CrewAI in Python: Coordinating Teams of AI Agents

Have you ever asked ChatGPT to research something, analyze the findings, and then write a polished report, all in one prompt? You probably got something back, but it wasn’t great. That’s because you’re asking a single model to wear way too many hats at once. CrewAI is a Python framework that solves this by letting you build a crew of specialized AI agents, each focusing on one part of the job.

For example, instead of cramming research, validation, and writing into a single prompt, you create a team. One agent researches, another validates, and a third writes. Each focuses on what it does best, working together to complete the task.

By the end of this tutorial, you’ll understand that:

• CrewAI coordinates teams where each agent has a specific role, goal, and backstory that influence its behavior.
• Sequential workflows automatically pass outputs from one agent to the next, making coordinated pipelines straightforward.
• The context parameter gives you fine-grained control over which task outputs feed into other tasks.
• You can equip agents with tools like web scraping to expand what they can do beyond text generation.
• API costs multiply quickly since each agent makes separate LLM calls, and verbose logging helps you debug agent behavior.

Before you invest time learning CrewAI, you should understand when it’s the right tool for your project. This comparison highlights the key trade-offs:

CrewAI’s sweet spot is workflows where agents have clear responsibilities and work in a predictable sequence. If you need fine-grained state management with branching logic, LangGraph gives you more control. If your agents need conversational back-and-forth, AG2—the community fork of AutoGen—supports chat-driven coordination patterns and may be a better fit.

Microsoft AutoGen is now in maintenance mode, so new projects typically choose AG2 or Microsoft Agent Framework.

Take the Quiz: Test your knowledge with our interactive “CrewAI in Python: Coordinating Teams of AI Agents” quiz. You’ll receive a score upon completion to help you track your learning progress:

---

Interactive Quiz

CrewAI in Python: Coordinating Teams of AI Agents

Check your understanding of CrewAI in Python. Review how to define agent roles, assign tasks, add tools, and coordinate multi-agent workflows.

Get Started With CrewAI in Python

Before you dive into building multi-agent systems with CrewAI, you’ll need to install it and set up an API key for your chosen language model provider. This tutorial uses Google’s Gemini model, which you can access for free through Google AI Studio.

You can install CrewAI from PyPI using pip. Before running the command below, you should create and activate a virtual environment. CrewAI requires Python 3.10 to 3.13, so run python --version first—installing on Python 3.14 or later will silently resolve to a much older CrewAI release and then fail to build:

$ python -m pip install 'crewai[tools,google-genai]'

This installs CrewAI’s core framework, the native Google Gemini provider, and prebuilt tools like web scraping that agents can use during their work.

You’ll need a Gemini API key to run the examples in this tutorial. If you don’t have one yet, then head over to Google AI Studio to sign in with your Google account and generate an API key for free.

Once you have your API key, set it as an environment variable:

• Windows
• Linux + macOS

PS> $ENV:GEMINI_API_KEY = "your-gemini-api-key-here"

$ export GEMINI_API_KEY="your-gemini-api-key-here"

With your environment variable set, CrewAI is ready to connect to Gemini in your projects.

To get started with CrewAI, you can create a single agent that acts as a travel advisor: