interactions: - request: body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long time CEO of a content creation agency with a Senior Writer on the team. You''re now working on a new project and want to make sure the content produced is amazing.\nYour personal goal is: Make sure the writers in your company produce amazing content.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number: ''integer'', second_number: ''integer'') - Useful for when you need to multiply two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a specific task to one of the following coworkers: Researcher\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don''t reference things but instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific question to one of the following coworkers: Researcher\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don''t reference things but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier, Delegate work to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect criteria for your final answer: the result of multiplication\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '3110' content-type: - application/json cookie: - __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ; _cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.46.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.46.0 x-stainless-raw-response: - 'true' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: content: "{\n \"id\": \"chatcmpl-A8ivxBEjq5OxAsWaiP1TTKZhYTwHB\",\n \"object\": \"chat.completion\",\n \"created\": 1726642713,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I need to use the multiplier tool to get the product of 2 and 6 in order to provide the correct answer.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\": 2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 691,\n \"completion_tokens\": 48,\n \"total_tokens\": 739,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f72c10b91a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 06:58:34 GMT Server: - cloudflare Transfer-Encoding: - chunked X-Content-Type-Options: - nosniff access-control-expose-headers: - X-Request-ID alt-svc: - h3=":443"; ma=86400 openai-organization: - crewai-iuxna1 openai-processing-ms: - '503' openai-version: - '2020-10-01' strict-transport-security: - max-age=15552000; includeSubDomains; preload x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '30000000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '29999244' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 1ms x-request-id: - req_b1986d14e22a34bd36a4cd5165859d83 http_version: HTTP/1.1 status_code: 200 - request: body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long time CEO of a content creation agency with a Senior Writer on the team. You''re now working on a new project and want to make sure the content produced is amazing.\nYour personal goal is: Make sure the writers in your company produce amazing content.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number: ''integer'', second_number: ''integer'') - Useful for when you need to multiply two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a specific task to one of the following coworkers: Researcher\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don''t reference things but instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific question to one of the following coworkers: Researcher\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don''t reference things but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier, Delegate work to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect criteria for your final answer: the result of multiplication\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the multiplier tool to get the product of 2 and 6 in order to provide the correct answer.\n\nAction: multiplier\nAction Input: {\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '3353' content-type: - application/json cookie: - __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ; _cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.46.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.46.0 x-stainless-raw-response: - 'true' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: content: "{\n \"id\": \"chatcmpl-A8ivynwPprr9hBWIZv5U2YlMN0Sia\",\n \"object\": \"chat.completion\",\n \"created\": 1726642714,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 747,\n \"completion_tokens\": 14,\n \"total_tokens\": 761,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f72c63d97a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 06:58:35 GMT Server: - cloudflare Transfer-Encoding: - chunked X-Content-Type-Options: - nosniff access-control-expose-headers: - X-Request-ID alt-svc: - h3=":443"; ma=86400 openai-organization: - crewai-iuxna1 openai-processing-ms: - '280' openai-version: - '2020-10-01' strict-transport-security: - max-age=15552000; includeSubDomains; preload x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '30000000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '29999193' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 1ms x-request-id: - req_27ac32222acd4a7bec99737282f3d664 http_version: HTTP/1.1 status_code: 200 - request: body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number: ''integer'', second_number: ''integer'') - Useful for when you need to multiply two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis is the expect criteria for your final answer: the result of multiplication\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\n12\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1791' content-type: - application/json cookie: - __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ; _cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.46.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.46.0 x-stainless-raw-response: - 'true' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: content: "{\n \"id\": \"chatcmpl-A8ivzfGw03kAzIgtRA0gBip6vokxr\",\n \"object\": \"chat.completion\",\n \"created\": 1726642715,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: The task is to determine the result of multiplying 2 by 6. I will use the multiplier tool to perform the multiplication.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\": 2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 365,\n \"completion_tokens\": 49,\n \"total_tokens\": 414,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f72c9ff6ca67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 06:58:35 GMT Server: - cloudflare Transfer-Encoding: - chunked X-Content-Type-Options: - nosniff access-control-expose-headers: - X-Request-ID alt-svc: - h3=":443"; ma=86400 openai-organization: - crewai-iuxna1 openai-processing-ms: - '619' openai-version: - '2020-10-01' strict-transport-security: - max-age=15552000; includeSubDomains; preload x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '30000000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '29999573' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_bbae78c1d6440f1018e95fe8888f046e http_version: HTTP/1.1 status_code: 200 - request: body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number: ''integer'', second_number: ''integer'') - Useful for when you need to multiply two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis is the expect criteria for your final answer: the result of multiplication\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\n12\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role": "user", "content": "Thought: The task is to determine the result of multiplying 2 by 6. I will use the multiplier tool to perform the multiplication.\n\nAction: multiplier\nAction Input: {\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '2051' content-type: - application/json cookie: - __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ; _cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.46.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.46.0 x-stainless-raw-response: - 'true' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: content: "{\n \"id\": \"chatcmpl-A8iw0xtv32J1wd2Kzi6Qc6n1wz2yq\",\n \"object\": \"chat.completion\",\n \"created\": 1726642716,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 422,\n \"completion_tokens\": 14,\n \"total_tokens\": 436,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f72cfe9d7a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 06:58:36 GMT Server: - cloudflare Transfer-Encoding: - chunked X-Content-Type-Options: - nosniff access-control-expose-headers: - X-Request-ID alt-svc: - h3=":443"; ma=86400 openai-organization: - crewai-iuxna1 openai-processing-ms: - '248' openai-version: - '2020-10-01' strict-transport-security: - max-age=15552000; includeSubDomains; preload x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '30000000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '29999517' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_2d3b621507ece90414a04ac99d228560 http_version: HTTP/1.1 status_code: 200 version: 1