Vercel Agent

Vercel Agent is a suite of AI-powered development tools built to speed up your workflow. Instead of spending hours debugging production issues or waiting for code reviews, Agent helps you catch problems faster and resolve incidents quickly.

Agent works because it already understands your application. Vercel builds your code, deploys your functions, and serves your traffic. Agent uses this deep context about your codebase, deployment history, and runtime behavior to provide intelligent assistance right where you need it.

Everything runs on Vercel's AI Cloud, infrastructure designed specifically for AI workloads. This means Agent can use secure sandboxes to reproduce issues, access the latest models, and provide reliable results you can trust.

Get automatic code reviews on every pull request. Code Review analyzes your changes, identifies potential issues, and suggests fixes you can apply directly.

What it does:

• Performs multi-step reasoning to identify security vulnerabilities, logic errors, and performance issues
• Generates patches and runs them in secure sandboxes with your real builds, tests, and linters
• Only suggests fixes that pass validation checks, allowing you to apply specific code changes with one click

Learn more in the Code Review docs.

When error alerts fire, Vercel Agent Investigations can analyze what's happening to help you debug faster. Instead of manually digging through logs and metrics, AI does the analysis and shows you what might be causing the issue.

What it does:

• Queries logs and metrics around the time of the alert
• Looks for patterns and correlations that might explain the problem
• Provides insights about potential root causes

Learn more in the Agent Investigation docs.

You can enable Vercel Agent in the Agent tab of your dashboard. Setup varies by feature:

• Code Review: You'll need to configure which repositories to review and whether to review draft PRs. See Code Review setup for details.
• Agent Investigation: This requires Observability Plus and in order to run investigations automatically, you'll need to enable Vercel Agent Investigations. See Investigation setup to get started.

Vercel Agent uses a credit-based system. Each review or investigation costs a fixed $0.30 USD plus token costs billed at the Agent's underlying AI provider's rate, with no additional markup. Pro teams can redeem a $100 USD promotional credit when enabling Agent.

You can purchase credits and enable auto-recharge in the Agent tab of your dashboard. For complete pricing details, credit management, and cost tracking information, see Vercel Agent Pricing.

Vercel Agent doesn't store or train on your data. It only uses LLMs from providers on our subprocessor list, and we have agreements in place that don't allow them to train on your data.