# Vercel — Introducing the new Vercel Agent

- Company: Vercel (vercel.com)
- Announced: 2026-07-21T04:00:00+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://vercel.com/blog/vercel-agent
- Record: https://forck.live/items/20685-introducing-the-new-vercel-agent
- Subject: v0 / AI SDK / AI Gateway

Vercel expanded its Agent from triaging alerts and reviewing pull requests to a dashboard-based tool that investigates production issues, answers project questions, and takes approved actions. The agent operates under its own identity, is read-only by default, and uses a plan-to-permission model where it requests scoped access for each task, dropping back to read-only after completion. Generated code runs in an ephemeral Firecracker microVM sandbox isolated from live systems.

## Evidence

Verbatim from https://vercel.com/blog/vercel-agent:

> Vercel Agent is read-only by default. To do something more, like rolling back a deploy, changing a config, or clearing a cache, it proposes a plan and requests access scoped specifically to that plan. You approve it, the agent does the work, then drops back to read-only as soon as the plan is completed.

---

Record: https://forck.live/items/20685-introducing-the-new-vercel-agent
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md