Files
crewAI/tests/cassettes/test_crew_with_delegating_agents.yaml
2024-09-13 04:38:19 -05:00

902 lines
46 KiB
YAML

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: 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: Senior Writer\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: Senior Writer\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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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:
- '2789'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A6vhrx5N3jOJkskAKhKNY5a55Bjo9\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215155,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To produce an amazing 1-paragraph
draft of an article about AI Agents, I should leverage the expertise of the
Senior Writer on my team and ensure they have all the necessary context.\\n\\nAction:
Delegate work to coworker\\nAction Input: {\\\"task\\\": \\\"Produce an amazing
1-paragraph draft of an article about AI Agents\\\",\\\"context\\\": \\\"We
need to create an engaging and insightful one-paragraph draft for an article
about AI Agents. The target audience consists of tech enthusiasts and professionals
who are familiar with basic AI concepts but are looking for deeper insights.
The draft should capture the essence of what AI Agents are, their functions,
and potential impacts, while being concise and captivating.\\\",\\\"coworker\\\":
\\\"Senior Writer\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
608,\n \"completion_tokens\": 147,\n \"total_tokens\": 755,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ac511e872ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:12:37 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:
- '1658'
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:
- '29999324'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_77891dfb383a65759fc4728da06ec3a1
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
a senior writer, specialized in technology, software engineering, AI and startups.
You work as a freelancer and are now working on writing content for a new customer.\nYour
personal goal is: Write the best content about AI and AI agents.\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: Produce an amazing 1-paragraph draft of an article about AI Agents\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:\nWe need to create an engaging and insightful one-paragraph
draft for an article about AI Agents. The target audience consists of tech enthusiasts
and professionals who are familiar with basic AI concepts but are looking for
deeper insights. The draft should capture the essence of what AI Agents are,
their functions, and potential impacts, while being concise and captivating.\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:
- '1547'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A6vhue4mYu79ARj3ITYzDR7U2fMvP\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215158,\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: AI Agents are sophisticated software entities designed to autonomously
perform tasks and make decisions, often leveraging machine learning and natural
language processing to interact with their environment in a manner that mimics
human intelligence. These digital assistants are transforming industries by
optimizing workflows, enhancing user experiences, and driving innovation. From
virtual customer service representatives that handle complex queries to intelligent
personal assistants that predict user needs, the functionalities of AI Agents
are vast and continually evolving. Their capacity to analyze data, adapt to
new information, and operate efficiently without human intervention positions
them as pivotal tools in the future landscape of technology and business, promising
to unlock unprecedented levels of productivity and creativity.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 290,\n \"completion_tokens\":
139,\n \"total_tokens\": 429,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ac619ceb2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:12:40 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:
- '1755'
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:
- '29999630'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_63b6bd04fa0562528f09e4b1aade4b52
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1571'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Fri, 13 Sep 2024 08:12:41 GMT
status:
code: 200
message: OK
- 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: 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: Senior Writer\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: Senior Writer\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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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": "assistant", "content": "Thought: To produce an amazing 1-paragraph
draft of an article about AI Agents, I should leverage the expertise of the
Senior Writer on my team and ensure they have all the necessary context.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Produce an amazing 1-paragraph
draft of an article about AI Agents\",\"context\": \"We need to create an engaging
and insightful one-paragraph draft for an article about AI Agents. The target
audience consists of tech enthusiasts and professionals who are familiar with
basic AI concepts but are looking for deeper insights. The draft should capture
the essence of what AI Agents are, their functions, and potential impacts, while
being concise and captivating.\",\"coworker\": \"Senior Writer\"}\nObservation:
AI Agents are sophisticated software entities designed to autonomously perform
tasks and make decisions, often leveraging machine learning and natural language
processing to interact with their environment in a manner that mimics human
intelligence. These digital assistants are transforming industries by optimizing
workflows, enhancing user experiences, and driving innovation. From virtual
customer service representatives that handle complex queries to intelligent
personal assistants that predict user needs, the functionalities of AI Agents
are vast and continually evolving. Their capacity to analyze data, adapt to
new information, and operate efficiently without human intervention positions
them as pivotal tools in the future landscape of technology and business, promising
to unlock unprecedented levels of productivity and creativity."}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4442'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A6vhxPXYPJypPxIhQQWHxuJBArZX4\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215161,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now have an engaging and insightful
1-paragraph draft about AI Agents. To meet the criteria of a 4-paragraph article
about AI, I need to expand this into a complete article. \\n\\nAction: Delegate
work to coworker\\nAction Input: {\\\"task\\\": \\\"Expand the initial 1-paragraph
draft into a full 4-paragraph article about AI Agents\\\",\\\"context\\\": \\\"We
have already created a compelling and engaging 1-paragraph draft that highlights
the essence of AI Agents, their functions, and potential impacts. Now we need
to expand this draft into a comprehensive 4-paragraph article. The target audience
consists of tech enthusiasts and professionals who are familiar with basic AI
concepts but are looking for deeper insights. The additional paragraphs should
delve into specific examples of AI Agents in various industries, discuss the
benefits and challenges associated with their adoption, and provide a forward-looking
perspective on future developments in this field.\\\",\\\"coworker\\\": \\\"Senior
Writer\\\"}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
887,\n \"completion_tokens\": 194,\n \"total_tokens\": 1081,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ac72bb9c2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:12:43 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:
- '2121'
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:
- '29998923'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_1b4dde6928f4fb740785d1965b278710
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKcAQoQ/YtWSOJC829pFx6p50VE5hIIHJ1sSj+W9OwqClRvb2wgVXNhZ2UwATkQPN2E
ir/0F0HwyeKEir/0F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjBKKAoJdG9vbF9uYW1lEhsK
GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '223'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Fri, 13 Sep 2024 08:12:46 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
a senior writer, specialized in technology, software engineering, AI and startups.
You work as a freelancer and are now working on writing content for a new customer.\nYour
personal goal is: Write the best content about AI and AI agents.\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: Expand the initial 1-paragraph draft into a full 4-paragraph article about
AI Agents\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:\nWe have already created a compelling and
engaging 1-paragraph draft that highlights the essence of AI Agents, their functions,
and potential impacts. Now we need to expand this draft into a comprehensive
4-paragraph article. The target audience consists of tech enthusiasts and professionals
who are familiar with basic AI concepts but are looking for deeper insights.
The additional paragraphs should delve into specific examples of AI Agents in
various industries, discuss the benefits and challenges associated with their
adoption, and provide a forward-looking perspective on future developments in
this field.\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:
- '1802'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A6vi004UVp9GnD0wFSWJ5tVECHYGe\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215164,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer.\\n\\nFinal
Answer: \\n\\nArtificial Intelligence (AI) Agents are transformative entities
designed to automate processes, make decisions, and solve problems by mimicking
human intelligence. These sophisticated systems leverage machine learning, natural
language processing, and data analytics to perform tasks that traditionally
required human intervention. From personal assistants like Siri and Alexa to
complex decision-making systems in autonomous vehicles, AI Agents are increasingly
becoming integral to our daily lives, promising enhanced efficiency and productivity
across numerous domains.\\n\\nOne of the most prominent examples of AI Agents
is their application in the healthcare industry. These intelligent systems can
analyze vast amounts of medical data to assist in diagnostic processes, personalize
treatment plans, and even predict outbreaks of diseases. For instance, IBM's
Watson for Oncology utilizes AI to provide evidence-based treatment options
by analyzing large datasets of medical literature and patient records. These
capabilities not only improve the accuracy of diagnoses but also significantly
reduce the time it takes to develop effective treatment plans, ultimately enhancing
patient outcomes.\\n\\nBeyond healthcare, AI Agents are making strides in industries
such as finance, retail, and manufacturing. In the financial sector, AI-driven
chatbots and virtual assistants help manage customer inquiries, detect fraudulent
activities, and offer personalized financial advice. Retailers use AI Agents
to optimize supply chain operations, manage inventory, and enhance customer
experiences through personalized recommendations. Meanwhile, in manufacturing,
AI-powered agents are pivotal in predictive maintenance, quality control, and
optimizing production lines. These applications underscore the versatility of
AI Agents in transforming business operations and driving economic growth.\\n\\nDespite
these notable benefits, the adoption of AI Agents also presents several challenges.
Concerns about data privacy and security, ethical considerations regarding decision-making
processes, and the potential for job displacement are significant hurdles that
need to be addressed. As AI Agents become more autonomous, ensuring transparency
and accountability in their operations is critical. Looking forward, the future
of AI Agents holds immense potential. Continued advancements in AI technologies,
coupled with robust regulatory frameworks, can further unlock the capabilities
of AI Agents, making them indispensable assets in our quest for innovation and
quality of life improvements. As we navigate this evolving landscape, fostering
collaboration between AI developers, policymakers, and society at large will
be crucial in harnessing the transformative potential of AI Agents.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 333,\n \"completion_tokens\":
445,\n \"total_tokens\": 778,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ac85eb9c2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:12:50 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:
- '6418'
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:
- '29999567'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d101542d195fc38e2f0cd2ef6d36cd0d
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: 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: Senior Writer\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: Senior Writer\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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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": "assistant", "content": "Thought: To produce an amazing 1-paragraph
draft of an article about AI Agents, I should leverage the expertise of the
Senior Writer on my team and ensure they have all the necessary context.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Produce an amazing 1-paragraph
draft of an article about AI Agents\",\"context\": \"We need to create an engaging
and insightful one-paragraph draft for an article about AI Agents. The target
audience consists of tech enthusiasts and professionals who are familiar with
basic AI concepts but are looking for deeper insights. The draft should capture
the essence of what AI Agents are, their functions, and potential impacts, while
being concise and captivating.\",\"coworker\": \"Senior Writer\"}\nObservation:
AI Agents are sophisticated software entities designed to autonomously perform
tasks and make decisions, often leveraging machine learning and natural language
processing to interact with their environment in a manner that mimics human
intelligence. These digital assistants are transforming industries by optimizing
workflows, enhancing user experiences, and driving innovation. From virtual
customer service representatives that handle complex queries to intelligent
personal assistants that predict user needs, the functionalities of AI Agents
are vast and continually evolving. Their capacity to analyze data, adapt to
new information, and operate efficiently without human intervention positions
them as pivotal tools in the future landscape of technology and business, promising
to unlock unprecedented levels of productivity and creativity."}, {"role": "assistant",
"content": "Thought: I now have an engaging and insightful 1-paragraph draft
about AI Agents. To meet the criteria of a 4-paragraph article about AI, I need
to expand this into a complete article. \n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Expand the initial 1-paragraph draft into a full 4-paragraph
article about AI Agents\",\"context\": \"We have already created a compelling
and engaging 1-paragraph draft that highlights the essence of AI Agents, their
functions, and potential impacts. Now we need to expand this draft into a comprehensive
4-paragraph article. The target audience consists of tech enthusiasts and professionals
who are familiar with basic AI concepts but are looking for deeper insights.
The additional paragraphs should delve into specific examples of AI Agents in
various industries, discuss the benefits and challenges associated with their
adoption, and provide a forward-looking perspective on future developments in
this field.\",\"coworker\": \"Senior Writer\"}\nObservation: Artificial Intelligence
(AI) Agents are transformative entities designed to automate processes, make
decisions, and solve problems by mimicking human intelligence. These sophisticated
systems leverage machine learning, natural language processing, and data analytics
to perform tasks that traditionally required human intervention. From personal
assistants like Siri and Alexa to complex decision-making systems in autonomous
vehicles, AI Agents are increasingly becoming integral to our daily lives, promising
enhanced efficiency and productivity across numerous domains.\n\nOne of the
most prominent examples of AI Agents is their application in the healthcare
industry. These intelligent systems can analyze vast amounts of medical data
to assist in diagnostic processes, personalize treatment plans, and even predict
outbreaks of diseases. For instance, IBM''s Watson for Oncology utilizes AI
to provide evidence-based treatment options by analyzing large datasets of medical
literature and patient records. These capabilities not only improve the accuracy
of diagnoses but also significantly reduce the time it takes to develop effective
treatment plans, ultimately enhancing patient outcomes.\n\nBeyond healthcare,
AI Agents are making strides in industries such as finance, retail, and manufacturing.
In the financial sector, AI-driven chatbots and virtual assistants help manage
customer inquiries, detect fraudulent activities, and offer personalized financial
advice. Retailers use AI Agents to optimize supply chain operations, manage
inventory, and enhance customer experiences through personalized recommendations.
Meanwhile, in manufacturing, AI-powered agents are pivotal in predictive maintenance,
quality control, and optimizing production lines. These applications underscore
the versatility of AI Agents in transforming business operations and driving
economic growth.\n\nDespite these notable benefits, the adoption of AI Agents
also presents several challenges. Concerns about data privacy and security,
ethical considerations regarding decision-making processes, and the potential
for job displacement are significant hurdles that need to be addressed. As AI
Agents become more autonomous, ensuring transparency and accountability in their
operations is critical. Looking forward, the future of AI Agents holds immense
potential. Continued advancements in AI technologies, coupled with robust regulatory
frameworks, can further unlock the capabilities of AI Agents, making them indispensable
assets in our quest for innovation and quality of life improvements. As we navigate
this evolving landscape, fostering collaboration between AI developers, policymakers,
and society at large will be crucial in harnessing the transformative potential
of AI Agents."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '8273'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A6vi7MeQDd3V1IHvNEclASgpCKVOU\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215171,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now have a comprehensive and
high-quality 4-paragraph article about AI Agents, which aligns with the required
criteria.\\n\\nFinal Answer: \\n\\nArtificial Intelligence (AI) Agents are transformative
entities designed to automate processes, make decisions, and solve problems
by mimicking human intelligence. These sophisticated systems leverage machine
learning, natural language processing, and data analytics to perform tasks that
traditionally required human intervention. From personal assistants like Siri
and Alexa to complex decision-making systems in autonomous vehicles, AI Agents
are increasingly becoming integral to our daily lives, promising enhanced efficiency
and productivity across numerous domains.\\n\\nOne of the most prominent examples
of AI Agents is their application in the healthcare industry. These intelligent
systems can analyze vast amounts of medical data to assist in diagnostic processes,
personalize treatment plans, and even predict outbreaks of diseases. For instance,
IBM's Watson for Oncology utilizes AI to provide evidence-based treatment options
by analyzing large datasets of medical literature and patient records. These
capabilities not only improve the accuracy of diagnoses but also significantly
reduce the time it takes to develop effective treatment plans, ultimately enhancing
patient outcomes.\\n\\nBeyond healthcare, AI Agents are making strides in industries
such as finance, retail, and manufacturing. In the financial sector, AI-driven
chatbots and virtual assistants help manage customer inquiries, detect fraudulent
activities, and offer personalized financial advice. Retailers use AI Agents
to optimize supply chain operations, manage inventory, and enhance customer
experiences through personalized recommendations. Meanwhile, in manufacturing,
AI-powered agents are pivotal in predictive maintenance, quality control, and
optimizing production lines. These applications underscore the versatility of
AI Agents in transforming business operations and driving economic growth.\\n\\nDespite
these notable benefits, the adoption of AI Agents also presents several challenges.
Concerns about data privacy and security, ethical considerations regarding decision-making
processes, and the potential for job displacement are significant hurdles that
need to be addressed. As AI Agents become more autonomous, ensuring transparency
and accountability in their operations is critical. Looking forward, the future
of AI Agents holds immense potential. Continued advancements in AI technologies,
coupled with robust regulatory frameworks, can further unlock the capabilities
of AI Agents, making them indispensable assets in our quest for innovation and
quality of life improvements. As we navigate this evolving landscape, fostering
collaboration between AI developers, policymakers, and society at large will
be crucial in harnessing the transformative potential of AI Agents.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1520,\n \"completion_tokens\":
463,\n \"total_tokens\": 1983,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26acb41c012ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:12:56 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:
- '4802'
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:
- '29997979'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 4ms
x-request-id:
- req_dcf51be12093a8d2787bf6475a781c52
http_version: HTTP/1.1
status_code: 200
version: 1