Integrations/Railway

Control what your AI agents do in Railway.

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

Request early accessSee how it works →
Railway
Deploy Agent
marketing ProjectOffReadFull use
api ProjectOffReadFull use
payments ProjectOffReadFull use
Deploy to production
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 services and deployments in that project. It can't change anything.
Full use
Manage and update
The agent can create services and update settings in that project.

Some actions stay off until explicitly turned on

Each one changes what is live, removes a service for good, or exposes its config, so it could override the limits set on individual projects.

Triggering production deploymentsDeleting services or projectsChanging variables
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 Railway 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, create services, and update settings in a single project
Example

A deploy management agent.

A deploy agent updates services in marketing and can read api, but it can't open the payments project or deploy to production.

marketing ProjectOffReadFull use
api ProjectOffReadFull use
payments ProjectOffReadFull use

Manage access

ALLOWEDDeploy Agent updated a service in marketing
ALLOWEDDeploy Agent read a deployment in api
BLOCKEDDeploy Agent tried to open the payments 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 Railway, so they never hold your Railway keys and never reach Railway directly.

Everything runs through Bollard AI

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

Denied by default

Every project starts off-limits, and deploying to production 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 Railway 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 service, and the decision. The record is readable and can't be edited after the fact.

Questions

Railway, answered.

Does connecting Railway 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 deploy to production or delete a service?+
Not unless you turn it on. Triggering production deployments and deleting services or projects are held off by default, so an agent can manage and read where you allow without ever changing what is 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 Railway 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 Railway, and the blocked attempt lands in the activity record with the reason.
How do we connect Railway?+
An admin connects the company's Railway 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 Railway, 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 →