Cookbook

LatestThe framework for building agentsFrameworksNext.jsSvelteNuxtNitroSDKsAI SDKChat SDKFlags SDKOtherTurboreposhadcn/uiSWRjust-bashdeepsecDocsCookbookWorldsChangelogExamplesSearch…⌘KAsk AIAsk AISearch…⌘KDocsCookbookWorldsChangelogExamplesGitHubVercel OSSLatesteveFrameworksNext.jsSvelteNuxtNitroSDKsAI SDKChat SDKFlags SDKOtherTurboreposhadcn/uiSWRjust-bashdeepsecv5 (Latest)Workflow 5.xOverviewAgent PatternsCommon PatternsIntegrationsAdvancedMenuCookbookCopy pageCopy for LLMView MarkdownAsk AI about this pageUse 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 Common patterns 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 Integrations 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 Advanced 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 On this pageAgent patternsCommon patternsIntegrationsAdvancedScroll to topGive feedbackAgent StackAI SDKAI GatewaySandboxWorkflowsConnectNewPassportNeweveNewCore PlatformCI/CDContent DeliveryFluid ComputeObservabilitySecurityPlatform SecurityWAFBot ManagementBot IDToolsVercel DropNewVercel AgentVercel PluginNewAgent SkillsDomainsv0FrameworkseveNewNext.jsNuxtSvelteKitNitroTurborepoTanstack StartFastAPIxmcpAll frameworksSDKsVercel SDKWorkflow SDKNewFlags SDKChat SDKNewQueues SDKNewStreamdownBuildAI AppsWeb AppsMarketing SitesPlatformsCommercePlatform EngineersDesign EngineersLearnDocsBlogChangelogKnowledge BaseAcademyArticlesCommunityIs AgenticExploreCustomersMarketplaceTemplatesPartner FinderVercel + AWSCompanyAboutCareersPressEventsStartupsShipped on VercelOpen Source ProgramEnterprisePricingHelpLegal & TrustPrivacy PolicyTerms of ServiceCookie PolicyDPAAcceptable Use PolicyLegalTrust CenterStatusSocialGitHubXLinkedInYouTubeInstagram