Cookbook

A curated collection of workflow patterns with clean, copy-paste code examples for real use cases.

Agent Patterns

Durable Agent — Replace a stateless AI agent with one that survives crashes and retries tool calls
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 happen exactly once, even when steps 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