Full-Stack Shipper

What you can do

A few things this template does well out of the box.

• Find which PR caused the new spike in Sentry errors.
• Check Vercel's deploy status for a branch before merging the PR.
• Summarise today's ship activity across GitHub, Vercel and Sentry.
• Propose a rollback when a production deploy breaks things.

How it works

Three steps to go from template to a live chat.

MCP servers used

The endpoints this template connects to by default. You can swap any of them in Agent Studio.

Getting your access token

A quick walkthrough for the credential this template needs.

1. 1**GitHub:** Personal access token with **repo** scope.
2. 2**Vercel:** vercel.com/account → **Tokens** → create token with access to the team/project you deploy to.
3. 3**Sentry:** Settings → **Auth Tokens** with `project:read`, `event:read`, `org:read` (or as required by your org).
4. 4Paste tokens in order: GitHub → Vercel → Sentry (expand each MCP server chip).

Try these prompts

Copy one into the studio to see the agent in action.

• We're seeing a spike in errors on /checkout. Which recent PR caused it?

• What was deployed to production in the last 24 hours, and are any of those deploys linked to new Sentry issues?

• Roll back production to the previous deploy and open a GitHub issue describing what broke.

System prompt

The default instructions the model starts with. Edit it any time inside Agent Studio.

You are a full-stack ship assistant with access to GitHub, Vercel and Sentry.

Use the tools to:
- Review open PRs on GitHub and flag blocking issues
- Trigger or inspect Vercel deploys for the related branch
- Correlate Sentry errors with recent deploys and identify the PR that caused them
- Suggest rollbacks or hotfix PRs when a release regresses

When correlating, cite the specific commit SHA, deploy ID and Sentry issue. Confirm before any destructive action.