Alessandro Romano

In this hands-on technical workshop, we’ll explore multi-agent orchestration using CrewAI, diving into how autonomous agents can collaborate to solve complex problems. You’ll learn how to define, configure, and coordinate agents using CrewAI’s core components, all in Python.

We’ll walk through the main classes of problems this approach is suited for and guide you step by step through building real-world workflows. Topics include agent creation, orchestration strategies, tool integration (including custom tools), and LLM-agnostic setups. We’ll also look at how to connect CrewAI with external libraries such as Streamlit to bring your solutions to life.

What You’ll Learn:

• How to define agents and tasks in CrewAI
• Coordinating agents through orchestration flows
• Using and creating tools and custom tools
• Working with different LLMs (LLM-agnostic setups)
• Integrating with libraries like Streamlit
• Best practices for building maintainable and scalable agent systems

In this Hack Session, we’ll explore the evolution from large language models (LLMs) to agentic AI—highlighting how this shift opens the door to solving a new class of complex, dynamic problems. We’ll look at what makes agentic systems different, why they matter, and how they’re already transforming workflows and applications.

We’ll walk through a high-level use case and demonstrate how frameworks like CrewAI make designing, orchestrating, and deploying these systems easier. This session is meant to inspire developers, researchers, and builders to rethink how they approach problem-solving with LLMs—moving from one-off prompts to collaborative, goal-driven agents.