The outcome

Operate an event-driven flow whose state transitions, side effects, retries, and recovery are deterministic and observable.

Step by step

A workflow you can repeat.

  1. 01

    Map start events, state schema, listeners, routes, crew calls, side effects, pause points, terminal states, and idempotency keys.

  2. 02

    Implement typed state and small start, listen, and router methods, keeping external actions behind validated interfaces and approval checks.

  3. 03

    Persist only necessary state, encrypt sensitive fields, correlate every run, and checkpoint before and after any non-reversible action.

  4. 04

    Test duplicate triggers, process restarts, timeouts, invalid routes, tool failures, human rejection, resumed runs, and partial external success.

  5. 05

    Add tracing and alerts, bound retries and concurrency, version state migrations, and deploy gradually with a tested rollback and replay policy.

Working standard

What good use looks like.

  • Model state transitions explicitly.
  • Checkpoint around side effects.
  • Make triggers and retries idempotent.

Official references

Check the current product documentation.