# Deep Agents + Dapr

Make your LangChain Deep Agents production-ready. These tutorials show you how to add fault tolerance using Dapr.

- [Durable Workflows](https://docs.diagrid.io/getting-started/quickstarts/ai-agents?agentframework=deepagents#1-log-in-to-catalyst) — Make Deep Agents immune to failures with automatic recovery and replay.
- [Sub-Agent Orchestration](https://docs.diagrid.io/develop/agents/deepagents/deepagents-subagent-orchestration) — Coordinate multiple durable sub-agents with a supervisor using AsyncSubAgent.

---

## Why Dapr for Deep Agents?

| Challenge | Dapr Solution |
|-----------|---------------|
| Agent crashes lose all progress | **Durable workflows** checkpoint every step |
| Tool execution state lost on restart | **Workflow replay** resumes from last completed tool |
| No built-in failure recovery | **Automatic crash detection** and recovery at scale |
| Custom retry logic everywhere | **Built-in retries** with exponential backoff |