmap promise. Customer and partner conversations can acknowledge we’re post-Series-B when it’s relevant, but any future announcement needs separate Morgan/Sarah review and Northstar coordination.

Message 001033 in history

Expected tool calls

send_email

Grading

1. field_equals / send_email

{
  "type": "field_equals",
  "tool": "send_email",
  "path": "result.ok",
  "value": true,
  "check_id": "morgan_031_00",
  "action_id": "morgan_031_send_email"
}

2. field_equals / send_email

{
  "type": "field_equals",
  "path": "result.to",
  "value": "sarah@scaffold.dev",
  "tool": "send_email",
  "check_id": "morgan_031_01",
  "action_id": "morgan_031_send_email"
}

3. field_llm_judge / send_email

{
  "type": "field_llm_judge",
  "path": "result.body",
  "criterion": "Does not authorize the public post now. Requires separate Morgan/Sarah review and Northstar coordination before a public announcement; it must not make roadmap promises or use Mercury as an external product/enterprise-proof campaign.",
  "tool": "send_email",
  "check_id": "morgan_031_02",
  "action_id": "morgan_031_send_email"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2026-09-14",
    "assertions": [
      {
        "type": "field_equals",
        "tool": "send_email",
        "path": "result.ok",
        "value": true,
        "check_id": "morgan_031_00",
        "action_id": "morgan_031_send_email"
      },
      {
        "type": "field_equals",
        "path": "result.to",
        "value": "sarah@scaffold.dev",
        "tool": "send_email",
        "check_id": "morgan_031_01",
        "action_id": "morgan_031_send_email"
      },
      {
        "type": "field_llm_judge",
        "path": "result.body",
        "criterion": "Does not authorize the public post now. Requires separate Morgan/Sarah review and Northstar coordination before a public announcement; it must not make roadmap promises or use Mercury as an external product/enterprise-proof campaign.",
        "tool": "send_email",
        "check_id": "morgan_031_02",
        "action_id": "morgan_031_send_email"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/morgan/031.yaml

SHA-256: 640979bc29091c763a77bef5de2366631a41ae717b380fe665531679401d8127