All guides

Production AI Radar

How to run durable agent workflows with Temporal

Long-running agent jobs with retries, checkpoints, and human approval — not fire-and-forget scripts.

TrialPlatform & DevEx15 min
Agent harness · approvals

Hover a node · click to focus · ←/→ steps

Spec → allowlisted tools → model loop. Writes pause for human approval; MCP goes through an allowlist gateway.

When you need this

  • Multi-step agent automation
  • Human approval before external actions
  • Scheduled agent maintenance jobs
  • Need replay after worker crash

Prerequisites

  • Temporal cluster or Temporal Cloud
  • One bounded pilot workflow identified
  • Approval channel (Slack / ticket) for humans

Tools

  • Strong for prod agents; assess ops learning curve vs simple queues.

  • Assess for complex agents; keep simpler RAG as plain pipelines until graph complexity pays off.

Steps

  1. 1

    Pick a bounded pilot workflow

    Choose a 3–5 step agent task with clear success criteria — not open-ended ‘do my job’ agents.

  2. 2

    Model activities and approvals

    Split into idempotent activities. Insert human approval signals before writes or external communications.

  3. 3

    Compose agent logic carefully

    Use LangGraph (or equivalent) for tool loops inside activities; keep Temporal as the durability and approval boundary.

  4. 4

    Wire observability

    Export workflow traces to OTel. Dashboard running, failed, and waiting-for-approval counts.

  5. 5

    Document replay and failure modes

    Test worker crash mid-workflow. Document how replay behaves and who unsticks approvals.

Adoption pitfalls

  • Putting non-idempotent side effects in activities without dedupe keys
  • No timeout on human approval → zombie workflows
  • Monolithic agent that Temporal cannot meaningfully checkpoint

Adoption checklist

  • Pilot workflow in production with owner
  • Human approval on all external writes
  • Replay tested after worker failure
  • On-call runbook for stuck workflows

SEER REAL assessment / sprint

Assessment flags fire-and-forget agents with prod side effects. Sprint implements one durable workflow with approval gates and a crash-replay drill.

Related radar blips