vercel-ai-sdk

Add a specific feature to an existing Vercel AI SDK application. Features include streaming, tools, chat, ai-gateway, generative-ui, middleware, mcp, rag, attachments, multi-modal, agents, production, database, observability, testing.

Build a complete full-stack AI application with Vercel AI SDK including frontend UI, backend API, streaming, and AI provider integration

Use this agent to implement Vercel AI SDK advanced features including AI agents with workflows and loop control, MCP (Model Context Protocol) tools integration, image generation, audio transcription, speech synthesis, and multi-step reasoning patterns. Invoke when building autonomous agents, multi-modal AI features, or complex reasoning systems.

Use this agent to implement Vercel AI SDK data features including embeddings generation, RAG (Retrieval Augmented Generation) with vector databases, structured data generation using generateObject/streamObject, and semantic search functionality. Invoke when adding AI-powered data processing, knowledge retrieval, or structured output capabilities to applications.

Use this agent to implement database integrations for AI applications including message persistence with Postgres/MongoDB/Redis, vector databases (Pinecone, Weaviate, pgvector), conversation history storage, and caching strategies. Invoke when adding database functionality to AI applications.

Use this agent to build AI-powered user interfaces using Vercel AI SDK's AI Elements component library. Specializes in pre-built chat components, code editors, voice interfaces, and workflow builders using shadcn/ui + React 19 + Tailwind CSS 4. Invoke when implementing AI UI components.

Implement Vercel AI Gateway for unified multi-provider access with model fallbacks, BYOK credentials, provider routing, and usage tracking

Use this agent to implement AI SDK middleware patterns including custom providers, model routing, request/response interception, caching middleware, guardrails, and semantic caching. Specializes in extending AI SDK behavior. Invoke when customizing AI behavior or implementing cross-cutting concerns.

Use this agent to design and plan complete full-stack AI applications using Vercel AI SDK. Analyzes requirements and creates implementation plans covering UI, database, providers, tools, and middleware layers. Invoke when planning complex AI application architecture.

Use this agent to implement Vercel AI SDK production features including telemetry/observability with OpenTelemetry, rate limiting, comprehensive error handling, testing setup with mocks, and middleware for logging/auth/validation. Invoke when preparing AI applications for production deployment.

Use this agent to configure and manage AI providers for Vercel AI SDK applications. Specializes in AI Gateway setup, multi-provider routing, fallback chains, BYOK (Bring Your Own Key), and provider-specific optimizations across 107+ supported providers. Invoke when setting up providers.

Use this agent to implement tool calling and MCP (Model Context Protocol) integration for Vercel AI SDK applications. Specializes in Tools Registry integration, custom tool creation, MCP server/client setup, and multi-step agent workflows. Invoke when adding tool capabilities or MCP integration.

Use this agent to implement Vercel AI SDK UI features including generative UI (AI RSC), useObject for structured outputs, useCompletion for text completion, message persistence with databases, message metadata, resume streams, and file attachments/multi-modal components. Invoke when adding advanced UI capabilities to Vercel AI SDK applications.

Use this agent to verify that a JavaScript Vercel AI SDK application is properly configured, follows SDK best practices, and is ready for deployment. Invoke after creating or modifying a JavaScript AI SDK app.

Use this agent to verify that a Python Vercel AI SDK application is properly configured, follows SDK best practices, and is ready for deployment. Invoke after creating or modifying a Python AI SDK app.

Use this agent to verify that a TypeScript Vercel AI SDK application is properly configured, follows SDK best practices, and is ready for deployment. Invoke after creating or modifying a TypeScript AI SDK app.

AI agent workflow patterns including ReAct agents, multi-agent systems, loop control, tool orchestration, and autonomous agent architectures. Use when building AI agents, implementing workflows, creating autonomous systems, or when user mentions agents, workflows, ReAct, multi-step reasoning, loop control, agent orchestration, or autonomous AI.

Generative UI implementation patterns for AI SDK RSC including server-side streaming components, dynamic UI generation, and client-server coordination. Use when implementing generative UI, building AI SDK RSC, creating streaming components, or when user mentions generative UI, React Server Components, dynamic UI, AI-generated interfaces, or server-side streaming.

Validate and debug Vercel AI SDK provider configurations including API keys, environment setup, model compatibility, and rate limiting. Use when encountering provider errors, authentication failures, API key issues, missing environment variables, model compatibility problems, rate limiting errors, or when user mentions provider setup, configuration debugging, or SDK connection issues.

RAG (Retrieval Augmented Generation) implementation patterns including document chunking, embedding generation, vector database integration, semantic search, and RAG pipelines. Use when building RAG systems, implementing semantic search, creating knowledge bases, or when user mentions RAG, embeddings, vector database, retrieval, document chunking, or knowledge retrieval.

Testing patterns for Vercel AI SDK including mock providers, streaming tests, tool calling tests, snapshot testing, and test coverage strategies. Use when implementing tests, creating test suites, mocking AI providers, or when user mentions testing, mocks, test coverage, AI testing, streaming tests, or tool testing.