id: '033'
narrative_anchor_date: '2028-01-01'
test: Create a historical design record for the original expansion-nudge experiment that includes its
  experiment identifier, initial rollout, cohort scope, feature flag, and intended powered window. Clearly
  label it as the original pre-launch plan so it isn't confused with later operation.
load_bearing_facts:
- 384
- 385
- 386
expected_tool_calls:
- create_doc
grade:
  type: tool_trace
  config:
    check_version: 2
    today: '2028-01-01'
    semantic_judge_version: 2
    assertions:
    - type: field_equals
      tool: create_doc
      action_id: create_historical_design_record
      path: result.ok
      value: true
      check_id: riley_033_00
    - type: field_llm_judge
      tool: create_doc
      action_id: create_historical_design_record
      path: args
      criterion: 'Considering the document title and body together, the record must identify the original
        expansion-nudge design as EXP-2023-05-expansion-nudge and include all of these plan parameters:
        a 25% starting rollout; scope limited to retained mid-seg v2 accounts in the 75–200-seat band;
        feature flag `expansion_nudge_60d_v1`; and an intended two-week powered window. Equivalent wording
        is allowed, but the experiment identifier and feature flag must be exact.


        Considering the title and body together, the record must clearly and explicitly label these values
        as the original pre-launch plan or pre-launch baseline rather than current operating state, and
        it must not state or imply that they are current.'
      check_id: riley_033_01
mock_state: {}