Expanded Vercel Agent with dashboard chat, investigations, and approved actions in public beta
Vercel Agent now runs in your dashboard with expanded capabilities including chat for project questions, investigations to diagnose production issues, and approved actions to take remediation steps. Agent has access to deployment data, logs, metrics, and repositories, and operates under user permissions with approval required for elevated actions.
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 app, it has access to the signals around it: deployments, logs, metrics, project configuration, usage, and connected repositories. That context is what turns a question into an answer and a problem into a fix.
What's new in this beta:
Agent code review works as it does today: Sandbox-validated suggestions on your pull requests, now one capability within a broader Agent.
You stay in control
Vercel Agent runs under its own identity and is bounded by the requesting user's permissions. It is read-only by default. When a task requires elevated access, Agent requests a scoped plan and makes no changes until you approve. Generated code runs in Vercel Sandbox before it reaches production, and elevated actions are attributed to the agent, the requester, and the approver.
Availability
Dashboard chat, investigations, and approved actions are in public beta for Pro and Enterprise teams. Rollout will be gradual. If you don't have access yet, you can request it in .this form
Simple requests, like finding a setting, explaining a DNS warning, or answering a docs question, are free for a limited number of messages during the beta. Requests that require Agent to investigate, plan, or write code are billed on demand: provider tokens at the underlying rate with no markup, plus a Vercel Token Rate of $0.25 per million tokens. This rate now also applies to Agent code review.
Learn more in the .documentation
ask questions about your projects and get answers grounded in your real deployment data, right from the dashboard.Dashboard chat:
: point Agent at a failed deployment, a runtime error, or a cost spike, and it traces the cause and recommends a fix.Production investigations
: with your sign-off, Agent can open a PR, roll back, or update a config to remediate an issue.Approved actions
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
OpenAI Decisions API now available on AI Gateway
OpenAI's Decisions API is now accessible through Vercel's AI Gateway with an OpenAI-compatible endpoint, enabling decision models to answer typed questions and return probabilities, choices, and scores for routing, triage, and guardrails use cases. Support is available across the OpenAI SDK, AI SDK, HTTP API, and CLI with the latest versions.
Timestamp attributes now supported in Vercel Flags
Vercel Flags now supports timestamp attributes for entities, allowing you to create time-based targeting rules. Use this feature to run limited-time campaigns, show content between specific dates, or target users based on registration date.
Glyph Cluster now available in stealth on AI Gateway
Glyph Cluster, a reasoning model for coding and long-context analysis, is now available as a stealth model on Vercel's AI Gateway for Pro and Enterprise plan teams with purchased AI Gateway credits at no cost during the stealth period. The model supports function calling, streams responses, and can be accessed via AI SDK, OpenAI-compatible APIs, and coding agents.