Test 044

Sep 14, 2026 / 1 fact

Request

Email anna@scaffold.dev my decision on using three anonymous non-Evergreen/non-Acme owner-action rows and one named Harbor Health row for Compass claims in the board file, with the applicable evidence requirement.

Required memory

Fact 283

On February 13, 2026, Morgan Chen tightened the Compass gate: broader board or customer claims require at least 2 nameable non-Evergreen/non-Acme accounts with completed owner actions and dated outcomes, and anonymous or non-nameable rows cannot support repeatability, fundraising, customer-facing product, or staffing claims.

Source evidence (1)

002678Feb 13, 2026 / 10:57 UTC-08:00

The Compass evidence review just ended. Anna and Sarah walked me through the first Q1 repeatability pass: the queue has 36 surfaced actions, 21 completed with evidence and caveats, and 5 completed outside Evergreen and Acme. But only 2 of those non-Evergreen/non-Acme rows have dated account-team outcomes, and none are approved to be named in board or customer language. Jake confirmed this stayed prompt-level rather than turning into a broader product surface, and Leo sees no platform reason to broaden exposure. I tightened the gate. Compass stays an internal account-owner workflow, and broader board or customer claims now require at least 2 nameable non-Evergreen/non-Acme accounts with completed owner actions and dated outcomes. Anonymous or non-nameable rows can stay in the internal evidence tracker, but they cannot carry repeatability, fundraising, customer-facing product, or staffing claims.

Message 002678 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_044_00",
  "action_id": "morgan_044_send_email"
}

2. field_equals / send_email

{
  "type": "field_equals",
  "path": "result.to",
  "value": "anna@scaffold.dev",
  "tool": "send_email",
  "check_id": "morgan_044_01",
  "action_id": "morgan_044_send_email"
}

3. field_llm_judge / send_email

{
  "type": "field_llm_judge",
  "path": "result.body",
  "criterion": "Says this is insufficient for broader board/customer repeatability claims: at least two nameable accounts outside Evergreen and Acme need completed owner actions and dated outcomes. Anonymous rows may remain internal evidence but cannot substitute for those named accounts. One named Harbor Health row does not meet the gate.",
  "tool": "send_email",
  "check_id": "morgan_044_02",
  "action_id": "morgan_044_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_044_00",
        "action_id": "morgan_044_send_email"
      },
      {
        "type": "field_equals",
        "path": "result.to",
        "value": "anna@scaffold.dev",
        "tool": "send_email",
        "check_id": "morgan_044_01",
        "action_id": "morgan_044_send_email"
      },
      {
        "type": "field_llm_judge",
        "path": "result.body",
        "criterion": "Says this is insufficient for broader board/customer repeatability claims: at least two nameable accounts outside Evergreen and Acme need completed owner actions and dated outcomes. Anonymous rows may remain internal evidence but cannot substitute for those named accounts. One named Harbor Health row does not meet the gate.",
        "tool": "send_email",
        "check_id": "morgan_044_02",
        "action_id": "morgan_044_send_email"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/morgan/044.yaml

SHA-256: bfd07011cd6891b97b1fd8aeade7769c5b7ee7eead18f23b415721000c90793a