Skip to Content
View all events

CrewAI for Production-Ready Multi‑Agent Systems

Published by Pearson

Intermediate content levelIntermediate

Deploy autonomous multi-agent AI teams to research, code, and solve tasks

  • Design entire "crews" of agents with distinct roles, backstories, and goals that collaborate like a real-world team.
  • Use complex hierarchical processes where "manager" agents autonomously delegate tasks and review work.
  • Master memory systems, human-in-the-loop safeguards, and configuration-driven architecture.

This live training will take developers beyond the basics of LLM interaction into the realm of building sophisticated, autonomous multi-agent systems. While Large Language Models are powerful on their own, their true potential is unlocked when they are orchestrated into teams that can plan, execute, and review complex tasks. CrewAI is quickly becoming state of the art in AI agent development and orchestration.

This live training will help master the CrewAI framework through hand-on examples. We start by building a simple "Hello World" research agent, then quickly advance to constructing a team of financial analysts equipped with custom tools. We then explore advanced concepts like hierarchical delegation—where a manager agent supervises a team—and implement long-term memory so agents "learn" from past executions. Finally, we cover essential production patterns, including human-in-the-loop approval flows for sensitive tasks (like writing code) and separating agent logic from configuration for maintainable software.

What you’ll learn and how you can apply it

  • Create Custom Tools to fetch stock data, read/write files, or search the web.
  • Implement both linear workflows into hierarchical structures where a "Manager" agent autonomously plans and delegates work.
  • Abstract agent prompts and definitions into configuration files for easier testing and version control.

This live event is for you because...

  • You are a software or data scientist familiar with Python and basic LLM concepts, ready to take their productivity and effectiveness to a new level by building autonomous systems that can execute multi-step workflows.
  • You are an intermediate or experienced developer aiming to move beyond interactive or “chatbot-style” LLM use and create fully automated, agentic workflows.

Prerequisites

What prior knowledge or experience do attendees need to get the most out of class?

  • Python
  • Jupyter
  • Familiarity with LLMs

Course Set-up

  • Python
  • CrewAI
  • Gemini API

Recommended Preparation

Recommended Follow-up

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Segment 1 – Foundations of Autonomous Agents (30 minutes)

  • Core Concepts
  • Roles
  • Goals
  • Backstories

Q&A + Break (10 minutes)

Segment 2 – Tools and Sequential Crews (40 minutes)

  • Use Search and APIs
  • Develop Custom Tools
  • Understand Context

Q&A + Break (10 minutes)

Segment 3 – Orchestration & Memory (50 minutes)

  • Hierarchical Process
  • Managers and Task delegation
  • RAG
  • Vector Databases

Q&A + Break (10 minutes)

Segment 4: Human-in-the-Loop (HITL) (40 minutes)

  • Files
  • Code development
  • HITL Workflows

Q&A + Break (10 minutes)

Segment 5: Production Patterns (30 minutes)

  • Extensible configurations
  • Supporting multiple LLMs
  • Error Handling
  • Best Practices

Wrap up (10 minutes)

Your Instructor

  • Bruno Gonçalves

    Bruno Gonçalves is an author, public speaker, corporate trainer, and consultant specializing in Generative AI, Blockchain Analytics, and Machine Learning. He has a diverse background that spans academia and industry, having previously served as a Data Science fellow at NYU's Center for Data Science while on leave from his tenured faculty position at Aix-Marseille Université. Bruno earned his PhD in the Physics of Complex Systems in 2008. He later focused his research on applying Data Science and Machine Learning to the large-scale analysis of online human behavior.

    linkedinXlinksearch

Skill covered

Generative AI