Beginner2h49m

Practical Multi AI Agents and Advanced Use Cases with crewAI

Instructor: João Moura

Earn an accomplishment with PRO · Updated Oct 7, 2025

Enroll for Free

Beginner
2h49m
15 Video Lessons
6 Code Examples
1 Graded Assignment PRO
Earn an accomplishment with PRO
Updated Oct 7, 2025
Instructor: João Moura
crewAI
Learn more aboutMembership PRO Plan

Enroll for Free

What you'll learn

Build agents that collaborate in complex workflows, integrating external tools and using different models to handle specific tasks efficiently.
Learn to evaluate and enhance your agents by conducting performance tests and providing human feedback to train and optimize their performance.
Create multi-agent systems to automate tasks, such as project planning, lead scoring, data reporting, and large-scale content creation.

Course recap

PRO

This course, taught by CrewAI founder Joao Moura, focuses on building production-ready multi-agent systems. Unlike introductory agent courses, it covers real-world deployment patterns including performance testing, human feedback training, multi-model configurations, external system integrations, and complex orchestration with Flows.

Concept map

Key concepts

Multi-agent orchestrationSequential, hierarchical, parallel, and hybrid task execution patterns
FlowsCrewAI feature for chaining crews with regular Python code using @start, @listen, and, or, and router decorators
Structured outputUsing Pydantic models to get typed, parseable data from agent crews
Agent training (CrewAI train)Human feedback loop where users provide per-task feedback that agents learn from permanently
Agent testing (CrewAI test)LLM-as-judge scoring of task outputs against expected output descriptions for consistency measurement
Dynamic task contextUsing the context attribute to pass results from parallel tasks to downstream tasks
Code execution agentsAgents with allow_code_execution=True that write and run Python in a Docker sandbox

Lesson highlights

1.Introduction — Course overview, real-world agent use cases across verticals
2.Overview of Multi AI-Agent Systems — Building blocks: agents, tasks, tools, crews; YAML configuration; caching, memory, guardrails
3.Internal and External Integrations — Custom tools inheriting from BaseTool; API calls, database connections, self-healing on failures
4.Automated Project Planning — Three-agent crew for task breakdown, estimation, and resource allocation with Pydantic structured output
5.Building Project Progress Report — Trello integration tools for automated sprint reporting
6.Complex Crew Setups — Parallel tasks with async_execution, context dependencies, introduction to Flows
7.Agentic Sales Pipeline — Flow with lead scoring crew, filtering, email writing crew; @start, @listen, @router decorators; state management
8.Performance Optimization — Speed vs. quality tradeoffs; CrewAI test for measuring consistency; CrewAI train for human feedback training
9.Support Data Insight Analysis — Code-executing agents that plot charts; full test-train-test cycle for improvement
10.Content Creation at Scale — Multi-model crew (Groq Llama 70B + GPT-4o); RAG-as-a-tool with WebsiteSearchTool; real-time web research
11.Multi-Model Use Cases — Using different LLM providers and fine-tuned models per agent
12.Generate, Deploy and Monitor Crews — crewai create crew CLI; crewai deploy for API generation; webhooks and polling
13.Blog Post Crew in Production — Creating crews from scratch with CLI; crewai create flow
14.Agentic Workflows in Industry — Interview with PWC CTO on enterprise agent deployment (10% to 70%+ code generation accuracy)
15.Conclusion

About this course

Join our new short course, Practical Multi AI Agents and Advanced Use Cases with crewAI, taught by João Moura, Founder of CrewAI, and learn how to build and deploy agent-based apps for advanced real applications in the industry.

In this course, you will build several practical apps like an automated project planning system, lead-scoring and engagement automation, support data analysis, and content creation at scale.

Throughout this course, you’ll learn:

The main building blocks—tasks, agents, crews—that go into creating these multi-agent systems, and all the different things that make them work such as caching, memory, and guardrails.
How to integrate your multi-agent application with internal and external systems.
How to connect multiple agents in complex setups including parallel, sequential, and hybrid, and how to create flows that involve multiple crews working together.
How to test your crew by measuring key metrics and train it using human feedback to optimize its performance for better and more consistent results.
How to work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task.
How to start a project from scratch in your environment, and prepare it for deployment.
Bonus Interview with Jacob Wilson, the Commercial GenAI CTO at PWC: Learn about deploying agentic workflows in real industry use cases.

Use cases in the course

You will work on many exciting use cases such as building:

A crew for automated project planning, breaking a project into tasks, creating time estimates, and allocating resources to them.
A project progress report with an example of interacting with a project management system such as Trello.
An agentic sales pipeline that takes in lead information, enriches and scores it, and writes personalized emails for qualified leads.
A customer support data insights analysis pipeline that generates issue reports and visualizations.
Content creation crew that researches the web, uses RAG as a tool on specific web pages to write content, reviews and modifies the content for quality, and generates social copies for different platforms.