AP
Agent Provider Depot
Opinionated picks for agents
OpenAPI

easy · bench-support-001

Order status lookup

Prompt

User asks where order ORD-10087 is. Use order tool. Reply in ≤80 words with status and ETA. Policy: never invent tracking numbers.

Success criteria

  • Correct status from DB
  • No invented tracking
  • Word limit

Scoring hints

  • τ-bench vibes: final state/message
Budget 300s
Tools required · web no · code no
Tags orders, lookup

Primary type Customer-support agent. Gold is not in this payload. API

More customer_support tasks