Building Durable Multi-Agent AI Workflows with Dapr Agents

From the creator

On this Episode of Open at Microsoft, we are showing the new Dapr Durable AI Agent Workflow Framework. As developers push the boundaries of AI-driven automation, the challenge of orchestrating and managing autonomous agents at scale becomes increasingly complex. Dapr Agents is an open-source framework that dramatically lowers the creation of production ready agentic systems, powered by the CNCF Dapr's distributed application runtime, used by thousands of enterprises today in mission critical services. By combining LLM-driven reasoning with Dapr’s virtual actor model, pub/sub messaging, and stateful workflows, Dapr Agents enables developers to build intelligent, scalable, and fault-tolerant multi-agent systems. If you're interested in building intelligent, scalable, and resilient agentic systems, this episode equips you with the knowledge to easily build these. ✅ Chapters: 00:00 Introduction 00:45 Whats Dapr Agents 03:03 Building Agentic Systems with Dapr and Dapr Agents 03:25 Current state of Agentic Adoption 04:24 How do you run AI Agents that can 05:22 Dapr as Foundational AI infrastructure 06:24 Agentic Frameworks focus on 07:20 Agentic Frameworks are Missing 08:46 How Dapr Implements Authentication 11:39 Dapr for AI Agents 12:39 Demo - Building Dapr Multi AI Agents workflow 20:11 How to Contribute and Getting Started ✅ Resources: Find the latest info about the open-source Dapr Agents project at: https://github.com/dapr/dapr-agents and https://dapr.github.io/dapr-agent

Published 2025-08-05 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.