Skip to content

Day 10 — Step Functions & Agent Orchestration #13

Description

@PunithVT

Day 10. Agent loops drift, retry badly, and lose context. Step Functions is AWS's answer to "make a workflow durable." Worth comparing it against framework-level orchestration like LangGraph.

Topics to cover:

  1. Step Functions basics — state machines, ASL, Standard vs Express
  2. Error handling and retries — Catch / Retry, exponential backoff, custom error types
  3. Parallel and Map states — fan-out for batch agent work
  4. Agent loops as state machines — when to use Step Functions vs LangGraph vs a plain loop
  5. Human-in-the-loop steps — Wait for token, callback patterns, approvals

Plan: Chandana on the Step Functions native side (ASL, retries, parallel), me on agent-loop orchestration (LangGraph parallels, HITL patterns), shipping one workflow that uses both.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions