Hire an AI Vercel release and deployment checker

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A version number worked out from your commits, and a changelog grouped into added, changed and fixed
• A go or no-go call with each blocker listed
• A live link on Vercel
• A report that compares the live site with the release you tagged

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are releasing a new version and cannot afford a bad deploy.

• Release preparer result. The version bump with the reason, a changelog grouped into added, changed and fixed, and the tag to use.
• Ship readiness gate result. The checks that ran, each blocker listed, and a go or no-go verdict.
• Vercel publisher result. A preview link first, then the live link once you agree to go to production.
• Deploy verifier result. The build the live site shows, your tag, and whether they match.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• The version follows from the commits, and the reason for the bump is written down.
• The changelog lists only changes that are in the commits.
• Every blocker is either fixed or has a clear reason it can wait.
• The proof compares something unique to this release, such as a build id or commit hash, not only "the page loads".
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Set the version and write the changelog. Finds your version files, reads the commits since the last tag, picks the bump and writes the changelog.
• Review, merge and tag. This one is yours. Check the bump and the notes, merge them and tag the release.
• Get a go or no-go. Runs your build, tests, secrets and config checks, asks about what a tool cannot see and lists the blockers.
• Fix the blockers. This one is yours. Fix every blocker. After a no-go, run the check again until it says go.
• Deploy to Vercel. Deploys a preview first, promotes it to production when you agree and returns the live link.
• Prove it is the new build. Checks for the quiet ways a deploy can pass while the old version stays up, reads the build shown by the live site and compares it with your tag.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id release-a-new-version-and-prove-it-is-live only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/release-a-new-version-and-prove-it-is-live/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your project (a folder or repo with its git history and tags)
• Your Vercel account, signed in on your computer
• Your build and test commands (optional)

Functions and deliverables

• Vercel release and deployment checker: Share your project, release access and approvals. Get a version, changelog, readiness decision and verified Vercel deployment when all gates pass.
  • A version number worked out from your commits, and a changelog grouped into added, changed and fixed
  • A go or no-go call with each blocker listed
  • A live link on Vercel
  • A report that compares the live site with the release you tagged
• Software release preparer: Share your project. Review a version and changelog proposal, then confirm file updates and a release tag.
  • The version number updated in your version files
  • A changelog entry grouped into Features, Fixes and Documentation
  • A release commit and an annotated tag
  • A GitHub Release page, if you ask for one
  • A dry-run preview of every change
  Source: Jim Liu.
• Code release readiness checker: Run code checks before release. Get pass, fail and manual items, with blockers grouped by severity.
  • A pass, fail, skip or manual result for each check
  • A list of blockers with file locations
  • A go or no-go verdict
  • A prompt to re-scan after changes
  Source: Alireza Rezvani.
• Vercel publisher: Say "deploy my app". Get it live on Vercel as a preview or production site, with the link.
  • A preview link
  • A claim link when deploying without login
  • A production deploy on request
  • Troubleshooting for network errors
  Source: OpenAI.
• Release readiness and live version checker: Check common blockers before a release. Then compare the live version with the one you meant to ship.
  • Pre-flight checklist results
  • Silent-failure checks
  • Proof the live version is new
  • Clear ship or hold verdict
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• You are releasing a new version and cannot afford a bad deploy.
• You have shipped, then found the old version still live.
• Your release notes and version numbers are guesses, not worked out from the commits.

Limits to check before starting

• You have no git tags yet: do a first release by hand, so the steps have a commit range to read.
• You only want to check a site that is already live: use a person or a simple page check, not this release workflow.
• You host on something other than Vercel: swap step 3 for a Netlify or Cloudflare deploy planner, or deploy by hand.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Sign in to Vercel first. The deploy step asks for a preview first and production only after you agree.
• Do your two steps, which are to merge and tag, then to fix blockers.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/release-a-new-version-and-prove-it-is-live for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.