Make AI Agents Durable
Agent frameworks are good at deciding what to do next and bad at surviving a crash halfway through. These courses take agents built with LangGraph, DeepAgents, the Microsoft Agent Framework and Dapr Agents and put them on durable execution, so a failed step resumes instead of restarting. Every one is a hands-on lab that runs in the browser.
Make LangGraph Agents Durable with Dapr Workflow - Schedule Planner
Run a LangGraph agent as a durable Dapr Workflow, inspect its checkpoints in Redis, then crash it mid-run and watch it resume.
Duration: 30 minutes
Supported languages: Python
Make LangGraph Agents Durable with Dapr Workflow - Supply Chain Auditor
Run a LangGraph agent that audits a real Dependabot PR for a supply-chain attack, crash it mid-audit, and watch Dapr Workflow resume it from durable state.
Duration: 30 minutes
Supported languages: Python. Requires an Anthropic API key.
Make DeepAgents Durable with Dapr Workflow - Deep Issue Investigation
Run a Python DeepAgents app that investigates a real GitHub issue, wrap it in a Dapr Workflow, crash it mid-run, and watch it resume from durable state.
Duration: 30 minutes
Supported languages: Python. Requires an OpenAI API key.
Make MAF Agents Durable with Dapr Workflow
Run a Microsoft Agent Framework (MAF) Aspire app orchestrated by Dapr Workflow, crash it mid-run, and watch it resume from durable state.
Duration: 30 minutes
Supported languages: .NET. Requires an OpenAI API key.
Dapr Agents: Build Durable LLM-powered Intelligent Applications with Tools and Workflows
Build LLM-powered agents with custom tool calls, MCP integration, and multi-agent collaboration using Dapr Agents in Python.
Duration: 45 minutes
Supported languages: Python. Requires an OpenAI API key.
Dapr Agents - Fix Outdated Agent Answers
Build a Python expert agent that pulls in live web results with Tavily so its answers stay current instead of stale.
Duration: 30 minutes
Supported languages: Python. Requires an OpenAI API key and a free Tavily API key.
