Integrations/Linear

Control what your AI agents do in Linear.

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

Request early accessSee how it works →
Linear
Triage Agent
Issues Workspace areaOffReadFull use
Projects Workspace areaOffReadFull use
Settings Workspace areaOffReadFull use
Change workspace settings
What agents can do

Set what each agent can do across your Linear workspace.

Each area of Linear, like issues, projects, or settings, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see that part of your workspace.
Read
Read-only
The agent can read issues and projects in that area. It can't change anything.
Full use
Create and update
The agent can create and update issues and comments in that area.

Some actions stay off until explicitly turned on

Each one removes work for good or changes how your workspace runs, so it could override the limits set elsewhere.

Changing workspace and team settingsDeleting issues and projectsManaging members and access
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 Linear a single time. Bollard AI lays out the areas of your workspace, and anything you don't allow 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, and update records in a single area
Example

An issue triage agent.

A triage agent creates and updates issues and can read your projects, but it can't change workspace settings.

Issues Workspace areaOffReadFull use
Projects Workspace areaOffReadFull use
Settings Workspace areaOffReadFull use

Manage access

ALLOWEDTriage Agent created an issue in Issues
ALLOWEDTriage Agent read a record in Projects
BLOCKEDTriage Agent tried to open Settings, 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 Linear, so they never hold your Linear keys and never reach Linear directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and changing workspace settings 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 Linear 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 issue or project, and the decision. The record is readable and can't be edited after the fact.

Questions

Linear, answered.

Does connecting Linear hand Bollard AI your whole workspace?+
Only the areas you allow. An admin connects your Linear, and you decide which areas, like issues or projects, each agent can reach. Bollard AI doesn't browse or copy your workspace. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete issues or change settings?+
Not unless you turn it on. Deleting issues and projects, and changing workspace settings, are held off by default, so an agent can triage and update work where you allow without ever removing it or reshaping the workspace, 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 Linear 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 Linear, and the blocked attempt lands in the activity record with the reason.
How do we connect Linear?+
An admin connects the company's Linear once. Bollard AI seals the connection and lays out the areas of your workspace 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 Linear, 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 →