Vercel Agent
Vercel Agentis available in Public Betaon Enterprise and Pro plans
Availability
Chat in Slack, dashboard chat, Investigations, and Code Review are in public beta for Pro and Enterprise teams.
Public Beta
Vercel Agent uses context from your Vercel projects, deployments, logs, metrics, configuration, usage, and connected repositories. It can use secure sandboxes to reproduce issues, validate generated code, and run checks before suggested changes reach production.
Copy page
Vercel Agent is an AI assistant built into Vercel. Use it to understand your projects, investigate production issues, review code, and take approved actions.
Ask questions about your projects, investigate what is happening in production, and take approved actions. Use chat from the dashboard or Slack.
Learn more in the Chat overview.
Get Sandbox-validated suggestions on your pull requests. Code Review can identify security vulnerabilities, logic errors, and performance issues, then validate proposed fixes with your builds, tests, and linters.
Learn more in the Code Review docs.
Use Vercel Agent Investigations to analyze anomaly alerts, failed deployments, runtime errors, and cost or performance issues. Vercel Agent queries relevant logs and metrics, identifies possible causes, and summarizes its findings.
Learn more in the Investigation docs.
Use Vercel Agent Installation to add supported Vercel products to a GitHub-connected project. Vercel Agent analyzes your repository, installs dependencies, writes integration code, and opens a pull request for your review.
Learn more in the Installation docs.
Approved actions
Vercel Agent is read-only by default. When a task requires write access, it presents a scoped plan and waits for your approval. With your approval, Vercel Agent can make changes directly or open a pull request, depending on the task.
Learn more about Vercel Agent Permissions and GitHub Operations.
Get started
Select Agent in the top-right corner of the dashboard to start a dashboard chat conversation or configure other Vercel Agent capabilities:
Pricing and privacy
Vercel Agent charges for paid work based on the tokens used. See Vercel Agent pricing for included usage, rates, and cost tracking.
Cross-link map: Vercel Agent (/docs/agent)From the Vercel docs graph (built 2026-09-21T05:26:59.511Z), spanning vercel.com docs + KB, nextjs.org, ai-sdk.dev, and other Vercel documentation sites. Full graph as JSON: https://vercel.com/docs/graph.jsonSemantically closest pagesThe Complete Guide to Vercel Agent — Learn what Vercel Agent does, how to set up Code Review, Investigation, Chat, and Installation, and what each feature coIntroducing the new Vercel AgentAn expanded Vercel Agent: chat, investigations, and approved actions, now in public betaInstallation — Let AI automatically install Web Analytics and Speed Insights in your appVercel Agent Pricing — Understand Vercel Agent pricing and how to track costsThis page links to (4)Installation — Let AI automatically install Web Analytics and Speed Insights in your appInvestigation — Let AI investigate your error alerts to help you debug fasterCode Review — Get automatic AI-powered code reviews on your pull requestsVercel Agent Pricing — Understand Vercel Agent pricing and how to track costsPages that link here (18)By site: vercel-changelog (6) · vercel-kb (7) · vercel-docs (5)From vercel-changelogAn expanded Vercel Agent: chat, investigations, and approved actions, now in public betaApply code suggestions from Vercel Agent with one clickAutomatic build fix suggestions with Vercel AgentNative Deployment Checks are now availableOn-demand Vercel Agent code reviewsVercel Agent has updated pricingFrom vercel-kbUsing Vercel Agent to review pull requests — Set up Vercel Agent Code Review to automatically review pull requests, apply validated fixes, request reviews with @vercVercel vs Akamai — A detailed guide to Vercel vs Akamai: compute models, AI infrastructure, framework support, media streaming, CDN capabilVercel vs Fastly — A detailed guide to Vercel vs Fastly: full-stack application platform vs edge infrastructure layer, covering framework sVercel vs Netlify — A detailed guide to Vercel vs Netlify: runtimes, compute architecture, AI infrastructure, security, and when to choose eVercel vs Northflank — A detailed guide to Vercel vs Northflank: Fluid compute, CDN and caching, container image functions, security defaults,Vercel vs Railway — A detailed guide to Vercel vs Railway: serverless vs always-on containers, container images via Dockerfile.vercel, frameVercel vs Render — A detailed guide to Vercel vs Render: compute models, AI infrastructure, Docker and container image support, backgroundFrom vercel-docsTools — Available tools in Vercel MCP for searching docs, managing teams, projects, deployments, Web Analytics, runtime logs andCode Review — Get automatic AI-powered code reviews on your pull requestsGlossary — Learn about the terms and concepts used in Vercel's products and documentation.Products — Browse Vercel products for building, deploying, securing, observing, and scaling web applications.Projects overview — A project is where you deploy and operate frontend apps, APIs, backends, containers, and agent workloads on Vercel.
For information about data access, staff review, product improvement, retention, and deletion, see the Chat, Vercel Agent Permissions, and Privacy Notice documentation.
Can you trust our partners?
Previous
- Dashboard chat: Ask questions and investigate issues from your dashboard.
- Slack: Work with Vercel Agent from a supported Slack conversation.
- Code Review: Configure automatic pull request reviews.
- Investigations: Enable automatic alert investigations.
- Installation: Install supported Vercel products through a pull request.
Microfrontends
Was this helpful?
