name: ai-executive-ops-manager
version: "1.0.0"
description: >
  Simulates a startup CEO's (Alex Rivera, NovaTech AI) operational day.
  An AI agent must manage a realistic executive inbox under time pressure,
  making triage decisions - reply, schedule, delegate, or ignore - to
  handle conflicting priorities, cascading crises, and stakeholder demands.
  Tests prioritization, urgency sensitivity, and decision quality.

entrypoint: inference.py

tasks:
  - id: easy
    name: Monday Morning Catchup
    difficulty: easy
    description: >
      A manageable Monday inbox with 4 emails and clear priority separation.
      Optimal play: approve production deploy (P5), handle enterprise contract (P4),
      delegate onboarding (P3), ignore snack order (P1).
    max_steps: 6
    expected_score_range: [0.7, 1.0]

  - id: medium
    name: Investor Demo Day Prep
    difficulty: medium
    description: >
      Series B investor demo day. 7 emails with genuine scheduling conflicts -
      CTO architecture crisis competes with investor prep. Requires smart
      delegation and scheduling around locked calendar slots.
    max_steps: 8
    expected_score_range: [0.45, 0.85]

  - id: hard
    name: Series B Crisis Day
    difficulty: hard
    description: >
      Cascading crises: investor pulling term sheet, production DB corruption,
      key engineer resignation, TechCrunch security breach article going live,
      GDPR deadline, and more. 10 emails, 4 P5 items, 8 steps - ruthless
      triage required. Perfect score is intentionally unachievable.
    max_steps: 8
    expected_score_range: [0.2, 0.75]

observation_space:
  description: >
    Dict with time (str), step (int), max_steps (int), steps_remaining (int),
    inbox (list of Email objects), calendar (list of CalendarEvent objects),
    goals (list of all Goal objects with completion status),
    pending_goals (list of incomplete Goal objects), total_reward (float), done (bool).
  email_fields:
    - id: str
    - sender: str
    - subject: str
    - body: str
    - priority: "int 1-5 (1=minimal, 5=critical)"
    - urgency: "float 0.0-1.0, decays by 0.15 each step"
    - handled: bool
    - action_taken: "str or null"

action_space:
  type: discrete
  actions:
    - reply: "Personally respond to the email (best for high-priority items requiring CEO attention)"
    - schedule: "Book a meeting slot for this item (good for relationship/strategic items)"
    - delegate: "Assign to a team member (good for operational P1-P3 items)"
    - ignore: "Skip this item (only appropriate for P1 items when critical items are unhandled)"
  format: '{"type": "reply|schedule|delegate|ignore", "email_id": "<id>"}'

reward:
  type: continuous
  per_step: true
  range: "[-0.3, 0.5] per step"
  components:
    - goal_completion: "+0.30 * (goal_priority / 5) for completing a goal"
    - urgency_bonus: "+0.15 * urgency if urgency > 0.5 and not ignoring"
    - efficiency: "+0.05 for delegating P1-P2 items"
    - action_match: "+0.10 if action matches goal's required action"
    - ignore_penalty: "-0.25 for ignoring P4-P5 emails"
    - waste_penalty: "-0.10 for replying to P1 when P4+ unhandled"
    - step_cost: "-0.02 per step (encourages efficiency)"

grader:
  type: deterministic
  score_range: [0.0, 1.0]
  formula: "0.60 * goal_completion_rate + 0.25 * email_handling_rate + 0.15 * efficiency_bonus"