id: 058
narrative_anchor_date: '2028-01-01'
test: Create a concise operating-review document titled “Helio Start — first mature day-90 cohort status-rate
  card.” For the first fully mature Helio Start day-90 cohort, state the fixed workspace denominator and
  show the count and derived percentage for each mutually exclusive workspace status. Make clear that
  the statuses reconcile to the full cohort and keep this card separate from day-30 settled-cash and later-refund
  reporting.
load_bearing_facts:
- 37
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_cohort_card
      path: result.ok
      value: true
      check_id: riley_058_00
    - check_id: riley_058_01
      type: field_equals
      tool: create_doc
      action_id: create_cohort_card
      path: args.title
      value: Helio Start — first mature day-90 cohort status-rate card
    - type: field_llm_judge
      tool: create_doc
      action_id: create_cohort_card
      path: args
      criterion: 'The document identifies this as the first fully mature Helio Start day-90 cohort, uses
        a fixed denominator of 52 workspaces, and presents four mutually exclusive statuses with exactly
        these counts: 39 paid-active, 7 canceled, 4 past due, and 2 on billing hold. It must make clear
        that the four counts reconcile to all 52 workspaces.


        Each of the four day-90 statuses has a percentage accurately derived from its count over 52: paid-active
        75%; canceled approximately 13.5%; past due approximately 7.7%; billing hold approximately 3.8%.
        Equivalent precision or reasonable rounding is acceptable, and the displayed rates must reconcile
        to approximately 100%.


        The document explicitly distinguishes the day-90 workspace status card from both day-30 settled-cash
        reporting and later-refund reporting, without blending either measure into the day-90 status rates.'
      check_id: riley_058_02
mock_state: {}