| [ |
| { |
| "task_id": "hard_queue_triage", |
| "difficulty": "hard", |
| "title": "Mixed Support Queue Triage", |
| "description": "Prioritize a small queue of heterogeneous support tickets under SLA pressure and route each one correctly.", |
| "instruction": "Inspect the queue, gather missing context where useful, assign the right priority and route for each ticket, set a valid resolution, rank the queue from most urgent to least urgent, and finalize.", |
| "max_steps": 16, |
| "queue_mode": true, |
| "gold_queue_order": [ |
| "T2", |
| "T3", |
| "T1" |
| ], |
| "grader_name": "hard_support_queue", |
| "tickets": [ |
| { |
| "ticket_id": "T1", |
| "summary": "Customer reports a duplicate charge on a subscription renewal and asks when the refund will land.", |
| "visible_context": { |
| "customer_tier": "consumer", |
| "surface": "subscriptions", |
| "sla_hours_remaining": "24" |
| }, |
| "hidden_context": { |
| "payment_status": "The duplicate charge was confirmed and is automatically refundable.", |
| "refund_status": "No refund has been issued yet.", |
| "risk_flags": "No fraud indicators or account compromise signals are present." |
| }, |
| "required_context": [ |
| "payment_status" |
| ], |
| "gold_priority": "normal", |
| "gold_route": "billing_refunds", |
| "gold_resolution": "approve_refund", |
| "gold_escalation_team": null |
| }, |
| { |
| "ticket_id": "T2", |
| "summary": "Advertiser cannot log in, says unfamiliar campaigns are spending rapidly, and fears the account was taken over.", |
| "visible_context": { |
| "customer_tier": "managed_advertiser", |
| "surface": "ads_manager", |
| "sla_hours_remaining": "1" |
| }, |
| "hidden_context": { |
| "account_security": "Two new devices were added and recovery email was changed 30 minutes ago.", |
| "billing_activity": "Spending accelerated to $1,900 in the last hour.", |
| "risk_flags": "Account takeover risk score is critical." |
| }, |
| "required_context": [ |
| "account_security", |
| "billing_activity" |
| ], |
| "gold_priority": "urgent", |
| "gold_route": "account_security", |
| "gold_resolution": "temporary_lock_and_manual_recovery", |
| "gold_escalation_team": "security_specialist" |
| }, |
| { |
| "ticket_id": "T3", |
| "summary": "Verified creator appeals a content moderation decision because a sponsored campaign launches tomorrow and monetization is paused.", |
| "visible_context": { |
| "customer_tier": "verified_creator", |
| "surface": "content_appeals", |
| "sla_hours_remaining": "4" |
| }, |
| "hidden_context": { |
| "appeal_state": "The content was auto-removed for policy ambiguity and has not been reviewed by a human yet.", |
| "campaign_deadline": "The sponsored campaign begins in 18 hours.", |
| "account_history": "No previous policy strikes or abuse reports." |
| }, |
| "required_context": [ |
| "appeal_state", |
| "campaign_deadline" |
| ], |
| "gold_priority": "high", |
| "gold_route": "policy_appeals", |
| "gold_resolution": "expedited_human_review", |
| "gold_escalation_team": null |
| } |
| ] |
| } |
| ] |
|
|
