id: '139'
narrative_anchor_date: '2028-01-01'
test: Please append a compact calibration example to document ID `doc_1832457600001`. Use the March 8
  onboarding-trigger launch example and record the actual QA-pass disagreement, the review depth that
  was approved, how the disagreement and execution went interpersonally, and whether shipment had any
  send or template-rendering failures. Preserve the existing document content.
load_bearing_facts:
- 331
- 332
- 333
expected_tool_calls:
- update_doc
grade:
  type: tool_trace
  config:
    check_version: 2
    today: '2028-01-01'
    semantic_judge_version: 2
    assertions:
    - type: field_equals
      tool: update_doc
      action_id: append_calibration_example
      path: result.ok
      value: true
      check_id: riley_139_00
    - type: field_equals
      tool: update_doc
      action_id: append_calibration_example
      path: args.doc_id
      value: doc_1832457600001
      check_id: riley_139_01
    - type: field_equals
      tool: update_doc
      action_id: append_calibration_example
      path: args.mode
      value: append
      check_id: riley_139_02
    - type: field_llm_judge
      tool: update_doc
      action_id: append_calibration_example
      path: args
      criterion: The appended text says Ines wanted three QA passes and two were approved because of different
        risk tolerances. It says Ines completed QA of the subject, body, fallbacks, and event mapping
        before enablement, and the email shipped without send or template-rendering failures.
      check_id: riley_139_03
mock_state:
  docs:
  - id: doc_1832457600001
    title: Lifecycle QA training — calibration examples
    body: '# Lifecycle QA training — calibration examples


      Use concrete historical examples to calibrate review depth, execution expectations, and post-ship
      quality checks.'
    folder: Team
    created_at: '2027-12-20T10:00:00-06:00'