PyData Amsterdam 2025

Event-Driven AI Agent Workflows with Dapr
09-24, 15:10–16:40 (Europe/Amsterdam), Katherine Johnson @ TNW City

As AI systems evolve, the need for robust infrastructure increases. Enter Dapr Agents: an open-source framework for creating production-grade AI agent systems. Built on top of the Dapr framework, Dapr Agents empowers developers to build intelligent agents capable of collaborating in complex workflows - leveraging Large Language Models (LLMs), durable state, built-in observability, and resilient execution patterns. This workshop will walk through the framework’s core components and through practical examples demonstrate how it solves real-world challenges.

Managing communication, state, and resiliency between distributed systems remains complex - especially when building multi-agent systems that can reason, act, and collaborate using LLMs. Dapr Agents addresses this gap by bringing durability, observability, and event-driven design to AI applications. In this workshop, we will create an event-driven workflow with multiple autonomous agents in Python and explore Dapr Agents' key features.

Target Audience

Engineers and data scientists who are exploring or working with LLM-based systems and are excited to build intelligent, multi-agent applications. Attendees should have intermediate Python knowledge. Experience with Dapr is not required, but some understanding of distributed systems, LLMs, or async programming will be helpful. We will not explain every concept in depth, but we will provide resources so you can dig deeper on your own as needed.

Here are the things you should install before the start of this workshop:

  • Docker
  • Python 3.10 or above
  • virtual environment (recommended uv >= 0.4.25)
  • Dapr CLI

Takeaways

You’ll learn how to:

  • Build agents using Python and Dapr
  • Connect these agents through event-driven pub/sub messaging
  • Persist agent state using Dapr’s state management
  • Design resilient, reactive multi-agent workflows
  • Observe and debug your system

Outline

  • Introduction (20 mins):
  1. What is Dapr?
  2. What are LLM Agents?
  3. Introducing Dapr Agents
  4. Workshop overview
  • Environment setup (5 mins)
  1. Install dependencies
  2. Clone workshop repo and verify setup
  • Develop event-driven workflows with multiple autonomous agents (65 mins)
  1. Create simple agents (exercise)
  2. Orchestrate workflow using different workflow types (exercise)
  3. Run the multi-agent system (exercise)
  4. Recap key learnings & share additional materials and next steps