Integrations/Sentry

Control what your AI agents do in Sentry.

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

Request early accessSee how it works →
Sentry
Triage Agent
Issues Sentry areaOffReadFull use
Releases Sentry areaOffReadFull use
Members Sentry areaOffReadFull use
Manage projects and members
What agents can do

Set what each agent can do across your Sentry org.

Each area of Sentry, like issues, releases, or members, 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 Sentry org.
Read
Read-only
The agent can read issues, events, and releases in that area. It can't change anything.
Full use
Resolve and update
The agent can resolve and assign issues in that area.

Some actions stay off until explicitly turned on

Each one removes projects or releases for good or changes who has access, so it could override the limits set elsewhere.

Creating or deleting projectsRemoving organization membersDeleting releases
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 Sentry a single time. Bollard AI lays out the areas of your org, 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, resolve, and assign issues in a single area
Example

An error triage agent.

A triage agent resolves and assigns issues and can read releases, but it can't remove members or delete projects.

Issues Sentry areaOffReadFull use
Releases Sentry areaOffReadFull use
Members Sentry areaOffReadFull use

Manage access

ALLOWEDTriage Agent resolved an issue in Issues
ALLOWEDTriage Agent read a record in Releases
BLOCKEDTriage Agent tried to open Members, 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 Sentry, so they never hold your Sentry keys and never reach Sentry directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and removing members or projects 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 Sentry 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

Sentry, answered.

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