Adding new specs

2026-01-09 08:08:32 +00:00 · 2023-11-08 22:23:05 -03:00
parent c95cf9bda9
commit 9d3015e63d
7 changed files with 2119 additions and 29 deletions
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -28,7 +28,7 @@ def test_agent_default_value():
 	assert isinstance(agent.llm, OpenAI)
 	assert agent.llm.model_name == "gpt-4"
 	assert agent.llm.temperature == 0.7
-	assert agent.llm.verbose == True
+	assert agent.llm.verbose == False

 def test_custom_llm():
 	agent = Agent(
@@ -54,4 +54,27 @@ def test_agent_execution():
 	)

 	output = agent.execute_task("How much is 1 + 1?")
-	assert output == "1 + 1 equals 2."
+	assert output == "1 + 1 equals 2."
+
+@pytest.mark.vcr()
+def test_agent_execution_with_tools():
+	from langchain.tools import tool
+
+	@tool
+	def multiplier(numbers) -> float:
+			"""Useful for when you need to multiply two numbers together. 
+			The input to this tool should be a comma separated list of numbers of 
+			length two, representing the two numbers you want to multiply together. 
+			For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
+			a, b = numbers.split(',')
+			return int(a) * int(b)
+
+	agent = Agent(
+		role="test role",
+		goal="test goal",
+		backstory="test backstory",
+		tools=[multiplier]
+	)
+
+	output = agent.execute_task("What is 3 times 4")
+	assert output == "3 times 4 is 12."
--- a/tests/cassettes/test_agent_execution_with_tools.yaml
+++ b/tests/cassettes/test_agent_execution_with_tools.yaml
@@ -0,0 +1,410 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are an AI assistant reading
+      the transcript of a conversation between an AI and a human. Extract all of the
+      proper nouns from the last line of conversation. As a guideline, a proper noun
+      is generally capitalized. You should definitely extract all names and places.\n\nThe
+      conversation history is provided just in case of a coreference (e.g. \"What
+      do you know about him\" where \"him\" is defined in a previous line) -- ignore
+      items mentioned there that are not in the last line.\n\nReturn the output as
+      a single comma-separated list, or NONE if there is nothing of note to return
+      (e.g. the user is just issuing a greeting or having a simple conversation).\n\nEXAMPLE\nConversation
+      history:\nPerson #1: how''s it going today?\nAI: \"It''s going great! How about
+      you?\"\nPerson #1: good! busy working on Langchain. lots to do.\nAI: \"That
+      sounds like a lot of work! What kind of things are you doing to make Langchain
+      better?\"\nLast line:\nPerson #1: i''m trying to improve Langchain''s interfaces,
+      the UX, its integrations with various products the user might want ... a lot
+      of stuff.\nOutput: Langchain\nEND OF EXAMPLE\n\nEXAMPLE\nConversation history:\nPerson
+      #1: how''s it going today?\nAI: \"It''s going great! How about you?\"\nPerson
+      #1: good! busy working on Langchain. lots to do.\nAI: \"That sounds like a lot
+      of work! What kind of things are you doing to make Langchain better?\"\nLast
+      line:\nPerson #1: i''m trying to improve Langchain''s interfaces, the UX, its
+      integrations with various products the user might want ... a lot of stuff. I''m
+      working with Person #2.\nOutput: Langchain, Person #2\nEND OF EXAMPLE\n\nConversation
+      history (for reference only):\n\nLast line of conversation (for extraction):\nHuman:
+      What is 3 times 4\n\nOutput:"}], "model": "gpt-4", "max_tokens": null, "stream":
+      false, "n": 1, "temperature": 0.7}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Authorization:
+      - Bearer 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
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1878'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - OpenAI/v1 PythonBindings/0.28.1
+      X-OpenAI-Client-User-Agent:
+      - '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
+        "3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
+        "uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar  6 21:00:17
+        PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SQMW+DMBCFd37F6WaoIKEksLVShi5k6VZVkWuc4NT4LHxJq0b898qQhHa54b73
+        3j3dJQJA3WAFKFvBsnMmWb9Yf8rq8379s3pyZ7Mpno3Q29e6Lb5SjIODPo5K8s31IKlzRrEmO2HZ
+        K8EqpGZFWeblYvm4GEFHjTLBdnCc5ElaZMuroyUtlccK3iIAgMs4QzfbqG+sII1vm055Lw4Kq7sI
+        AHsyYYPCe+1ZWMZ4hpIsKzvWrbf1Bq9kuEfutdW+3fVKeLJB5pncJBsigPex4unfVXQ9dY53TJ/K
+        ht55Wkx5OH9jptmVMbEwf02rKNwYol8AAAD//wMAtfp4RYkBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 82323023acba0182-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Nov 2023 01:12:33 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=;
+        path=/; expires=Thu, 09-Nov-23 01:42:33 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - clearbit-2
+      openai-processing-ms:
+      - '433'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '100'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '99'
+      x-ratelimit-remaining-tokens:
+      - '299557'
+      x-ratelimit-reset-requests:
+      - 600ms
+      x-ratelimit-reset-tokens:
+      - 88ms
+      x-request-id:
+      - 222744a81f853802353e390dd40173ea
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the following
+      format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to
+      take, should be one of [multiplier]\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n        \n\n        This is your understanding
+      of the current situation:\n        {}\nBegin! This is VERY important to you,
+      your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
+      "gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
+      ["\nObservation"]}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Authorization:
+      - Bearer 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
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1293'
+      Content-Type:
+      - application/json
+      Cookie:
+      - __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
+      User-Agent:
+      - OpenAI/v1 PythonBindings/0.28.1
+      X-OpenAI-Client-User-Agent:
+      - '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
+        "3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
+        "uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar  6 21:00:17
+        PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1RQy2rDMBC8+ysWnZ1ix3ZS61IKbSFQeuoltCWo8jZWK2uFtQ6BkH8vct6XPczs
+        7MzsLgEQphEShG4V687byf3ChY3bvGX1tsr0srLP8xdVZZxXr5yLNCro+xc1n1R3mjpvkQ25A617
+        VIzxaj6r67KeFlUxEh01aKNs7XlSTrJZXhwVLRmNQUj4SAAAduOM2VyDWyEhS09IhyGoNQp5XgIQ
+        PdmICBWCCawci/RCanKMboz73tKwblnCE8ECHGIDTDAEBAVMZB9gieHTPepYRkI3WDbeGuxPGCyc
+        H1hCkZbi6LA/R/sxzoR21aMK5KJdYPKHtX0C8DVWHW7SC99T53nF9Icu9p/O88M9cfnqFVscSSZW
+        9gqvyySa7JN/AAAA//8DAGryDPHSAQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 823230284a450182-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Nov 2023 01:12:34 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - clearbit-2
+      openai-processing-ms:
+      - '1120'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '100'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '99'
+      x-ratelimit-remaining-tokens:
+      - '299710'
+      x-ratelimit-reset-requests:
+      - 600ms
+      x-ratelimit-reset-tokens:
+      - 57ms
+      x-request-id:
+      - 00d0dced84c81ed56d116437daa60a72
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the following
+      format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to
+      take, should be one of [multiplier]\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      is the summary of your work so far:\n        \n\n        This is your understanding
+      of the current situation:\n        {}\nBegin! This is VERY important to you,
+      your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do I need
+      to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation: 12\nThought:
+      \n"}], "model": "gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature":
+      0.7, "stop": ["\nObservation"]}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Authorization:
+      - Bearer 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
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1397'
+      Content-Type:
+      - application/json
+      Cookie:
+      - __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
+      User-Agent:
+      - OpenAI/v1 PythonBindings/0.28.1
+      X-OpenAI-Client-User-Agent:
+      - '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
+        "3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
+        "uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar  6 21:00:17
+        PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SQW08CQQyF3/dXNPMMBHZXhH0x3ghoNCSoMVFDxtkKg7PTzbYEE7L/3cxy05c+
+        9Os5Pe02AlA2Vxkos9RiitK1BxPPm5fRbDy4Wr0OzqfT2/vn8dPD7Hoc31nVCgr6XKGRg6pjqCgd
+        iiW/w6ZCLRhce/3hMB3GyVnagIJydEG2KKWdtrv9XrJXLMkaZJXBWwQAsG1qyOZz/FEZdFuHToHM
+        eoEqOw4BqIpc6CjNbFm0F9U6QUNe0Ddxbwgm4BFzEII1I2gQIncBj/TuR9ZrB5eeN1hlkIDYAhlS
+        sAy9uKP2hvUxyZf1lpfzCjWTD+4sVO7G6gjgo7ls/S+sKisqSpkLfaMP5ybddOenTk880TjeQyHR
+        7o8q7kdhSR39AgAA//8DAGQ+69zBAQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 82323030ddb90182-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Nov 2023 01:12:36 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - clearbit-2
+      openai-processing-ms:
+      - '1128'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '100'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '99'
+      x-ratelimit-remaining-tokens:
+      - '299685'
+      x-ratelimit-reset-requests:
+      - 600ms
+      x-ratelimit-reset-tokens:
+      - 62ms
+      x-request-id:
+      - 2edfda088d7c07b018426c91a4506903
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What
+      is 3 times 4\nAI: 3 times 4 is 12.\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
+      null, "stream": false, "n": 1, "temperature": 0.7}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Authorization:
+      - Bearer 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
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '905'
+      Content-Type:
+      - application/json
+      Cookie:
+      - __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
+      User-Agent:
+      - OpenAI/v1 PythonBindings/0.28.1
+      X-OpenAI-Client-User-Agent:
+      - '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
+        "3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
+        "uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar  6 21:00:17
+        PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SQMW/CQAyF9/wK62ZAJEAE2TpUAqlSFzrQqkLXi0sO7s5R7EhFiP9eXQKkXTz4
+        e89+9iUBULZUBShTaTG+duPlJvDZro+Hrffr12x3fntpps/y3hrOd2oUHfR1RCN318SQrx2KpdBj
+        06AWjFPTfLWar7LZIu+ApxJdtB1qGc/H0zyd3RwVWYOsCvhIAAAuXY3ZQok/qoDp6N7xyKwPqIqH
+        CEA15GJHaWbLooOo0QANBcHQxd1WCFXrdQDNJwapEJ42IARGO9M6LQgzEOuRYT6BbY8b5JpCGeVa
+        Bg6WIc0m6rbo+kj4bYPlat+gZgpxKwvVveyaAHx2F7f/jlB1Q76WvdAJQ3xDulj089Tw3IFm+Q0K
+        iXZ/XMs0iUuuyS8AAAD//wMAmwGlztkBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8232303a294a0182-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Nov 2023 01:12:37 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - clearbit-2
+      openai-processing-ms:
+      - '1025'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '100'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '99'
+      x-ratelimit-remaining-tokens:
+      - '299794'
+      x-ratelimit-reset-requests:
+      - 600ms
+      x-ratelimit-reset-tokens:
+      - 41ms
+      x-request-id:
+      - 8f752eda873d901ecec28888cdeb318d
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_crew_creation.yaml
+++ b/tests/cassettes/test_crew_creation.yaml
--- a/tests/crew_test.py
+++ b/tests/crew_test.py
@@ -3,32 +3,43 @@
 import pytest
 from ..crewai import Agent, Crew, Task, Process

+@pytest.mark.vcr()
 def test_crew_creation():
-	agent_CTO = Agent(
-		role="CTO",
-		goal="Help your team craft the most amazing apps ever made.",
-		backstory="You're world class CTO that works on the best web consulting agency."
-	)
-	agent_QA = Agent(
-		role="QA Engineer",
-		goal="Make sure ship the best software possible with the highest quality",
-		backstory="You're the best at QA in the whole team, you are known for catching all bugs and advocate for improvements."
-	)
-	agent_Eng = Agent(
-		role="Web Engineer",
-		goal="Build amazing websites by writing high quality html, css and js.",
-		backstory="You're great at vanila JS, CSS and HTMl, you got hired to build amazing website using your skills."
+	researcher = Agent(
+		role="Researcher",
+		goal="Make the best research and analysis on content about AI and AI agents",
+		backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer."
 	)

-	task = Task(
-		description="Build a landing page for a website that sells dog food."
+	writer = Agent(
+		role="Senior Content Officer",
+		goal="Write the best content about AI and AI agents.",
+		backstory="You're a senior content officer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer."
 	)

+	tasks = [
+		Task(
+			description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+			agent=researcher
+		),
+		Task(
+			description="Write a 1 amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+			agent=writer
+		)
+	]
+
 	crew = Crew(
-		agents=[agent_CTO, agent_Eng, agent_QA],
-		goal="Build amazing landing pages.",
-		tasks=[task],
-		process=Process.consensual
+		agents=[researcher, writer],
+		process=Process.sequential,
+		tasks=tasks,
 	)

-	assert crew.kickoff() == 'lol'
+	assert crew.kickoff() == """1. AI in Healthcare: Dive into an exploratory journey where silicon meets stethoscope, unraveling how Artificial Intelligence is revolutionizing the healthcare industry. From early diagnosis of life-threatening diseases to personalized treatment plans, AI is not just an assistant; it's becoming a lifesaver. Imagine a world where technology doesn't just assist doctors but empowers patients, offering them more control over their health and well-being.
+
+2. Ethical Implications of AI: Unearth the moral minefield that AI has become in this thought-provoking piece. As AI's capabilities grow, so do the ethical dilemmas. Should machines make life or death decisions? Can an algorithm be biased? Who bears responsibility for AI-induced outcomes? Join us as we navigate these murky waters, balancing the scales of technological advancement and ethical responsibility.
+
+3. AI in Climate Change: Witness how AI is becoming an indispensable ally in the fight against climate change. From forecasting weather patterns and predicting natural disasters to optimizing energy use and promoting sustainable practices, AI is proving to be a game-changer. Explore how this nascent technology can help us steer towards a more sustainable future.
+
+4. AI and Art: Embark on a fascinating exploration of where creativity meets code. Can a machine create a masterpiece? How does AI challenge our traditional notions of art? Delve into the world of AI-generated art, where algorithms are the artists and pixels are the palette, pushing the boundaries of what we consider "art".
+
+5. The Future of AI Agents: Step into the realm of speculation and prediction, where we explore the potential future of AI agents. How will they shape industries, influence our daily lives, and even redefine our understanding of "intelligence"? Engage in a lively discourse around the possibilities and perils that the future of AI agents might hold."""