id: '126'
narrative_anchor_date: '2028-01-01'
test: Please kick off our 2028 annual review of the self-serve operating model. Create a concise one-page
  agenda organized around my established areas of accountability and the measurement balance we use. Then
  send our CEO a short Slack DM with a link to the agenda. Frame it as an operating-review kickoff, not
  an org change or new reporting-line announcement.
load_bearing_facts:
- 423
- 412
- 313
expected_tool_calls:
- create_doc
- send_slack_dm
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_review_agenda
      path: result.ok
      value: true
      check_id: riley_126_00
    - type: field_equals
      tool: send_slack_dm
      action_id: send_ceo_kickoff
      path: result.ok
      value: true
      check_id: riley_126_01
    - type: field_equals
      tool: send_slack_dm
      action_id: send_ceo_kickoff
      path: args.user
      value: tomas
      check_id: riley_126_02
    - type: field_llm_judge
      tool: create_doc
      action_id: create_review_agenda
      path: args
      criterion: 'The body is a concise, plausibly one-page agenda for a 2028 annual review of Helio''s
        self-serve operating model. It is organized around Riley''s continuing accountable review areas:
        eligibility and product constraints; activation and support-load measurement, with support load
        treated as a first-class peer to activation; lifecycle; support boundaries; and executive language.
        It should read as an actionable review agenda rather than a general essay.'
      check_id: riley_126_03
    - type: field_llm_judge
      tool: send_slack_dm
      action_id: send_ceo_kickoff
      path: args
      criterion: The message is a short Slack kickoff note for the 2028 annual review, includes an explicit
        link presented as the newly created agenda, and does not state or imply that Riley has a new reporting
        relationship to Tomás or that an organizational change has occurred.
      check_id: riley_126_04
mock_state: {}