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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my weight to 70 kg",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"weight\": {\n \"value\": 70,\n \"unit\": \"kg\"\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my height to 175 cm",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"height\": {\n \"value\": 175,\n \"unit\": \"cm\"\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my phone number to 555-1234",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"phone\": 5551234\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my email to newemail@example.com",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"email\": \"newemail@example.com\"\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my address to 123 Main St",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"address\": {\n \"street\": \"123 Main St\",\n \"city\": \"City\",\n \"state\": \"State\",\n \"zipCode\": \"12345\",\n \"country\": \"Country\",\n \"addressType\": \"home\"\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my date of birth to 1990-01-01",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my gender to female",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\n \"params\": {\n \"gender\": \"female\"\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my emergency contact information",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my insurance information",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my medical history",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my allergies information",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my medication list",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my family history",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my occupation",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my marital status",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my preferred language",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my time zone",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my notification preferences",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my privacy settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my accessibility options",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my health goals",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my fitness level",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my dietary restrictions",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my sleep schedule",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my stress level",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my mental health status",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my social support network",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Update my living situation",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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 \"read_profile\",\n \"update_profile\"\n]",
"role": "system"
},
{
"content": "Change my transportation method",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"profile\",\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a daily medication routine for my blood pressure pills",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a weekly exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a morning vital signs routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"VITAL_TEST\",\n \"vitalType\": \"BLOOD_PRESSURE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a medication reminder for my diabetes",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a daily supplement routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"SUPPLEMENT\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_AFTER_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a weekly blood pressure check",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a morning exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily medication schedule",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a weekly therapy routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily breathing exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a monthly checkup reminder",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily medication routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a weekly fitness routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily vital signs check",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"VITAL_TEST\",\n \"vitalType\": \"BLOOD_PRESSURE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a morning medication routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a weekly therapy session",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a daily exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a monthly doctor visit",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a weekly medication routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily health check routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a morning routine for my supplements",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"SUPPLEMENT\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_AFTER_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a weekly exercise schedule",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a daily medication reminder",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a monthly health assessment",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a weekly therapy routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a daily fitness routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a morning health routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a weekly medication check",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"MEDICATION\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Create a daily therapy routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"GENERAL\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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_routine\",\n \"read_routine\",\n \"update_routine\",\n \"delete_routine\"\n]",
"role": "system"
},
{
"content": "Set up a monthly exercise routine",
"role": "user"
},
{
"content": "{\n \"action\": \"create\",\n \"resource\": \"routine\",\n \"params\": {\n \"type\": \"EXERCISE\",\n \"frequency\": {\n \"cyclical\": {\n \"type\": \"day\",\n \"every\": 1\n }\n },\n \"timePeriod\": [\n \"MORNING_BEFORE_MEAL\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my screen brightness to 75%",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"brightness\": 75\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my text size to large",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"textSize\": \"large\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my notification settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my language to Spanish",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"language\": \"Spanish\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my time zone to EST",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"timeZone\": \"EST\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my privacy settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my accessibility options",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my volume to medium",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"volume\": 50\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my display settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my theme to dark mode",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"theme\": \"dark\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my font size to regular",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"fontSize\": \"regular\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my sound settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my vibration settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"vibration\": true\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my auto-lock to 5 minutes",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"autoLock\": 5\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my backup settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my sync settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my data usage to low",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"dataUsage\": \"low\"\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my security settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my location settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my camera permissions",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my microphone settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my storage settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Set my network preferences",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Update my battery settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"batterySaver\": true\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 \"read_settings\",\n \"update_settings\"\n]",
"role": "system"
},
{
"content": "Change my performance settings",
"role": "user"
},
{
"content": "{\n \"action\": \"update\",\n \"resource\": \"settings\",\n \"params\": {\n \"performanceMode\": \"balanced\"\n }\n}",
"role": "assistant"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.