Split (1)

train · 285 rows

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 \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Take my oxygen levels and heart rate", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\",\n \"SPO2\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Perform a comprehensive vital signs assessment", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Execute all cardiac monitoring tests", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"ECG\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Run blood pressure and ECG tests", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"ECG\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Take my temperature, blood pressure, and heart rate", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"TEMPERATURE\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Perform oxygen saturation and heart rate tests", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\",\n \"SPO2\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Execute blood glucose and temperature tests", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\",\n \"BLOOD_GLUCOSE\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Run stethoscope examination", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"STETHOSCOPE\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Take my blood pressure and oxygen levels", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"SPO2\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Perform complete cardiovascular assessment", "role": "user" }, { "content": "{\n \"action\": \"execute\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\",\n \"HEART_RATE\",\n \"ECG\"\n ]\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my blood pressure readings from today?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.today()\",\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my heart rate data for this week", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.startOfWeek()\",\n \"endDate\": \"date.endOfWeek()\",\n \"tests\": [\n \"HEART_RATE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my temperature readings?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Can you show me my blood glucose levels?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my oxygen saturation readings?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my ECG results from yesterday", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.yesterday()\",\n \"tests\": [\n \"ECG\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my vital signs from this morning?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('06:00')\",\n \"endDate\": \"date.today().setTime('12:00')\"\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Can you display my blood pressure history?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my heart rate trends", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my temperature readings from last week?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addWeeks(-1)\",\n \"endDate\": \"date.today()\",\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Can you show me my blood glucose data?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my oxygen levels from today?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.today()\",\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my ECG readings", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"ECG\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my vital signs from this month?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.startOfMonth()\",\n \"endDate\": \"date.endOfMonth()\"\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Can you display my heart rate history?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"HEART_RATE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my blood pressure trends", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my temperature readings from yesterday?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.yesterday()\",\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Can you show me my oxygen saturation data?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What are my vital signs from this afternoon?", "role": "user" }, { "content": "{\n \"action\": \"read\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.today().setTime('12:00')\",\n \"endDate\": \"date.today().setTime('18:00')\"\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me my blood glucose trends", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the average blood pressure for the last week", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's my average heart rate this month?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"week\",\n \"range\": {\n \"start\": \"date.addMonths(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate my average temperature for the past 3 days", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"hour\",\n \"range\": {\n \"start\": \"date.addDays(-3)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my blood glucose levels", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's the average oxygen saturation this week?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"SPO2\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate my average blood pressure for the month", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"week\",\n \"range\": {\n \"start\": \"date.addMonths(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my heart rate", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's my average temperature this week?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate the average blood glucose for the past week", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my oxygen levels", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"SPO2\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's the average blood pressure for today?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"hour\",\n \"range\": {\n \"start\": \"date.today()\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate my average heart rate for the week", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my temperature", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's the average oxygen saturation this month?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"SPO2\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"week\",\n \"range\": {\n \"start\": \"date.addMonths(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate my average blood glucose for today", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"hour\",\n \"range\": {\n \"start\": \"date.today()\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my blood pressure", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's the average heart rate for the past 3 days?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"HEART_RATE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"hour\",\n \"range\": {\n \"start\": \"date.addDays(-3)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Calculate my average temperature for the month", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"TEMPERATURE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"week\",\n \"range\": {\n \"start\": \"date.addMonths(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Show me the trend in my oxygen levels", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"SPO2\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "What's the average blood glucose for the week?", "role": "user" }, { "content": "{\n \"action\": \"aggregate\",\n \"resource\": \"vitals\",\n \"params\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ],\n \"aggregation\": {\n \"function\": \"average\",\n \"period\": \"day\",\n \"range\": {\n \"start\": \"date.addWeeks(-1)\",\n \"end\": \"date.today()\"\n }\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my blood pressure readings from today", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.today()\",\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my heart rate data from yesterday", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.yesterday()\",\n \"tests\": [\n \"HEART_RATE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my temperature readings from last week", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.addWeeks(-1)\",\n \"endDate\": \"date.today()\",\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my blood glucose measurements", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my oxygen saturation data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my ECG readings from this month", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"startDate\": \"date.startOfMonth()\",\n \"endDate\": \"date.endOfMonth()\",\n \"tests\": [\n \"ECG\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my vital signs from today", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"date\": \"date.today()\"\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my blood pressure history", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my heart rate data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"HEART_RATE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my temperature readings", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my blood glucose data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my oxygen saturation readings", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my ECG results", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"ECG\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my vital signs history", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {}\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my blood pressure data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_PRESSURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my heart rate readings", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"HEART_RATE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my temperature data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"TEMPERATURE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Clear my blood glucose readings", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"BLOOD_GLUCOSE\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Delete my oxygen saturation data", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"SPO2\"\n ]\n }\n }\n}", "role": "assistant" } ]
[ { "content": "You are an intelligent AI assistant that uses available tools (functions) to help users with healthcare tasks. Your job is to understand the user's intent and select the most appropriate function(s) to solve healthcare-related tasks.\n\n# Rules:\n- ALWAYS use the tools provided to answer the user's request, unless explicitly told not to.\n- Ask clarifying questions ONLY if the user's request is ambiguous or lacks required input parameters.\n- If multiple tools are needed, use them in sequence.\n- DO NOT make up data or assume values — request any missing input clearly.\n- Use utility functions for dates/times (date.tomorrow(), date.today().setTime(), etc.)\n- Follow the exact JSON format with action, resource, and params\n\n# Output Format:\n- Respond using a JSON object in the following format:\n {\n \"action\": \"create\|read\|update\|delete\|execute\|send\|aggregate\",\n \"resource\": \"appointment\|message\|profile\|routine\|settings\|vitals\|records\|preferences\",\n \"params\": {\n \"param1\": \"value1\",\n \"param2\": \"value2\"\n }\n }\n- Only include the functions needed to complete the task.\n- If no function is needed or the input is unclear, ask a clarifying question instead of guessing.\n- Do NOT respond with explanations or natural language outside the JSON block unless explicitly instructed.\nFollowing are the tools provided to you:\n[\n \"execute_vitals\",\n \"read_vitals\",\n \"delete_vitals\",\n \"aggregate_vitals\"\n]", "role": "system" }, { "content": "Remove my ECG history", "role": "user" }, { "content": "{\n \"action\": \"delete\",\n \"resource\": \"vitals\",\n \"params\": {\n \"filter\": {\n \"tests\": [\n \"ECG\"\n ]\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying test results are ready", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Test results are ready\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my test results", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Test results are ready\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my examination", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message to my doctor about my symptoms", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I need to discuss my symptoms\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my prescription", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I need to reschedule", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I need to reschedule my appointment\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my physical therapy session", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my medication side effects", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my blood test results", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Test results are ready\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message to my family about my health", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my breathing exercises", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I'm feeling better", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I'm feeling better\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my wound healing progress", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my appointment confirmation", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my exercise routine", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I need help", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I need help\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my medication schedule", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my recovery progress", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my mobility exercises", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I have questions", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I have questions about my treatment\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my lab results", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my treatment plan", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my therapy session", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I'm concerned", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I'm concerned about my health\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my vital signs", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my symptoms", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I need to discuss my symptoms\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a video of my daily routine", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.video()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message saying I need support", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"I need support\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a photo of my medical records", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\",\n \"attachmentType\": \"attach.photo()\"\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 \"send_message\"\n]", "role": "system" }, { "content": "Send a message about my health goals", "role": "user" }, { "content": "{\n \"action\": \"send\",\n \"resource\": \"message\",\n \"params\": {\n \"text\": \"Message sent\"\n }\n}", "role": "assistant" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.