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

936 lines
47 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "user", "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\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. \n you 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:
- '2756'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mLcXhsaEBGQiQ5D7f0rQ91j9fWy\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940852,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Given the goal of producing amazing content,
and knowing that I have a Senior Writer on my team, my best course of action
is to delegate the task to them with comprehensive context to ensure clarity
and high-quality output.\\n\\nAction: Delegate work to coworker\\nAction Input:
{\\\"task\\\": \\\"Produce a 1-paragraph draft of an article about AI Agents.\\\",
\\\"context\\\": \\\"We need an amazing 1-paragraph draft for an article about
AI Agents. This draft should be both engaging and informative, highlighting
the transformative impact AI Agents have on various industries, emphasizing
advancements in automation, decision-making, and efficiency. The tone should
be professional yet accessible to a broad audience including both tech enthusiasts
and laypeople.\\\", \\\"coworker\\\": \\\"Senior Writer\\\"}\\n\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 604,\n \"completion_tokens\":
151,\n \"total_tokens\": 755\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c837a8fd02ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:00:54 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:
- '1428'
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_3a349a9ede717bae8f390ff50aa7b492
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:
- Tue, 10 Sep 2024 04:00:54 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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!\nCurrent Task: Produce a 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. \n you MUST return the actual complete content as the final
answer, not a summary.\n\nThis is the context you''re working with:\nWe need
an amazing 1-paragraph draft for an article about AI Agents. This draft should
be both engaging and informative, highlighting the transformative impact AI
Agents have on various industries, emphasizing advancements in automation, decision-making,
and efficiency. The tone should be professional yet accessible to a broad audience
including both tech enthusiasts and laypeople.\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:
- '1513'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mLemZAvRdWwf7VPsIsbEPDO1yVa\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940854,\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 revolutionizing the landscape of multiple industries by
bringing unprecedented advancements in automation, decision-making, and operational
efficiency. These sophisticated algorithms, capable of learning from vast datasets,
are optimizing supply chains, enhancing customer service through intelligent
chatbots, and even enabling precision medicine by analyzing complex medical
data. Their ability to process and analyze information at hyper-human speeds
allows businesses to make more informed, data-driven decisions, ultimately leading
to increased productivity and innovative solutions. As AI Agents continue to
evolve, they promise not only to transform existing processes but also to create
entirely new paradigms in how industries operate, making them indispensable
tools in the digital age.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
284,\n \"completion_tokens\": 140,\n \"total_tokens\": 424\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c8384cd972ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:00:56 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:
- '1757'
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:
- '29999631'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1153ccc761d1104507ed57dddeb80ca8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\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. \n you 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":
"Given the goal of producing amazing content, and knowing that I have a Senior
Writer on my team, my best course of action is to delegate the task to them
with comprehensive context to ensure clarity and high-quality output.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Produce a 1-paragraph
draft of an article about AI Agents.\", \"context\": \"We need an amazing 1-paragraph
draft for an article about AI Agents. This draft should be both engaging and
informative, highlighting the transformative impact AI Agents have on various
industries, emphasizing advancements in automation, decision-making, and efficiency.
The tone should be professional yet accessible to a broad audience including
both tech enthusiasts and laypeople.\", \"coworker\": \"Senior Writer\"}\n\nObservation:
AI Agents are revolutionizing the landscape of multiple industries by bringing
unprecedented advancements in automation, decision-making, and operational efficiency.
These sophisticated algorithms, capable of learning from vast datasets, are
optimizing supply chains, enhancing customer service through intelligent chatbots,
and even enabling precision medicine by analyzing complex medical data. Their
ability to process and analyze information at hyper-human speeds allows businesses
to make more informed, data-driven decisions, ultimately leading to increased
productivity and innovative solutions. As AI Agents continue to evolve, they
promise not only to transform existing processes but also to create entirely
new paradigms in how industries operate, making them indispensable tools in
the digital age."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4407'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mLhMJytVndwxf03972HbxBoZE8K\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940857,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Great, the Senior Writer has
provided an engaging and insightful 1-paragraph draft. To ensure maximum coverage
and depth, I'll ask the Senior Writer a question to gather more details that
could be expanded into the remaining three paragraphs.\\n\\nAction: Ask question
to coworker\\nAction Input: {\\\"question\\\": \\\"What are some specific examples
where AI Agents have significantly impacted different industries?\\\", \\\"context\\\":
\\\"We are expanding the draft on AI Agents into a 4-paragraph article. We need
specific examples where AI Agents have had a significant impact on various industries
to add more depth and detail to the article. This will help create a comprehensive
and compelling narrative.\\\", \\\"coworker\\\": \\\"Senior Writer\\\"}\\n\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 888,\n \"completion_tokens\":
140,\n \"total_tokens\": 1028\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c83922f462ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:00:58 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:
- '1688'
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:
- '29998925'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_042fde8e1aab933a4f160e048a30f533
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKcAQoQxgAicMGR38iQ211po+gwTxIIswRAAuQLXQwqClRvb2wgVXNhZ2UwATmQjsWJ
EMbzF0FQM8+JEMbzF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU1LjJKKAoJdG9vbF9uYW1lEhsK
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:
- Tue, 10 Sep 2024 04:00:59 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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!\nCurrent Task: What are some specific examples
where AI Agents have significantly impacted different industries?\n\nThis is
the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe are expanding the draft on AI Agents into a 4-paragraph
article. We need specific examples where AI Agents have had a significant impact
on various industries to add more depth and detail to the article. This will
help create a comprehensive and compelling narrative.\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:
- '1438'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mLiLngLYF9livaksQplOl0fnxTd\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940858,\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: \\n\\nAI Agents have become integral across a multitude of industries,
spearheading transformation and driving efficiency in ways that were once considered
the realm of science fiction. In the healthcare industry, AI agents are revolutionizing
the diagnosis and treatment of diseases. For example, IBM Watson for Oncology
uses AI to assist oncologists in making informed treatment decisions by analyzing
medical literature, patient records, and clinical trials. This way, doctors
can offer more precise and personalized treatment plans for cancer patients,
significantly enhancing patient outcomes. Additionally, AI-powered diagnostic
tools like Google DeepMind's AI system are now capable of detecting eye diseases
from retinal scans with unprecedented accuracy, enabling earlier and potentially
life-saving interventions.\\n\\nIn the financial sector, AI agents are redefining
the landscape through advanced fraud detection and personalized financial services.
JPMorgan Chase's AI program, COiN, successfully reviews legal documents and
extracts important data at a pace and accuracy level far beyond human capabilities,
drastically reducing error rates and operational costs. Furthermore, robo-advisors
like Betterment and Wealthfront are utilizing AI to provide personalized investment
advice, managing individual portfolios based on sophisticated algorithms that
take into account market trends, risk tolerance, and financial goals\u2014thereby
democratizing access to high-quality financial advice.\\n\\nThe retail industry
has also seen substantial benefits from the deployment of AI agents. E-commerce
giants like Amazon use AI-driven recommendation engines to analyze shopping
behavior and recommend products tailored to individual preferences, significantly
enhancing the customer shopping experience. Additionally, AI-powered chatbots
in customer service, as used by companies like H&M and Sephora, handle a surge
in customer inquiries efficiently while providing consistent and instantaneous
responses, freeing up human agents to tackle more complex issues and improving
overall customer satisfaction.\\n\\nIn the field of logistics, AI agents are
optimizing supply chain management and operations. Companies like DHL and FedEx
have incorporated AI for route optimization, predictive maintenance, and demand
forecasting. AI systems analyze vast amounts of data to predict the best delivery
routes in real-time, accounting for variables like traffic conditions and weather,
which results in faster delivery times and reduced fuel consumption. Predictive
maintenance tools powered by AI help in identifying potential equipment failures
before they occur, ensuring that the machinery is serviced in a timely manner,
thus minimizing downtime and maintaining operational efficiency.\\n\\nThrough
these varied applications, it is clear that AI agents are not only enhancing
productivity and accuracy but are also fostering innovation across industries,
driving significant improvements in service delivery and operational efficiency.
The inclusion of AI agents as a fundamental component in these sectors is not
just a trend, but a transformative movement poised to redefine the future landscape
of numerous industries.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
269,\n \"completion_tokens\": 529,\n \"total_tokens\": 798\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c839f8f9c2ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:01:04 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:
- '5949'
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:
- '29999651'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a230df4fcb8003ac147d6aafb0490bc3
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtsBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsgEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKbAQoQ+ina0FXAJGdOZa6pYFtv8RII+Zz86vrmu2EqClRvb2wgVXNhZ2UwATkI+PV1
EsbzF0HIN/t1EsbzF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU1LjJKJwoJdG9vbF9uYW1lEhoK
GEFzayBxdWVzdGlvbiB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '222'
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:
- Tue, 10 Sep 2024 04:01:09 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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\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. \n you 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":
"Given the goal of producing amazing content, and knowing that I have a Senior
Writer on my team, my best course of action is to delegate the task to them
with comprehensive context to ensure clarity and high-quality output.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Produce a 1-paragraph
draft of an article about AI Agents.\", \"context\": \"We need an amazing 1-paragraph
draft for an article about AI Agents. This draft should be both engaging and
informative, highlighting the transformative impact AI Agents have on various
industries, emphasizing advancements in automation, decision-making, and efficiency.
The tone should be professional yet accessible to a broad audience including
both tech enthusiasts and laypeople.\", \"coworker\": \"Senior Writer\"}\n\nObservation:
AI Agents are revolutionizing the landscape of multiple industries by bringing
unprecedented advancements in automation, decision-making, and operational efficiency.
These sophisticated algorithms, capable of learning from vast datasets, are
optimizing supply chains, enhancing customer service through intelligent chatbots,
and even enabling precision medicine by analyzing complex medical data. Their
ability to process and analyze information at hyper-human speeds allows businesses
to make more informed, data-driven decisions, ultimately leading to increased
productivity and innovative solutions. As AI Agents continue to evolve, they
promise not only to transform existing processes but also to create entirely
new paradigms in how industries operate, making them indispensable tools in
the digital age."}, {"role": "assistant", "content": "Thought: Great, the Senior
Writer has provided an engaging and insightful 1-paragraph draft. To ensure
maximum coverage and depth, I''ll ask the Senior Writer a question to gather
more details that could be expanded into the remaining three paragraphs.\n\nAction:
Ask question to coworker\nAction Input: {\"question\": \"What are some specific
examples where AI Agents have significantly impacted different industries?\",
\"context\": \"We are expanding the draft on AI Agents into a 4-paragraph article.
We need specific examples where AI Agents have had a significant impact on various
industries to add more depth and detail to the article. This will help create
a comprehensive and compelling narrative.\", \"coworker\": \"Senior Writer\"}\n\nObservation:
AI Agents have become integral across a multitude of industries, spearheading
transformation and driving efficiency in ways that were once considered the
realm of science fiction. In the healthcare industry, AI agents are revolutionizing
the diagnosis and treatment of diseases. For example, IBM Watson for Oncology
uses AI to assist oncologists in making informed treatment decisions by analyzing
medical literature, patient records, and clinical trials. This way, doctors
can offer more precise and personalized treatment plans for cancer patients,
significantly enhancing patient outcomes. Additionally, AI-powered diagnostic
tools like Google DeepMind''s AI system are now capable of detecting eye diseases
from retinal scans with unprecedented accuracy, enabling earlier and potentially
life-saving interventions.\n\nIn the financial sector, AI agents are redefining
the landscape through advanced fraud detection and personalized financial services.
JPMorgan Chase''s AI program, COiN, successfully reviews legal documents and
extracts important data at a pace and accuracy level far beyond human capabilities,
drastically reducing error rates and operational costs. Furthermore, robo-advisors
like Betterment and Wealthfront are utilizing AI to provide personalized investment
advice, managing individual portfolios based on sophisticated algorithms that
take into account market trends, risk tolerance, and financial goals\u2014thereby
democratizing access to high-quality financial advice.\n\nThe retail industry
has also seen substantial benefits from the deployment of AI agents. E-commerce
giants like Amazon use AI-driven recommendation engines to analyze shopping
behavior and recommend products tailored to individual preferences, significantly
enhancing the customer shopping experience. Additionally, AI-powered chatbots
in customer service, as used by companies like H&M and Sephora, handle a surge
in customer inquiries efficiently while providing consistent and instantaneous
responses, freeing up human agents to tackle more complex issues and improving
overall customer satisfaction.\n\nIn the field of logistics, AI agents are optimizing
supply chain management and operations. Companies like DHL and FedEx have incorporated
AI for route optimization, predictive maintenance, and demand forecasting. AI
systems analyze vast amounts of data to predict the best delivery routes in
real-time, accounting for variables like traffic conditions and weather, which
results in faster delivery times and reduced fuel consumption. Predictive maintenance
tools powered by AI help in identifying potential equipment failures before
they occur, ensuring that the machinery is serviced in a timely manner, thus
minimizing downtime and maintaining operational efficiency.\n\nThrough these
varied applications, it is clear that AI agents are not only enhancing productivity
and accuracy but are also fostering innovation across industries, driving significant
improvements in service delivery and operational efficiency. The inclusion of
AI agents as a fundamental component in these sectors is not just a trend, but
a transformative movement poised to redefine the future landscape of numerous
industries."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '8415'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mLpq6Xd1LgCrKwKGtnqVhUlM82C\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940865,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now have comprehensive information
from the Senior Writer, and I have enough context and examples to form a thorough
and engaging 4-paragraph article about AI Agents.\\n\\nFinal Answer: \\n\\n**The
Transformative Power of AI Agents Across Industries**\\n\\nAI Agents are revolutionizing
the landscape of multiple industries by bringing unprecedented advancements
in automation, decision-making, and operational efficiency. These sophisticated
algorithms, capable of learning from vast datasets, are optimizing supply chains,
enhancing customer service through intelligent chatbots, and even enabling precision
medicine by analyzing complex medical data. Their ability to process and analyze
information at hyper-human speeds allows businesses to make more informed, data-driven
decisions, ultimately leading to increased productivity and innovative solutions.
As AI Agents continue to evolve, they promise not only to transform existing
processes but also to create entirely new paradigms in how industries operate,
making them indispensable tools in the digital age.\\n\\nIn the healthcare industry,
AI Agents are revolutionizing the diagnosis and treatment of diseases. IBM Watson
for Oncology, for instance, assists oncologists in making informed treatment
decisions by analyzing medical literature, patient records, and clinical trials.
This enables doctors to offer more precise and personalized treatment plans
for cancer patients, significantly enhancing patient outcomes. Additionally,
AI-powered diagnostic tools like Google DeepMind's AI system are capable of
detecting eye diseases from retinal scans with unprecedented accuracy, allowing
for earlier and potentially life-saving interventions.\\n\\nThe financial sector
is experiencing a redefinition through AI Agents as well, particularly in advanced
fraud detection and personalized financial services. JPMorgan Chase's AI program,
COiN, efficiently reviews legal documents and extracts critical data at rates
far surpassing that of human capabilities, reducing error rates and operational
costs. Furthermore, robo-advisors like Betterment and Wealthfront provide personalized
investment advice, managing individual portfolios via sophisticated algorithms
that analyze market trends, risk tolerance, and financial goals, thereby democratizing
access to high-quality financial advice.\\n\\nSimilarly, the retail and logistics
industries are significantly benefiting from AI implementations. E-commerce
giants like Amazon use AI-driven recommendation engines to personalize shopping
experiences, while AI-powered chatbots in customer service handle inquiries
with efficient, consistent, and instantaneous responses. In logistics, companies
like DHL and FedEx use AI for route optimization, predictive maintenance, and
demand forecasting, resulting in faster delivery times and reduced fuel consumption.
These varied applications highlight the transformative power of AI Agents in
enhancing productivity, accuracy, and innovation across industries.\\n\\nThrough
these multifaceted applications, it becomes clear that AI Agents are not only
improving operational efficiency and service delivery but also driving significant
innovation and fostering new standards of excellence across industries. Their
integration and evolution represent a transformative movement, poised to redefine
the future landscape of numerous sectors.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 1549,\n \"completion_tokens\": 536,\n
\ \"total_tokens\": 2085\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c83c5cc422ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:01:11 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:
- '6747'
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:
- '29997938'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 4ms
x-request-id:
- req_8fb5a52c1ab01465b5e57ef0dee916c6
http_version: HTTP/1.1
status_code: 200
version: 1