An expanded Vercel Agent: chat, investigations, and approved actions, now in public beta
Vercel Agent now investigates production issues, writes code, and takes action—all with your approval. Public beta starts today.
Why it matters
Vercel is shipping an AI agent embedded in its deployment platform that can diagnose production problems, generate fixes, and execute remediation—turning infrastructure observability into autonomous action. This is the application layer betting that AI agents tied to platform context (logs, deployments, metrics) are more useful than generic LLM chat.
The key facts
8 to knowVercel Agent in public beta with dashboard chat, investigations, and approved actions
Agent has access to deployments, logs, metrics, project config, usage, and repositories
Read-only by default; elevated actions require user approval before execution
Code review sandbox-validated before production deployment
Available to Pro and Enterprise teams with gradual rollout
Pricing: simple requests free (limited messages in beta); investigation/planning/code-writing billed at $0.25 per million tokens plus provider token costs
Agent actions attributed to agent, requester, and approver for audit trail
Capabilities include: dashboard chat, production issue tracing, PR creation, rollbacks, config updates
Go to the source
Vercel Blogvercel.com
Publisher excerpt: Today, we're launching expanded capabilities for Vercel Agent in public beta. Vercel Agent now lives in your dashboard and can investigate production issues, answer questions about your projects, and take action on your behalf. Because Agent runs inside the platform that deploys and serves your…