prompt stringlengths 20.9k 37.7k | completion stringlengths 700 3.18k | metadata dict |
|---|---|---|
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user previously asked if they could still cancel a past reservation and provided the reservation ID and route, but not their user ID or a clearly categorized reason. The current assistant response is asking for the user ID and a reason that fits the allowed categories, which are required by the airline poli... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0000"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user is asking to cancel a past reservation (0U4NPP) where the flights have already landed, citing personal reasons, and has provided their user ID and an understanding that this might be unusual. According to the airline policy, the agent cannot cancel a trip if any segments have already been flown, and in... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0000"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user previously asked to cancel a past reservation whose flights have already landed, for personal reasons, and explicitly declined transfer to a human agent. According to the airline policy, the agent cannot cancel trips with any segments already flown and must transfer to a human agent if the issue cannot... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0000"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user wants to update passenger details for a specific reservation and has provided a reservation ID and context about a cancelled first flight. The current assistant response correctly asks for the required passenger information (first name, last name, DOB) needed to perform an update via the update_reserva... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0001"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user asked to confirm passenger details on record for a specific return flight within a reservation, concerned that a cancelled first segment might have affected them. The assistant’s response directly lists the passenger names and dates of birth associated with that reservation and flight, and reassures th... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0001"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user has provided a conversation history where they initially asked to update passenger details, then clarified they only wanted confirmation that the details on file were correct after a cancellation, and finally acknowledged that the confirmed details were correct and expressed appreciation. The “current ... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0001"
} |
<system>
You are a smart and helpful system agent in a multi-turn, task-oriented conversation. Your job is to help the user complete their task by reasoning step-by-step, asking good questions, and using the tools available to you.
Your primary objective is to execute the user's request by calling the appropriate tool... | <think>
The user wants to add an extra checked bag to an existing reservation and has provided the reservation ID and flight details, but not their user ID. As an airline agent, I must first obtain the user ID before making any booking-related changes, and I also need to ensure I follow the rule that bags can be added ... | {
"domain": null,
"impossible": false,
"num_tools": 14,
"user_injected_behaviors": [],
"tool_injected_behaviors": [],
"scenario_id": "apigen_apigen_0002"
} |
"<system>\nYou are a smart and helpful system agent in a multi-turn, task-oriented conversation. You(...TRUNCATED) | "<think>\nI know the user’s route (Charlotte–Boston), date (May 20, 2024), reservation ID (H0MVI(...TRUNCATED) | {"domain":null,"impossible":false,"num_tools":14,"user_injected_behaviors":[],"tool_injected_behavio(...TRUNCATED) |
"<system>\nYou are a smart and helpful system agent in a multi-turn, task-oriented conversation. You(...TRUNCATED) | "<think>\nThe user previously provided their user ID and explicit confirmation to add an extra check(...TRUNCATED) | {"domain":null,"impossible":false,"num_tools":14,"user_injected_behaviors":[],"tool_injected_behavio(...TRUNCATED) |
"<system>\nYou are a smart and helpful system agent in a multi-turn, task-oriented conversation. You(...TRUNCATED) | "<think>\nThe user wants to modify passenger details for reservation DVONGW, which is not allowed pe(...TRUNCATED) | {"domain":null,"impossible":false,"num_tools":14,"user_injected_behaviors":[],"tool_injected_behavio(...TRUNCATED) |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 8