I like writing. You could discover that for those who comply with me or my weblog. For that cause, I’m continually producing new content material and speaking about Knowledge Science and Synthetic Intelligence.
I found this ardour a few years in the past once I was simply beginning my path in Knowledge Science, studying and evolving my abilities. At the moment, I heard some extra skilled professionals within the space saying {that a} good research method was working towards new abilities and writing about it someplace, instructing no matter you discovered.
As well as, I had simply moved to the US, and no one knew me right here. So I needed to begin someplace, creating my skilled picture on this aggressive market. I keep in mind I talked to my cousin, who’s additionally within the Tech trade, and he instructed me: write weblog posts about your experiences. Inform folks what you’re doing. And so I did.
And I by no means stopped.
Quick ahead to 2025, now I’ve nearly 2 hundred printed articles, a lot of them with In direction of Knowledge Science, a broadcast Ebook, and an excellent viewers.
Writing helped me a lot within the Knowledge Science space.
Most just lately, one among my pursuits has been the superb Pure Language Processing and Giant Language Fashions topics. Studying about how these trendy fashions work is fascinating.
That curiosity led me to experiment with Agentic Ai as properly. So, I discovered about CrewAI, a simple and open-source bundle that helps us construct AI brokers in a enjoyable and straightforward approach, with little code. I made a decision to check it by making a crew of brokers to jot down a weblog publish, after which see how that goes.
On this publish, we are going to discover ways to create these brokers and make them work collectively to supply a easy weblog publish.
Let’s try this.
What’s a Crew?
A crew of AI brokers is a mix of two or extra brokers, every of them performing a process in the direction of a remaining purpose.
On this case research, we are going to create a crew that may work collectively to supply a small weblog publish a couple of given matter that we are going to present.
The move works like this:
- We select a given matter for the brokers to jot down about.
- As soon as the crew is began, it’ll go to the data base, learn a few of my beforehand written articles, and attempt to mimic my writing fashion. Then, it generates a set of tips and passes it to the subsequent agent.
- Subsequent, the Planner agent takes over and searches the Web in search of good content material concerning the matter. It creates a plan of content material and sends it to the subsequent agent.
- The Author agent receives the writing plan and executes it in response to the context and knowledge obtained.
- Lastly, the content material is handed to the final agent, the Editor, who critiques the content material and returns the ultimate doc because the output.
Within the following part, we are going to see how this may be created.
Code
CrewAI is a good Python bundle as a result of it simplifies the code for us. So, let’s start by putting in the 2 wanted packages.
pip set up crewai crewai-tools
Subsequent, in order for you, you possibly can comply with the directions on their Quickstart web page and have a full venture construction created for you with simply a few instructions on a terminal. Principally, it’ll set up some dependencies, generate the folder construction steered for CrewAI tasks, in addition to generate some .yaml and .py information.
I personally choose to create these myself, however it’s as much as you. The web page is listed within the References part.
Folder Construction
So, right here we go.
We’ll create these folders:
And these information:
- Within the config folder: create the information
brokers.yamlandduties.yaml - Within the data folder, that’s the place I’ll add the information with my writing fashion.
- Within the venture root: create
crew.pyandfundamental.py.
Be certain that to create the folders with the names talked about, as CrewAI appears to be like for brokers and duties contained in the config folder and for the data base inside a data folder.
Subsequent, allow us to set our brokers.
Brokers
The brokers are composed of:
- Title of the agent:
writer_style - Function: LLMs are good function gamers, so right here you possibly can inform them which function to play.
- Purpose: inform the mannequin what the purpose of that agent is.
- Backstory: Describe the story behind this agent, who it’s, what it does.
writer_style:
function: >
Writing Fashion Analyst
purpose: >
Totally learn the data base and study the traits of the crew,
corresponding to tone, fashion, vocabulary, temper, and grammar.
backstory: >
You might be an skilled ghost author who can mimic any writing fashion.
You know the way to determine the tone and magnificence of the unique author and mimic
their writing fashion.
Your work is the idea for the Content material Author to jot down an article on this matter.I received’t bore you with all of the brokers created for this crew. I imagine you bought the thought. It’s a set of prompts explaining to every agent what they’re going to do. All of the brokers directions are saved within the brokers.yaml file.
Consider it as for those who had been a supervisor hiring folks to create a crew. Take into consideration what varieties of execs you would wish, and what abilities are wanted.
We’d like 4 professionals who will work in the direction of the ultimate purpose of manufacturing written content material: (1) a Author Stylist, (2) a Planner, (3) a Author, and (4) an Editor.
If you wish to see the setup for them, simply verify the total code within the GitHub repository.
Duties
Now, again to the analogy of the supervisor hiring folks, as soon as we “employed” our total crew, it’s time to separate the duties. We all know that we wish to produce a weblog publish, we’ve 4 brokers, however what every of them will do.
Nicely, that might be configured within the file duties.yaml.
As an example, let me present you the code for the Author agent. As soon as once more, these are the components wanted for the immediate:
- Title of the duty:
write - Description: The outline is like telling the skilled the way you need that process to be carried out, similar to we might inform a brand new rent carry out their new job. Give exact directions to get the very best outcome doable.
- Anticipated output: That is how we wish to see the output. Discover that I give directions like the dimensions of the weblog publish, the amount of paragraphs, and different data that helps my agent to provide me the anticipated output.
- Agent to carry out it: Right here, we’re indicating the agent who will carry out this process, utilizing the identical title set within the
brokers.yamlfile. - Output file: Now all the time relevant, but when so, that is the argument to make use of. We requested for a markdown file as output.
write:
description: >
1. Use the content material plan to craft a compelling weblog publish on {matter}.
2. Incorporate web optimization key phrases naturally.
3. Sections/Subtitles are correctly named in an enticing method. Be certain that
so as to add Introduction, Drawback Assertion, Code, Earlier than You Go, References.
4. Add a summarizing conclusion - That is the "Earlier than You Go" part.
5. Proofread for grammatical errors and alignment with the author's fashion.
6. Use analogies to make the article extra participating and complicated ideas simpler
to grasp.
expected_output: >
A well-written weblog publish in markdown format, prepared for publication.
The article have to be inside a 7 to 12 minutes learn.
Every part should have at the very least 3 paragraphs.
When writing code, you'll write a snippet of code and clarify what it does.
Watch out to not add an enormous snippet at a time. Break it in affordable chunks.
Within the examples, create a pattern dataset for the code.
Within the Earlier than You Go part, you'll write a conclusion that's participating
and factually correct.
agent: content_writer
output_file: blog_post.mdAfter the brokers and duties are outlined, it’s time to create our crew move.
Coding the Crew
Now we are going to create the file crew.py, the place we are going to translate the beforehand introduced move to Python code.
We start by importing the wanted modules.
#Imports
import os
from crewai import Agent, Activity, Course of, Crew, LLM
from crewai.venture import CrewBase, agent, crew, process
from crewai.data.supply.pdf_knowledge_source import PDFKnowledgeSource
from crewai_tools import SerperDevToolWe’ll use the essential Agent, Activity, Crew, Course of and LLM to create our move. PDFKnowledgeSource will assist the primary agent studying my writing fashion, and SerperDevTool is the instrument to go looking the web. For that one, make sure that to get your API key at https://serper.dev/signup.
A finest follow in software program growth is to maintain your API keys and configuration settings separate out of your code. We’ll use a .env file for this, offering a safe place to retailer these values. Right here’s the command to load them into the environment.
from dotenv import load_dotenv
load_dotenv()Then, we are going to use the PDFKnowledgeSource to point out the Crew the place to seek for the author’s fashion. By default, that instrument appears to be like on the data folder of your venture, thus the significance of the title being the identical.
# Information sources
pdfs = PDFKnowledgeSource(
file_paths=['article1.pdf',
'article2.pdf',
'article3.pdf'
]
)Now we are able to arrange the LLM we wish to use for the Crew. It may be any of them. I examined a bunch of them, and people I favored probably the most had been qwen-qwq-32b and gpt-4o. When you select OpenAI’s, you will have an API Key as properly. For Qwen-QWQ, simply uncomment the code and remark out the OpenAI’s strains.. You want an API key from Groq.
# LLMs
llm = LLM(
# mannequin="groq/qwen-qwq-32b",
# api_key= os.environ.get("GROQ_API_KEY"),
mannequin= "gpt-4o",
api_key= os.environ.get("OPENAI_API_KEY"),
temperature=0.4
)Now we’ve to create a Crew Base, displaying the place CrewAI can discover the brokers and duties configuration information.
# Creating the crew: base exhibits the place the brokers and duties are outlined
@CrewBase
class BlogWriter():
"""Crew to jot down a weblog publish"""
agents_config = "config/brokers.yaml"
tasks_config = "config/duties.yaml"Brokers Capabilities
And we’re able to create the code for every agent. They’re composed of a decorator @agent to point out that the next operate is an agent. We then use the category Agent and point out the title of the agent within the config file, the extent of verbosity, being 1 low, 2 excessive. You can even use a Boolean worth, corresponding to true or false.
Lastly, we specify if the agent makes use of any instrument, and what mannequin it’ll use.
# Configuring the brokers
@agent
def writer_style(self) -> Agent:
return Agent(
config=self.agents_config['writer_style'],
verbose=1,
knowledge_sources=[pdfs]
)
@agent
def planner(self) -> Agent:
return Agent(
config=self.agents_config['planner'],
verbose=True,
instruments=[SerperDevTool()],
llm=llm
)
@agent
def content_writer(self) -> Agent:
return Agent(
config=self.agents_config['content_writer'],
verbose=1
)
@agent
def editor(self) -> Agent:
return Agent(
config=self.agents_config['editor'],
verbose=1
)Duties Capabilities
The subsequent step is creating the duties. Equally to the brokers, we are going to create a operate and enhance it with @process. We use the category Activity to inherit CrewAI’s functionalities after which level to the duty for use from our duties.yaml file for use for every process created. If any output file is predicted, use the output_file argument.
# Configuring the duties
@process
def fashion(self) -> Activity:
return Activity(
config=self.tasks_config['mystyle'],
)
@process
def plan(self) -> Activity:
return Activity(
config=self.tasks_config['plan'],
)
@process
def write(self) -> Activity:
return Activity(
config=self.tasks_config['write'],
output_file='output/blog_post.md' # That is the file that might be comprise the ultimate weblog publish.
)
@process
def edit(self) -> Activity:
return Activity(
config=self.tasks_config['edit']
)Crew
To attach every part collectively, we now create a operate and enhance it with the @crew decorator. That operate will line up the brokers and the duties within the order to be carried out, because the course of chosen right here is the best: sequential. In different phrases, every part runs in sequence, from begin to end.
@crew
def crew(self) -> Crew:
"""Creates the Weblog Publish crew"""
return Crew(
brokers= [self.writer_style(), self.planner(), self.content_writer(), self.editor(), self.illustrator()],
duties= [self.style(), self.plan(), self.write(), self.edit(), self.illustrate()],
course of=Course of.sequential,
verbose=True
)Operating the Crew
Operating the crew may be very easy. We create the fundamental.py file and import the Crew Base BlogWriter created. Then we simply use the features crew().kickoff(inputs) to run it, passing a dictionary with the inputs for use to generate the weblog publish.
# Script to run the weblog author venture
# Warning management
import warnings
warnings.filterwarnings('ignore')
from crew import BlogWriter
def write_blog_post(matter: str):
# Instantiate the crew
my_writer = BlogWriter()
# Run
outcome = (my_writer
.crew()
.kickoff(inputs = {
'matter': matter
})
)
return outcome
if __name__ == "__main__":
write_blog_post("Value Optimization with Python")There it’s. The result’s a pleasant weblog publish created by the LLM. See beneath.
That’s so good!
Earlier than You Go
Earlier than you go, know that this weblog publish was 100% created by me. This crew I created was an experiment I needed to do to study extra about create AI brokers and make them work collectively. And, like I mentioned, I like writing, so that is one thing I’d have the ability to learn and assess the standard.
My opinion is that this crew nonetheless didn’t do an excellent job. They had been in a position to full the duties efficiently, however they gave me a really shallow publish and code. I’d not publish this, however at the very least it could possibly be a begin, perhaps.
From right here, I encourage you to study extra about CrewAI. I took their free course the place João de Moura, the creator of the bundle, exhibits us create completely different sorts of crews. It’s actually attention-grabbing.
GitHub Repository
https://github.com/gurezende/Crew_Writer
About Me
If you wish to study extra about my work, or comply with my weblog (it’s actually me!), listed here are my contacts and portfolio.
References
[Quickstart CrewAI](https://docs.crewai.com/quickstart)
[CrewAI Documentation](https://docs.crewai.com/introduction)
[GROQ](https://groq.com/)
[OpenAI](https://openai.com)
[CrewAI Free Course](https://study.crewai.com/)