Dataset Viewer
messages
listlengths 3
3
|
|---|
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to create an appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you book an appointment as I have a headache",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"symptoms\": \"headache\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Create an appointment for me tomorrow",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.tomorrow()\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to book an appointment with my doctor at 2:30 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.today().setTime('14:30')\",\n \"endDate\": \"date.today().setTime('15:00')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule an appointment for me this Thursday, I have a cold",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"symptoms\": \"cold\",\n \"startDate\": \"date.nextWeekday('thursday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Book an appointment on October 12, at 2:30 PM, I want to discuss my headache",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"symptoms\": \"headache\",\n \"startDate\": \"date.today().setTime('14:30')\",\n \"endDate\": \"date.today().setTime('15:00')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to see a doctor for my fever",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you schedule me for next Monday morning?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('monday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to book a consultation for my back pain",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"symptoms\": \"pain\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule me for tomorrow afternoon",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.tomorrow().setTime('14:00')\",\n \"endDate\": \"date.tomorrow().setTime('14:30')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need an appointment for my annual checkup",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Book me for this Friday at 3 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('friday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to see the doctor about my cough",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule an appointment for next week",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.addWeeks(1)\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to book a follow-up appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you schedule me for this evening?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want an appointment for my knee pain",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Book me for tomorrow morning at 9 AM",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.tomorrow().setTime('09:00')\",\n \"endDate\": \"date.tomorrow().setTime('09:30')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to see a specialist",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule me for this weekend",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('saturday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Book an appointment for 10:00 AM tomorrow",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.today().setTime('10:00')\",\n \"endDate\": \"date.today().setTime('10:30')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to schedule for 2:30 PM today",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.today().setTime('14:30')\",\n \"endDate\": \"date.today().setTime('15:00')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you book me for 4:00 PM this Friday?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('friday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule me for 8:00 AM next Monday",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('monday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need an appointment at 11:30 AM",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Book me for 3:15 PM tomorrow",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.tomorrow()\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to schedule for 1:00 PM today",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.today()\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you book me for 9:30 AM this Wednesday?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('wednesday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Schedule me for 5:00 PM next Thursday",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('thursday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need an appointment at 12:00 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I have a severe headache and need to see a doctor",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I'm experiencing chest pain and need urgent care",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I have a high fever and feel terrible",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I'm having breathing difficulties",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I have severe stomach pain",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I'm experiencing dizziness and nausea",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I have a persistent cough",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I'm having vision problems",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I have joint pain and stiffness",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I'm experiencing anxiety and panic attacks",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to change my appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you add 'headache' as a symptom for my upcoming appointment?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Re-schedule my appointment to 10:00 AM",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.today().setTime('10:00')\",\n \"endDate\": \"date.today().setTime('10:30')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Change the time for my appointment tomorrow to 3:00 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n },\n \"updates\": {\n \"startDate\": \"date.tomorrow().setTime('15:00')\",\n \"endDate\": \"date.tomorrow().setTime('15:30')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to reschedule my appointment to next week",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.addWeeks(1)\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you change my appointment from tomorrow to Friday?",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n },\n \"updates\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to update my appointment time to 2:00 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {\n \"startDate\": \"date.today().setTime('14:00')\",\n \"endDate\": \"date.today().setTime('14:30')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you add my fever symptoms to my appointment?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to move my appointment to next month",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addMonths(1)\",\n \"endDate\": \"date.addMonths(2)\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you change my appointment to the morning?",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to update my appointment with new symptoms",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you reschedule my appointment for this evening?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to change my appointment date",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you update my appointment to include my cold symptoms?",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {},\n \"updates\": {\n \"symptoms\": \"cold\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to move my appointment to tomorrow",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you delete my appointment?",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to cancel my appointment tomorrow",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Delete my appointment at 11 AM",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('11:00')\",\n \"endDate\": \"date.today().setTime('11:30')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Cancel my appointment on October 26, at 10:00 AM",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('10:00')\",\n \"endDate\": \"date.today().setTime('10:30')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to cancel my appointment for next week",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addWeeks(1)\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you remove my appointment for tomorrow?",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to cancel my 3 PM appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('15:00')\",\n \"endDate\": \"date.today().setTime('15:30')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Delete my appointment scheduled for Friday",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('friday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to cancel my morning appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you remove my appointment for next Monday?",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.nextWeekday('monday')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to cancel my appointment with the specialist",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Delete my appointment for this afternoon",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I need to cancel my follow-up appointment",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you remove my appointment for tomorrow morning?",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "I want to cancel my appointment for next month",
"role": "user"
},
{
"content": "{\n \"action\": \"delete\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addMonths(1)\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "What are my upcoming appointments",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have any appointment on Thursday?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.nextWeekday('thursday')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Show me the details for my appointment on Friday, 12:30 PM",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.nextWeekday('friday').setTime('12:30')\",\n \"endDate\": \"date.nextWeekday('friday').setTime('13:00')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have any upcoming appointments?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have an appointment tomorrow?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Is there a consultation scheduled this Monday?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {\n \"startDate\": \"date.nextWeekday('monday')\"\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you check if I have an appointment next week?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addWeeks(1)\",\n \"endDate\": \"date.addWeeks(2)\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "How many upcoming appointments do I have?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you show me all my scheduled appointments?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "What appointments do I have this week?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.startOfWeek()\",\n \"endDate\": \"date.endOfWeek()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have any appointments today?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Show me my appointments for next month",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addMonths(1)\",\n \"endDate\": \"date.addMonths(2)\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "What time is my appointment tomorrow?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.tomorrow()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have any appointments with the cardiologist?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you show me my appointment history?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "What appointments do I have scheduled?",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"appointment\",\n \"params\": {}\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Do I have any morning appointments?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('06:00')\",\n \"endDate\": \"date.today().setTime('12:00')\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Show me my appointments for this weekend",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.startOfWeek()\",\n \"endDate\": \"date.endOfWeek()\"\n }\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "What specialist appointments do I have?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"create_appointment\",\n \"read_appointment\",\n \"update_appointment\",\n \"delete_appointment\"\n]",
"role": "system"
},
{
"content": "Can you list all my upcoming visits?",
"role": "user"
},
{
"content": "{\n \"action\": \"read\",\n \"resource\": \"appointment\",\n \"params\": {\n \"filter\": {}\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Execute blood pressure and heart rate tests",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Run a complete vital signs check",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"TEMPERATURE\",\n \"SPO2\",\n \"BLOOD_GLUCOSE\",\n \"ECG\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Take my temperature and blood pressure",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"TEMPERATURE\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Perform heart rate and oxygen saturation tests",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\",\n \"SPO2\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Execute ECG and blood pressure measurements",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"ECG\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Run all available vital tests",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"TEMPERATURE\",\n \"SPO2\",\n \"BLOOD_GLUCOSE\",\n \"ECG\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Take my vitals including temperature",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Perform blood glucose and heart rate tests",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\",\n \"BLOOD_GLUCOSE\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Execute stethoscope and otoscope examinations",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"STETHOSCOPE\",\n \"OTOSCOPE\"\n ]\n }\n}",
"role": "assistant"
}
] |
[
{
"content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create|read|update|delete|execute|send|aggregate\",\n \"resource\": \"appointment|message|profile|routine|settings|vitals|records|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]",
"role": "system"
},
{
"content": "Run blood pressure, heart rate, and temperature tests",
"role": "user"
},
{
"content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"TEMPERATURE\"\n ]\n }\n}",
"role": "assistant"
}
] |
End of preview. Expand
in Data Studio
Healthcare API Tool Calling Dataset
Dataset Description
This dataset contains 650+ examples of healthcare API tool calling responses in JSON format. Each example includes:
- query: Natural language user request
- plan: JSON response following healthcare API specification
- tools: List of required tools for the response
Dataset Structure
{
"query": "I want to create an appointment",
"plan": {
"action": "create",
"resource": "appointment",
"params": {}
},
"tools": ["create_appointment", "read_appointment", "update_appointment", "delete_appointment"]
}
Resources Covered
- Appointments: Create, read, update, delete medical appointments
- Vitals: Execute, read, delete, aggregate vital signs
- Messages: Send text and media messages
- Profiles: Read and update user profiles
- Routines: Create and manage health routines
- Settings: Update system settings
- Records: Manage medical records
- Preferences: Update user preferences
Key Features
- Utility Functions: All dates/times use proper utility functions (date.tomorrow(), date.today().setTime(), etc.)
- JSON Compliance: Follows exact healthcare API specification
- Comprehensive Coverage: 650+ examples across all resource types
- Real-world Scenarios: Based on actual healthcare use cases
Usage
This dataset is designed for training healthcare API tool calling models. Each example demonstrates:
- Natural language understanding
- JSON response generation
- Tool selection and parameter mapping
- Healthcare domain knowledge
Citation
If you use this dataset, please cite:
@dataset{healthcare_api_tool_calling,
title={Healthcare API Tool Calling Dataset},
author={Your Name},
year={2024},
url={https://huggingface.co/datasets/your-username/healthcare-api-tool-calling}
}
License
MIT License - see LICENSE file for details.
- Downloads last month
- 33