---
title: AI
description: Build AI-powered applications using Vercel's agentic infrastructure.
url: "https://vercel.com/kb/ai"
published: 2025-11-07
last_updated: 2026-09-03
install_vercel_plugin: npx plugins add vercel/vercel-plugin
---

# AI

Build AI-powered applications using Vercel's agentic infrastructure.

## Ship your own software factory with eve

- [Build a software factory with eve](/kb/guide/eve-software-factory): Foreman, a software factory built on eve. It turns GitHub and Linear work items into reviewed draft pull requests through four agent stations, triaging issues and fixing its own red CI along the way.
- [Give your software factory a browser](/kb/guide/software-factory-browser): Add a KERNEL cloud browser to the eve software factory template so Foreman can reproduce flow bugs, sign in through managed auth, and verify fixes on preview deployments in attended sessions.
- [Manage Vercel projects with a software factory](/kb/guide/software-factory-vercel-mcp): Add Vercel's hosted MCP to the eve software factory template so Foreman can read build logs, runtime errors, and deployment history for the app your target repository deploys, brokered at app scope through Vercel Connect.

## Build an agent with eve

- [Build a software factory with eve](/kb/guide/eve-software-factory): Foreman, a software factory built on eve. It turns GitHub and Linear work items into reviewed draft pull requests through four agent stations, triaging issues and fixing its own red CI along the way.
- [Build an incident response sre agent with eve](/kb/guide/eve-incident-sre-agent): sre is an incident response agent for Slack. It investigates production issues using a hypothesis-driven approach and returns verifiable evidence from connected sources.
- [How to automatically approve tool calls in eve with Jev](/kb/guide/auto-approve-tool-calls-eve-jev): Use Jev to review tool calls in eve, allow routine actions, and request human approval when needed. Configure the policy and test its failure paths.
- [Run a marketing team from Slack with eve](/kb/guide/marketing-team-eve): Team of five marketing agents built on eve. The lead routes work to specialists that write long-form into Notion, queue social posts in Typefully, run email in Resend, and audit for SEO, with approvals for anything irreversible.
- [How to build a browser agent that works behind a login](/kb/guide/build-a-browser-agent): Build a browser agent with eve, Vercel Connect, and KERNEL managed auth that signs a user in through a human-in-the-loop handoff and completes tasks behind a login without exposing credentials.
- [Give your eve agent an email inbox with Resend](/kb/guide/eve-agent-with-resend): Connect an eve agent to email using the Chat SDK channel and the Resend adapter. Handle inbound email, threaded replies, attachments, and proactive sends.
- [Manage your Sanity project from Slack with eve](/kb/guide/eve-sanity-copilot): A Slack-based Sanity copilot built on eve. It queries and edits content with GROQ, shapes schemas, manages releases, and drafts long-form pieces into Notion.

## Build with a eve Template

- [Data analyst](https://vercel.com/templates/eve/eve-data-analyst): Slack-based data analyst built on eve that answers questions about your business from a Postgres database.
- [Contentful assistant](https://vercel.com/templates/eve/eve-contentful-agent): Slack-based Contentful assistant with Vercel Drives providing a searchable copy of your Contentful content.
- [Marketing team](https://vercel.com/templates/eve/eve-marketing-team): A team of marketing agents: a lead routes work to specialists for positioning, long-form content, social, SEO, and email, publishing through Notion, Typefully, and Resend.
- [Software factory](https://vercel.com/templates/eve/eve-software-factory): Software factory built on eve: AI agents work each stage of the development loop, and people make the judgment calls.
- [Incident response](https://vercel.com/templates/eve/eve-incident-response-agent): sre investigates production issues using a hypothesis-driven approach and outputs verifiable evidence from sources.
- [GitHub maintainer](https://vercel.com/templates/eve/eve-github-maintainer): Kody, a personal GitHub maintainer agent that emails you a weekly digest of open issues, acts on your email replies, summarizes new pull requests, answers @mentions, and works delegated Linear issues.
- [Personal agent](https://vercel.com/templates/nuxt/eve-personal-agent): A durable AI assistant with long-term memory. Chat on the web or Slack, query Linear, and pick up where you left off.
- [Vercel Drives Starter](https://vercel.com/templates/eve/eve-vercel-drives-starter): An eve agent that reads and saves your team's files on a Vercel Drive.
- [Memory](https://vercel.com/templates/eve/eve-memory-agent): A Slack agent built on eve that remembers what your team tells it. Personal preferences and channel conventions are stored separately in Vercel Blob and recalled before every reply.
- [TanStack Start agent](https://vercel.com/templates/eve/eve-tanstack-agent): Web chat built on eve and TanStack Start, where the agent can respond with generative UI like tables and dashboards.

## Using AI Gateway

- [Run AI prompts in your GitHub Actions with the Vercel AI Action](/kb/guide/run-ai-prompts-in-your-github-actions-with-the-vercel-ai-action): Use the vercel/ai-action@v2 GitHub Action to call the AI Gateway from a workflow. Generate text or structured JSON, set system messages, and handle untrusted input safely.
- [Build AI agents with AI Gateway and AI SDK](/kb/guide/ai-gateway-and-ai-sdk): Build AI agents on Vercel with AI Gateway and AI SDK, then make them reliable, capable, and durable with Sandbox, Chat SDK, Vercel Connect, and Workflow.
- [How to build an AI agent for Slack with Chat SDK and AI SDK](/kb/guide/how-to-build-an-ai-agent-for-slack-with-chat-sdk-and-ai-sdk): Build a Slack AI agent using Chat SDK, AI SDK's ToolLoopAgent, and Vercel AI Gateway. Covers project setup, tool definitions, streaming responses, deployment to Vercel, and scaling tool selection with toolpick.
- [Cost-aware model routing through AI Gateway](/kb/guide/cost-aware-model-routing-with-ai-gateway): Route easy requests to a cheap model and escalate only hard ones to a frontier model through one AI Gateway endpoint, with budgets and spend monitoring.
- [How I use OpenCode with Vercel AI Gateway to build features fast](/kb/guide/how-i-use-opencode-with-vercel-ai-gateway-to-build-features-fast): How to route different AI models to different coding tasks automatically, cutting token costs by \~70% without losing quality on the work that matters.
- [How to build a durable AI code agent on Vercel](/kb/guide/how-to-build-a-durable-ai-code-agent-on-vercel): Build an AI agent that generates code, writes its own tests, and executes them in an isolated microVM with automatic retries.

## Building agentic applications

- [The Complete Guide to Vercel Connect](/kb/guide/vercel-connect): Use Vercel Connect to call provider APIs like Slack, GitHub, Linear, Microsoft, Discord, Snowflake, and Salesforce from your agents and services with short-lived, scoped tokens instead of long-lived secrets.
- [Building AI apps on Vercel: an overview](/kb/guide/how-to-build-ai-app): Learn the key AI concepts and tools for building and scaling AI apps.
- [Course: Builder’s Guide to the AI SDK](https://vercel.com/academy/ai-sdk): Build production-ready AI features with the AI SDK and Next.js. Learn LLMs, prompting, extraction, streaming, and more.

## All AI guides

- [Private enterprise agents on Vercel](/kb/guide/private-enterprise-agents-vercel): Design private enterprise agents that call internal APIs and databases with Vercel Functions, Secure Compute, AI Gateway, Workflows, and Vercel Connect.
- [Moderate product reviews with Jev, TanStack AI, and AI Gateway](/kb/guide/moderate-product-reviews-jev-tanstack-ai): Moderate product reviews for an e-commerce storefront with Jev from TypeSafe AI and TanStack AI's \`decide()\` function. The \`@tanstack/ai-vercel-gateway\` adapter returns typed choices, scores, and boolean probabilities through Vercel AI Gateway, so your code can publish clear reviews and hold flagged ones.
- [How to classify, route, and score with Jev and AI SDK](/kb/guide/typesafe-jev-and-ai-sdk): Use Jev from TypeSafe AI with AI SDK's experimental \`evaluate\` API to classify, route, score, and verify inside your application. Jev returns typed choices, scores, and boolean probabilities through AI Gateway.
- [Vercel AI SDK vs TanStack AI](/kb/guide/vercel-ai-sdk-vs-tanstack-ai): Compare the Vercel AI SDK and TanStack AI for building AI-powered TypeScript applications and agents. Learn how AI SDK and TanStack AI differ in agent abstractions, harnesses, framework support, persistence, streaming protocols, tool calling, and bundle optimization.
- [Build a v0-style app builder with OpenAI Agents API and Vercel Sandbox](/kb/guide/v0-clone-openai-agents-vercel-sandbox): Build a chat-to-app workspace with live Next.js previews, follow-up edits, and saved projects using the OpenAI Agents API preview, Vercel Sandbox, and Queues.
- [Build an agent with OpenAI Agents API on Vercel](/kb/guide/openai-agents-api-vercel): Build and deploy an agent with OpenAI Agents API, Vercel Functions, Queues, and Sandbox for isolated code execution.
- [Using TanStack AI with Vercel Sandbox](/kb/guide/tanstack-ai-vercel-sandbox): Run coding agents in isolated Vercel Sandbox microVMs with the @tanstack/ai-sandbox-vercel provider, with durable resume-by-id, port previews, and workspace policies.
- [Using TanStack AI with Vercel AI Gateway](/kb/guide/tanstack-ai-vercel-ai-gateway): Connect TanStack AI to Vercel AI Gateway with the @tanstack/ai-vercel-gateway adapter to stream chat, route across providers, and generate embeddings and images with one API key.
- [Durable agent approval workflows on Vercel](/kb/guide/agent-approval-workflow-stack-guide): How enterprise architects choose a stack and decide where to run durable, human-in-the-loop agent approval workflows on Vercel.
- [How to route your coding agent spend through AI Gateway](/kb/guide/route-coding-agent-spend-through-ai-gateway): Point Claude Code, Codex, Cursor, and every other harness on your machine at AI Gateway with one CLI command, on a budgeted key, so all of your coding agent spend lands in one place.
- [Make your site readable by AI agents](/kb/guide/make-your-site-readable-by-ai-agents): A practical guide to making your website discoverable, readable, and actionable for AI agents, grounded in over 1,000 real agent runs and a controlled experiment with the ora.ai research lab.
- [Build Claude Managed Agents with Vercel Services](/kb/guide/claude-managed-agents-vercel-services): Deploy Claude Managed Agents with Vercel Services to run a streaming research analyst in a browser chat, using Anthropic's Chat SDK quickstart.
- [Build Claude Managed Agents with Chat SDK](/kb/guide/claude-managed-agents-chat-sdk): Ship a Slack research bot built on Claude Managed Agents and Chat SDK. One persistent session per thread, streamed briefs with sources, and no Slack credentials to manage.
- [Building an AI chat app with RAG and source citations on Vercel](/kb/guide/building-ai-chat-app-with-rag-and-citations-on-vercel): A production stack for AI chat with retrieval, reranking, source citations, and background ingestion on Vercel using Next.js and the AI SDK.
- [Production architecture for a RAG chatbot on Vercel](/kb/guide/rag-chatbot-production-architecture-on-vercel): Architect a production RAG chatbot on Vercel Functions with Fluid compute, AI Gateway, and a region-pinned vector store.
- [Using xmcp with Next.js](/kb/guide/using-xmcp-with-nextjs): Add an MCP server to an existing Next.js app with xmcp. Create typed tools, add authentication, and deploy to Vercel as a Vercel Function.
- [Building community moderation agents using AI SDK](/kb/guide/building-community-moderation-agents-using-ai-sdk): Learn how to build an AI-powered community moderation agent with Next.js, the AI SDK, and AI Gateway.
- [How to protect your AI endpoints with Vercel BotID](/kb/guide/protect-ai-endpoints-with-vercel-botid): Gate every request to your AI endpoints with Vercel BotID and checkBotId() so inference runs only for verified callers. Covers setup, Deep Analysis, and verified bots.
- [Building human-in-the-loop agents for community moderation with durable workflows](/kb/guide/building-human-in-the-loop-agents-for-community-moderation-with-durable-workflows): Learn how to build AI agents that escalate decisions to humans in Slack, pause and resume runs reliably, and stream progress using Vercel Workflows.
- [Run AI prompts in your GitHub Actions with the Vercel AI Action](/kb/guide/run-ai-prompts-in-your-github-actions-with-the-vercel-ai-action): Use the vercel/ai-action@v2 GitHub Action to call the AI Gateway from a workflow. Generate text or structured JSON, set system messages, and handle untrusted input safely.
- [How to build an agent for Liveblocks with Chat SDK and AI SDK](/kb/guide/liveblocks-chat-sdk-ai-sdk): Build an AI agent that replies to @-mentions in Liveblocks comment threads with streamed responses and tool calling, using Chat SDK, AI SDK, and Redis.
- [What is WorkflowAgent?](/kb/guide/what-is-workflowagent): Build durable AI agents with WorkflowAgent: tool calls that retry as workflow steps, suspend for human approval, and resume after timeouts or page refreshes.
- [Human-in-the-Loop with Chat SDK and Workflow SDK](/kb/guide/human-in-the-loop-with-chat-sdk-and-workflow-sdk): Combine Chat SDK and Workflow SDK to suspend workflows on approval cards in a chat platform, then resume on click via createWebhook.
- [How to build a durable AI code agent on Vercel](/kb/guide/how-to-build-a-durable-ai-code-agent-on-vercel): Build an AI agent that generates code, writes its own tests, and executes them in an isolated microVM with automatic retries.
- [Ship a GitHub code review bot with Hono and Redis](/kb/guide/ship-a-github-code-review-bot-with-hono-and-redis): This guide walks through building a GitHub bot that reviews pull requests on demand. When a user @mentions the bot on a PR, Chat SDK picks up the mention, spins up a Vercel Sandbox with the repo cloned, and uses AI SDK to analyze the diff.
- [Building an agent with OpenAI Agents SDK and Vercel Sandbox](/kb/guide/building-an-agent-with-openai-agents-sdk-and-vercel-sandbox): Learn how to build an agent with with OpenAI Agents SDK and Vercel Sandbox
- [Build a Claude Managed Agent with Vercel Workflow](/kb/guide/claude-managed-agent-vercel): Learn how to build a Claude Managed Agent on Vercel with auth, credential vaults, durable polling, and a chat UI.
- [How to build an AI agent for Slack with Chat SDK and AI SDK](/kb/guide/how-to-build-an-ai-agent-for-slack-with-chat-sdk-and-ai-sdk): Build a Slack AI agent using Chat SDK, AI SDK's ToolLoopAgent, and Vercel AI Gateway. Covers project setup, tool definitions, streaming responses, deployment to Vercel, and scaling tool selection with toolpick.
- [How to build an MCP server with Nuxt](/kb/guide/how-to-build-an-mcp-server-with-nuxt): Add an MCP server to your Nuxt app with the Nuxt MCP Toolkit. Create tools, resources, and prompt templates that AI assistants like Cursor and VS Code can connect to.
- [How to evaluate a rapid AI prototyping tool](/kb/guide/how-to-evaluate-a-rapid-ai-prototyping-tool): A practical guide on how to evaluate an AI prototyping tool for your team, from thinking through requirements like security and prototype fidelity, to choosing the right pilot metrics, to structuring a two-phase rollout that starts with a small group and expands once the first phase proves out.
- [Building a Slack agent with durable workflows](/kb/guide/building-a-slack-agent-with-durable-workflows): Build an AI-powered Slack bot that gathers team data, drafts a summary, and refines it through conversation.
- [Using private GitHub repositories with Vercel Sandbox](/kb/guide/sandbox-private-github-repositories): Learn how to use Vercel Sandbox with private GitHub repositories using fine-grained tokens, classic tokens, or GitHub App tokens.
- [How to install system packages in Vercel Sandbox](/kb/guide/how-to-install-system-packages-in-vercel-sandbox): Learn how to install additional system packages in Vercel Sandbox with apt-get on the default Ubuntu-based managed images, or dnf on legacy Amazon Linux runtimes.
- [Using Vercel Sandbox to run Claude’s Agent SDK](/kb/guide/using-vercel-sandbox-claude-agent-sdk): Learn how to deploy Claude's Agent SDK in Vercel Sandbox for secure and isolated execution of AI-powered code generation and autonomous agent tasks.
- [Streaming responses from LLMs](/kb/guide/streaming-from-llm): Learn how to use the AI SDK to stream LLM responses.
- [Building AI apps on Vercel: an overview](/kb/guide/how-to-build-ai-app): Learn the key AI concepts and tools for building and scaling AI apps.
- [Build an MCP Server with Weather tools using Express and Vercel](/kb/guide/mcp-server-with-weather-tool-express): Make your Express weather API accessible to AI assistants through the Model Context Protocol.
- [What is Retrieval Augmented Generation (RAG)](/kb/guide/what-is-rag): Learn how RAG enhances AI applications by providing Large Language Models (LLMs) with relevant context, enabling accurate responses to queries about proprietary data, recent information, and domain-specific knowledge.
- [Build an AI Chat Agent with Weather API Tool Calling](/kb/guide/build-ai-agent-weather-api): Build an intelligent conversational agent that fetches real-time weather data using the AI SDK, tool calling, and a backend weather API powered by Express, FastAPI or Nitro
- [Understanding vector databases for AI apps](/kb/guide/understanding-vector-databases-for-ai-apps): Learn how vector databases enable semantic search through embeddings and similarity matching.
- [An Introduction to Evals](/kb/guide/an-introduction-to-evals): Evaluations test model and agent outputs to ensure they meet the standards and requirements you specify.
- [Build a ChatGPT Connector (MCP server)](/kb/guide/mcp-server-chatgpt-connector): Build a ChatGPT MCP server with mcp-handler and Fluid compute. Add search, fetch, and OAuth, deploy to Vercel, then validate it in developer mode.
- [Safely running AI generated code in your Next.js application](/kb/guide/running-ai-generated-code-sandbox): How to execute untrusted, AI‑generated code from a Next.js app using Vercel Sandbox, an isolated, ephemeral environment.
- [How to protect your AI app from bots](/kb/guide/how-to-protect-your-ai-app-from-bots): Learn how to protect your AI app from bots, scrapers, and abuse using Firewall, BotID, and more.
- [How to block bots from OpenAI GPTBot](/kb/guide/how-to-block-bots-openai-gptbot): Learn how to use the Vercel WAF to block, rate limit, or challenge traffic from OpenAI GPTBot.
- [Fine-tuning GPT with OpenAI, Next.js, and Vercel AI SDK](/kb/guide/fine-tuning-openai-nextjs): In this guide, we will build Shooketh – an AI bot fine-tuned on Shakespeare's literary works with OpenAI GPT-4o and the Vercel AI SDK.
- [Vector Databases Explained](/kb/guide/vector-databases): Learn about vector databases: what they are, 8 of the best examples and how to build an AI semantic search app with them.
- [How to use OpenAI Function Calling with Next.js and the Vercel AI SDK](/kb/guide/openai-function-calling): Learn how to use OpenAI Function Calling and Vercel AI SDK in a Next.js Application to build AI-powered user experiences.
- [Building an AI Chatbot with Cohere, Next.js, and the Vercel AI SDK](/kb/guide/cohere-nextjs-vercel-ai-sdk): Learn how to build a generative AI application using Cohere, Next.js, and Vercel.
- [Building an AI chatbot with Next.js, Langchain, and OpenAI](/kb/guide/nextjs-langchain-vercel-ai): Dive into the world of LangChain.js and Next.js with our detailed guide. Learn how to set up a chatbot, structure outputs, integrate agents, and more. Perfect for developers looking to harness the power of AI in their web applications.
- [Securing your AI applications with Rate Limiting](/kb/guide/securing-ai-app-rate-limiting): Learn how to secure your AI applications with rate limiting using Vercel WAF and Vercel AI SDK
- [How to Use ML Models from Hugging Face in Vercel Functions](/kb/guide/ml-models-hugging-face): This guide provides step-by-step instructions on how to integrate ML models from Hugging Face into Vercel Functions
- [Building AI-powered Article Embeddings with Chroma and GPT-4](/kb/guide/ai-powered-article-embeddings-with-chroma-and-gpt-4): This guide provides step-by-step instructions on using Chroma and GPT-4 to build AI-powered article embeddings for tasks like similarity-based search and recommendation systems.
- [What is a Large Language Model (LLM)?](/kb/guide/what-is-a-large-language-model): Learn what Large Language Models (LLMs) are, how they work, and how you can use them to generate UI, debug code, and integrate AI features into your web applications.
- [Running OpenClaw in Vercel Sandbox](/kb/guide/running-openclaw-in-vercel-sandbox): This guide walks you through setting up OpenClaw inside a Vercel Sandbox and configuring the WhatsApp channel.
- [Build an agent with Vercel and Flue](/kb/guide/build-an-agent-with-vercel-and-flue): Build and deploy an agent with Flue, Vercel Sandbox, and AI Gateway
- [What is an LLM Tool?](/kb/guide/what-is-an-llm-tool): Learn what tools are, how tool calling works, and how you can use them to build agents.
- [How I use OpenCode with Vercel AI Gateway to build features fast](/kb/guide/how-i-use-opencode-with-vercel-ai-gateway-to-build-features-fast): How to route different AI models to different coding tasks automatically, cutting token costs by \~70% without losing quality on the work that matters.
- [How to use snapshots for faster sandbox startup](/kb/guide/how-to-use-snapshots-for-faster-sandbox-startup): Learn how to save sandbox state with snapshots and skip installation on future runs.
- [How to execute AI-generated code safely with Vercel Sandbox](/kb/guide/how-to-execute-ai-generated-code-safely): Learn how to run code generated by AI models in an isolated sandbox environment.
- [How to reconnect to a running Sandbox](/kb/guide/how-to-reconnect-to-a-running-sandbox): Learn how to use \`Sandbox.get()\` to reconnect to an existing sandbox from a different process or after a script restart.
- [Build a Claude Managed Agent with Vercel Sandbox](/kb/guide/run-claude-managed-agent-tools-with-vercel-sandbox): Build a Claude Managed Agent with Vercel Sandbox: each session runs in a fresh microVM with credential brokering and a webhook-driven control plane on Vercel.
- [Agent Skills: Creating, Installing, and Sharing Reusable Agent Context](/kb/guide/agent-skills-creating-installing-and-sharing-reusable-agent-context): This guide will cover what skills are, how to create custom skills for yourself and your team, and how to publish them to the community.
- [How to build an on-demand voice agent with Vercel Sandbox](/kb/guide/how-to-build-an-on-demand-voice-agent-with-vercel-sandbox): Build a voice AI application that creates isolated LiveKit agent environments using Vercel Sandbox, enabling real-time conversations without maintaining persistent infrastructure.

## Explore other topics in the Vercel Knowledge Base

- [Vercel Sandbox](/kb/vercel-sandbox): The compute primitive designed to safely run untrusted or user-generated code on Vercel.
- [Infrastructure and Compute](/kb/infrastructure-and-compute): Scale and deliver applications efficiently across regions using Vercel's Fluid Compute and CDN.
- [Migrations](/kb/migrations): Learn how to migrate your application or agent to Vercel's agentic infrastructure.
- [Backends](/kb/backends): Backends on Vercel run on Fluid compute with Active CPU pricing, plus Instant Rollback, the Vercel Firewall, protected previews, and rolling releases.