Sagas

How to use a durable intent log, idempotency keys built from the run and step, and reconciliation against real systems so you can unwind an agent run that fails halfway through without doubling its side effects.

You'll learn how to classify saga and agent-pipeline steps as reversible, semi-reversible, or terminal, and use that classification to decide execution order so your rollback path never tries to undo something that can't be undone.

A compensation handler that had never once fired in production finally ran — cleanly, successfully, logged as a win — and quietly refunded the same customer twice, which is exactly the failure mode agentic pipelines are about to hit on a much faster clock.