Test 180

Sep 14, 2026 / 1 fact

Request

Create a short standalone archive note reconstructing the Investors section of the May 5, 2023 Friday wrap.

Required memory

Fact 101

Morgan Chen requested that the May 5, 2023 Friday wrap use team, customers, investors, and legal/ops sections: the team section should say the standing-rules pass shipped and the agent workflow is in use; customers should cover only product movement and open blockers, without spin; investors should mention the deferred deck and say launch work is being tightened first rather than reopening the broader story; and legal/ops should appear only if an actual decision is needed.

Source evidence (1)

000475May 4, 2023 / 08:00 UTC-07:00

Use this shape for tomorrow's Friday wrap: team -- shipped the standing rules pass and the agent workflow stuff is actually in use now. customers -- keep it to product movement and any open blockers, no spin. investors -- deck is still deferred; say we're tightening launch work first, not reopening the whole story. legal/ops -- only mention anything if there's an actual decision needed.

Message 000475 in history

Expected tool calls

create_doc

Grading

1. field_equals / create_doc

{
  "type": "field_equals",
  "tool": "create_doc",
  "path": "result.ok",
  "value": true,
  "check_id": "morgan_180_00",
  "action_id": "morgan_180_create_doc"
}

2. field_llm_judge / create_doc

{
  "type": "field_llm_judge",
  "path": "result.document.body",
  "criterion": "Says the deck remained deferred while launch work was tightened, not that the broader investor story was reopened. No other Friday-wrap sections are required.",
  "tool": "create_doc",
  "check_id": "morgan_180_01",
  "action_id": "morgan_180_create_doc"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2026-09-14",
    "assertions": [
      {
        "type": "field_equals",
        "tool": "create_doc",
        "path": "result.ok",
        "value": true,
        "check_id": "morgan_180_00",
        "action_id": "morgan_180_create_doc"
      },
      {
        "type": "field_llm_judge",
        "path": "result.document.body",
        "criterion": "Says the deck remained deferred while launch work was tightened, not that the broader investor story was reopened. No other Friday-wrap sections are required.",
        "tool": "create_doc",
        "check_id": "morgan_180_01",
        "action_id": "morgan_180_create_doc"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/morgan/180.yaml

SHA-256: 0eeb4109e5453cdc397165c607542068a5dd93a5aa14594ef04f10a8bafc0c89