Integrations/Vercel

Control what your AI agents do in Vercel.

Let your team build AI agents for Vercel. Bollard AI controls what each one can do, project by project.

Request early accessSee how it works →
Vercel
Deploy Agent
marketing-site ProjectOffReadFull use
app ProjectOffReadFull use
api ProjectOffReadFull use
Read environment variables
What agents can do

Set what each agent can do in every project.

Each project gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see the project or that it exists.
Read
Read-only
The agent can read deployments and project details. It can't change anything.
Full use
Manage and update
The agent can create deployments and update settings in that project.

Some actions stay off until explicitly turned on

Each one can leak secrets, remove a project for good, or change what is live, so it could override the limits set on individual projects.

Reading or changing environment variablesDeleting projects or domainsPromoting a deployment to production
Set up & manage

Connect once. Manage everyone from there.

Connect once, then control access person by person. No new keys to hand out.

Step 1 · Set up

Connect once, company-wide

An admin connects your company's Vercel a single time and chooses which projects it covers. Any project left out stays out of reach for every agent.

Step 2 · Manage

Control access per person and agent

From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.

OffNo access
ReadRead-only
Full useRead, deploy, and update settings in a single project
Example

A preview deploy agent.

A deploy agent ships preview builds on marketing-site and can read app, but it can't open the api project or read its secrets.

marketing-site ProjectOffReadFull use
app ProjectOffReadFull use
api ProjectOffReadFull use

Manage access

ALLOWEDDeploy Agent created a preview deployment in marketing-site
ALLOWEDDeploy Agent read a deployment in app
BLOCKEDDeploy Agent tried to open the api project, denied by default

Monitor activity

The security model

Top-tier security.

Bollard AI is access control for AI agents. It sits between your agents and Vercel, so they never hold your Vercel keys and never reach Vercel directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Vercel. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every project starts off-limits, and reading secrets is held back on top of that. An agent gets in only where you've allowed it, and anything Bollard AI doesn't recognise is refused and held for review, never waved through on a guess.

Your keys stay sealed

Your Vercel keys are sealed in a vault unique to your company and never shown again. Bollard AI unlocks them only for the instant an allowed request needs it.

Activity you can read

Every attempt is recorded in plain English: who or which agent, what they tried, which project or deployment, and the decision. The record is readable and can't be edited after the fact.

Questions

Vercel, answered.

Does connecting Vercel hand Bollard AI all your projects?+
Only what's connected. An admin chooses which projects Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your account. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read our secrets or ship to production?+
Not unless you turn it on. Reading environment variables and promoting a deployment to production are held off by default, so an agent can ship previews where you allow without ever touching secrets or going live, until you explicitly allow it.
Can an agent see more than the person who owns it?+
No. An agent reaches only what its owner reaches. An explicit Off always overrides an inherited permission.
Where do our Vercel keys live?+
Sealed in an encrypted vault, behind a key unique to your company. It's never shown again once connected, and Bollard AI unseals it only for the instant an allowed request needs it.
What happens when an agent tries something it's not allowed to do?+
Bollard AI blocks the request before it reaches Vercel, and the blocked attempt lands in the activity record with the reason.
How do we connect Vercel?+
An admin connects the company's Vercel once. Bollard AI seals the connection and builds the list of projects to set rules for. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team's agents to work in Vercel, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.

Request early accessAll integrations →