interactions: - request: body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\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: Scorer\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: Scorer\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 [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: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expect criteria for your final answer: The score of the title.\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: - '3014' 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-A8izgtsPKj7ahTZyvtIi963PBeGor\",\n \"object\": \"chat.completion\",\n \"created\": 1726642944,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"To determine an appropriate score for the title \\\"The impact of AI in the future of work,\\\" I need to get an expert evaluation from Scorer.\\n\\nAction: Ask question to coworker\\nAction Input: {\\\"question\\\": \\\"Can you provide an integer score between 1-5 for the title 'The impact of AI in the future of work'?\\\", \\\"context\\\": \\\"The title to be scored is 'The impact of AI in the future of work'. I need an integer score between 1-5. The score should reflect the overall quality and relevance of the title.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\": 125,\n \"total_tokens\": 789,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f785fed68a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 07:02:25 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: - '1352' 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: - '29999268' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 1ms x-request-id: - req_91a2c46dd64b52affe2e08ba3a82b5da http_version: HTTP/1.1 status_code: 200 - request: body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task use the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Can you provide an integer score between 1-5 for the title ''The impact of AI in the future of work''?\n\nThis is the expect criteria for your final answer: Your best answer to your coworker asking you this, accounting for the context shared.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe title to be scored is ''The impact of AI in the future of work''. I need an integer score between 1-5. The score should reflect the overall quality and relevance of the title.\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: - '1226' 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-A8izhcbDp9WWxLBp3tvmdEGPExDaK\",\n \"object\": \"chat.completion\",\n \"created\": 1726642945,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 246,\n \"completion_tokens\": 15,\n \"total_tokens\": 261,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f786aea22a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 07:02:26 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: - '494' 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: - '29999712' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_b11a43ff9e5009ce1345fd561352b23b http_version: HTTP/1.1 status_code: 200 - request: body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\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: Scorer\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: Scorer\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 [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: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expect criteria for your final answer: The score of the title.\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": "To determine an appropriate score for the title \"The impact of AI in the future of work,\" I need to get an expert evaluation from Scorer.\n\nAction: Ask question to coworker\nAction Input: {\"question\": \"Can you provide an integer score between 1-5 for the title ''The impact of AI in the future of work''?\", \"context\": \"The title to be scored is ''The impact of AI in the future of work''. I need an integer score between 1-5. The score should reflect the overall quality and relevance of the title.\", \"coworker\": \"Scorer\"}\n\nObservation: 4"}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '3598' 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-A8izim0cojvqzrlLzs30KghifFmzB\",\n \"object\": \"chat.completion\",\n \"created\": 1726642946,\n \"model\": \"gpt-4o-2024-05-13\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I have obtained the score from Scorer.\\n\\nFinal Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 797,\n \"completion_tokens\": 16,\n \"total_tokens\": 813,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8c4f786fec47a67a-MIA Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 18 Sep 2024 07:02:27 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: - '417' 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: - '29999135' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 1ms x-request-id: - req_74e5d8e9e5b4dbbe82f5360c622a03a7 http_version: HTTP/1.1 status_code: 200 version: 1