<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CrewAI on Dapr Docs</title><link>https://v1-18.docs.dapr.io/developing-ai/agent-integrations/crewai/</link><description>Recent content in CrewAI on Dapr Docs</description><generator>Hugo</generator><language>en</language><atom:link href="https://v1-18.docs.dapr.io/developing-ai/agent-integrations/crewai/index.xml" rel="self" type="application/rss+xml"/><item><title>CrewAI Workflows</title><link>https://v1-18.docs.dapr.io/developing-ai/agent-integrations/crewai/crewai-workflows/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://v1-18.docs.dapr.io/developing-ai/agent-integrations/crewai/crewai-workflows/</guid><description>&lt;h2 id="overview">Overview&lt;/h2>
&lt;p>Dapr Workflows make it possible to run CrewAI agents &lt;strong>reliably&lt;/strong>, &lt;strong>durably&lt;/strong>, and &lt;strong>with built-in resiliency&lt;/strong>.&lt;br>
By orchestrating CrewAI tasks with the Dapr Workflow engine, developers can:&lt;/p>
&lt;ul>
&lt;li>Ensure long-running CrewAI work survives crashes and restarts.&lt;/li>
&lt;li>Get automatic checkpoints, retries, and state recovery.&lt;/li>
&lt;li>Run each CrewAI task as a durable activity.&lt;/li>
&lt;li>Observe execution through tracing, metrics, and structured logs.&lt;/li>
&lt;/ul>
&lt;p>This guide walks through orchestrating multiple CrewAI tasks using Dapr Workflows, ensuring each step is run &lt;em>exactly once&lt;/em> even if the process restarts.&lt;/p></description></item></channel></rss>