Durable Execution
What is the difference between retries and compensation in durable agent workflows?
Retries automatically re-execute a failed step until it succeeds or exhausts a limit, assuming the step is idempotent. Compensation runs undo logic for already-completed steps when the overall workflow must roll back. Catalyst supports both: retries via Dapr Workflow retry policies and compensation via custom rollback activities. Use retries for transient errors; use compensation for semantic rollback of side effects.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Durable Execution
What is durable execution in AI agent workflows?
Durable execution means an AI agent workflow can keep its progress even when a process crashes, a tool call fails, or the system restarts.
- Durable Execution
Why do production AI agents need durable workflows?
Production AI agents need durable workflows because real agent tasks rarely finish in a single clean request.
- Durable Execution
Is checkpointing enough for production AI agents?
Checkpointing helps, but it is usually not enough by itself for production AI agents. It explains the production reliability impact for AI agent workflows.