Cookbook

Use these workflow patterns and copy-paste code examples to implement common use cases.

Agent patterns

WorkflowAgent: Build durable, resumable AI agents with AI SDK's WorkflowAgent
Human-in-the-Loop: Pause an agent for human approval, then resume based on the decision
Agent Cancellation: Stop a running agent immediately via run.cancel() or gracefully via a hook + Promise.race

Sequential & Parallel Execution: Compose steps with await, Promise.all, and Promise.race against durable sleeps and webhooks
Workflow Composition: Call workflows from other workflows by direct await or background spawn via start()
Saga: Coordinate multi-step transactions with automatic rollback when a step fails
Batching: Process large collections in parallel batches with failure isolation
Rate Limiting: Handle 429 responses and transient failures with RetryableError and backoff
Scheduling: Use durable sleep to schedule actions minutes, hours, or weeks ahead
Timeouts: Add deadlines to slow steps, hooks, and webhooks by racing them against a durable sleep
Idempotency: Ensure side effects and duplicate starts are safe to retry
Webhooks: Receive HTTP callbacks from external services and process them durably

AI SDK: Use streamText() directly inside a workflow for lower-level control over model calls and tool execution
Chat SDK: Build durable chat sessions with workflow persistence and AI SDK chat primitives
Sandbox: Orchestrate Vercel Sandbox lifecycle inside durable workflows

Child Workflows: Spawn and orchestrate child workflows from a parent
Upgrading Workflows: Identify a clean upgrade point in a long-running workflow and spawn a fresh run on the latest deployment carrying state forward
Serializable Steps: Wrap non-serializable third-party objects so they cross the workflow boundary
Publishing Libraries: Ship npm packages that export reusable workflow functions