Agentic Minds - Crew AI

Name: Agentic Minds - Crew AI
Rating: 4.6 (59 reviews)

Crew AI

Created byAshish Choube

Last updated 11/2025

English

What you'll learn

Understand the fundamentals of CrewAI — learn how CrewAI works, its architecture, and how it uses agent-based collaboration to solve complex AI tasks.
Set up and configure CrewAI projects — install Python, uv, and the CrewAI CLI tool, and create a fully functional CrewAI environment on your system.
Design and build AI agent workflows — define agents, roles, and tasks using YAML configurations, connect them with tools and APIs, and orchestrate with Crew
Integrate external AI models and APIs — connect CrewAI with OpenAI, LangChain, Groq, Hugging Face, and other third-party APIs to enhance agent capabilities.

Course content

1 section • 9 lectures • 1h 27m total length

Installation of Python and VS code6:04
In this video, we’ll walk through how to install Python and Visual Studio Code (VS Code) — two essential tools you’ll need before working with CrewAI or any AI project.
You’ll learn:
How to download and install the correct version of Python (3.10–3.14)
How to properly configure environment variables (Add Python to PATH)
How to download and set up VS Code, the most popular code editor for AI and Python development
How to install useful extensions in VS Code to write and run Python scripts efficiently
By the end of this video, you’ll have your system ready with both Python and VS Code configured — so you can confidently move on to installing uv and CrewAI in the next lesson.
Installation of Crew AI10:53
In this video, we’ll learn how to install CrewAI and its essential dependency manager, uv, step by step.
You’ll learn:
How to verify your Python version to ensure compatibility with CrewAI
How to install uv, the fast package and environment manager used by CrewAI
How to use uv to install the CrewAI CLI tool on Windows, macOS, or Linux
How to resolve common installation errors and configure CrewAI correctly
How to verify your installation and create your first CrewAI project
By the end of this video, you’ll have CrewAI successfully installed and ready to use on your PC — setting the foundation for building your own AI agents and multi-agent workflows in the upcoming lessons.
Creation of Open AI API Key6:09
In this video, we’ll walk you through the process of creating an OpenAI API key — a crucial step for connecting CrewAI or other AI tools to OpenAI’s models such as GPT-4.
You’ll learn:
How to log in or sign up on the OpenAI platform
How to navigate to the API keys section in your account dashboard
How to generate a new secret API key safely
Best practices for storing and managing your API key securely
How to avoid common mistakes, such as exposing your key publicly
By the end of this video, you’ll have your own OpenAI API key ready to use for integrating with CrewAI and other AI frameworks, enabling powerful multi-agent workflows and automation.
Creation of Serper API Key6:13
In this video, we’ll learn how to create a Serper API key — an important step for integrating real-time search capabilities into your CrewAI projects.
You’ll learn:
How to sign up or log in to the Serper.dev platform
Where to find the API key section in your dashboard
How to generate a new Serper API key securely
Best practices for storing your API key safely
How to avoid exposing your key in public repositories or shared projects
By the end of this video, you’ll have your own Serper API key ready to connect with CrewAI, enabling your agents to retrieve accurate and up-to-date information in real time.
Setup for Web Summarizer Project7:31
In this lecture, you’ll learn how to build a powerful Web Summarizer Agent using CrewAI — a project that can automatically gather and summarize information from the web based on any topic you choose.
We’ll cover:
How to design an intelligent agent workflow with CrewAI.
How to integrate tools like the Serper Dev for real-time web searches.
How to structure two key agents: a Web Search Agent for retrieving data, and a Summarizer Agent for processing and summarizing the content.
Creation of Agents and Tasks in CrewAI10:11
In this section, we’ll explore how to define tasks for our Web Summarizer Project using YAML configuration in CrewAI. Tasks are the specific actions your agents will perform to achieve their goals. By clearly defining tasks, we give structure to our agent workflow and ensure consistent, high-quality results.
We’ll cover two main tasks:
Web Search Task
This task directs the Web Research Agent to perform a thorough search for the given topic. It uses tools to find the most recent, accurate, and relevant information from trusted sources like articles, research papers, and blogs. The expected output is a collection of text snippets and summaries that provide valuable insights about the topic.
Web Summarizer Task
This task directs the Summarization Specialist to review the gathered research content and produce a clear, concise summary. The summary will highlight key findings, trends, and insights in an easy-to-read format, ensuring factual accuracy without repetition. The final output will be structured logically and formatted in Markdown.
By the end of this section, you’ll understand how to create and configure tasks that match the capabilities of your agents. This is a crucial step in building a dynamic, topic-aware Web Summarizer pipeline that delivers precise and useful summaries.
Creation of Crew python file14:22
In this section, we will learn how to create a Crew file — the core Python definition that brings your multi-agent system to life in CrewAI.
A Crew file acts as the blueprint for your project. It defines:
Agents: the specialized roles that perform specific functions.
Tasks: the work assignments agents execute.
Processes: the workflow logic that coordinates task execution.
We’ll walk through the structure of a Crew file, covering:
How to use the @CrewBase decorator to mark a class as a crew definition.
How to define agents with the @agent decorator and link them to configuration in agents.yaml.
How to define tasks with the @task decorator and link them to configuration in tasks.yaml.
How to assemble everything into a crew using the @crew decorator.
By the end of this section, you will be able to create a fully functional Crew file that connects agents, tasks, and processes — forming the foundation of your CrewAI workflow.
Set up the tool and Environment and run the main file12:49
In this section, you will learn how to prepare your development environment for efficient AI project execution. We’ll walk you through the step-by-step process of setting up the required tools, installing dependencies, and configuring your project environment to ensure smooth execution. You will gain hands-on experience with commands like crewai install to bootstrap your project and understand the role of configuration files such as pyproject.toml.
By the end of this section, you will be able to:
Install and configure the necessary tools for your AI project
Set up the project environment and dependencies
Navigate project directories and organize project structure
Run the main project file to start your AI application
Integrate it with Gradio12:57
In this section, you will explore Gradio, a powerful Python library that allows developers to build interactive, web-based interfaces for machine learning models quickly and easily. You’ll learn how to create user-friendly UIs so that anyone — technical or non-technical — can interact with your AI application without writing code.
By the end of this section, you will be able to:
Understand what Gradio is and why it’s useful
Set up a Gradio interface for your project
Create input/output components for model interaction
Deploy your Gradio app locally or on the web
Integrate Gradio with your AI models for real-time interaction
This section equips you with practical knowledge to make your AI solutions interactive, accessible, and demo-ready with minimal effort.

Requirements

Python installed (version 3.10–3.14) — no advanced coding skills required, just a basic understanding of Python syntax.
Optional: Familiarity with AI tools or frameworks like OpenAI or LangChain will be helpful, but not mandatory.

Description

Title : Build a Web Summarizer AI Agent Using Crew AI – Complete Hands-On Free Course

In today’s AI-driven world, intelligent automation and multi-agent collaboration are transforming how we interact with information. This free course introduces you to Crew AI, a powerful open-source Python framework that enables developers to build multi-agent AI systems — intelligent agents that work together to perform complex tasks autonomously.

Through this course, you will learn how to build a Web Summarizer Crew — a team of AI agents capable of fetching, reading, and summarizing web content efficiently. The project demonstrates how Crew AI can coordinate multiple agents, each with specialized roles such as “Researcher,” “Summarizer,” and “Reviewer,” to achieve a common goal: producing accurate and concise summaries from online articles, research pages, or reports.

A key highlight of this course is the integration of the Serper tool, a Google Search API wrapper that allows agents to access live web data dynamically. Using Serper, the Web Summarizer Crew can search the internet, extract relevant web pages, and then process them through its agents to produce meaningful summaries using large language models (LLMs) such as OpenAI GPT.

You’ll gain an in-depth understanding of how Crew AI’s architecture operates — from defining Agents with specific roles and backstories, assigning Tasks to structure their workflow, to orchestrating the overall Crew for smooth collaboration. Each agent can use tools like Serper, web scrapers, and text analyzers to independently process data and communicate results to other agents.

By the end of this hands-on course, you’ll have built a fully functional AI-powered Web Summarizer, learned how Crew AI handles inter-agent communication, and understood how to expand this system with new tools and workflows for various domains such as content creation, business intelligence, or research automation.

This course is perfect for AI enthusiasts, data scientists, and Python developers who want to explore Crew AI, understand multi-agent coordination, and apply these concepts to real-world automation scenarios — all while working on a practical, ready-to-deploy Proof of Concept (POC) project.

Who this course is for:

Python developers or tech enthusiasts interested in experimenting with next-generation agentic frameworks like CrewAI.
AI/ML students and researchers who want hands-on experience with CrewAI to automate research, content generation, or data analysis tasks.
Beginners in AI and Machine Learning who want to explore how multi-agent systems work and how to build intelligent AI workflows.
Professionals and innovators looking to integrate AI agents into business, marketing, or automation solutions.