Integrations/Opsgenie

Control what your AI agents do in Opsgenie.

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

Request early accessSee how it works →
Opsgenie
On-Call Agent
Alerts Account areaOffReadFull use
Schedules Account areaOffReadFull use
Users Account areaOffReadFull use
Delete alerts and change schedules
What agents can do

Set what each agent can do across your account.

Each area of Opsgenie, like alerts, schedules, or users, 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 account.
Read
Read-only
The agent can read alerts and on-call schedules in that area. It can't change anything.
Full use
Triage and update
The agent can acknowledge and update alerts in that area.

Some actions stay off until explicitly turned on

Each one removes alerts for good or changes who gets paged, so it could override the limits set elsewhere.

Deleting alertsChanging schedules and escalationsRemoving users
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 Opsgenie a single time. Bollard AI lays out the areas of your account, 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, acknowledge, and update alerts in a single area
Example

An on-call triage agent.

An on-call agent acknowledges alerts and can read your schedules, but it can't change who is paged or remove users.

Alerts Account areaOffReadFull use
Schedules Account areaOffReadFull use
Users Account areaOffReadFull use

Manage access

ALLOWEDOn-Call Agent acknowledged an Alert
ALLOWEDOn-Call Agent read the Schedules
BLOCKEDOn-Call Agent tried to open Users, 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 Opsgenie, so they never hold your Opsgenie keys and never reach Opsgenie directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Opsgenie. 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 who gets paged 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 Opsgenie 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 alert or schedule, and the decision. The record is readable and can't be edited after the fact.

Questions

Opsgenie, answered.

Does connecting Opsgenie hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Opsgenie, and you decide which areas, like alerts or schedules, each agent can 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 delete alerts or change who gets paged?+
Not unless you turn it on. Deleting alerts and changing schedules and escalations are held off by default, so an agent can acknowledge and read where you allow without ever removing alerts or changing who is paged, 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 Opsgenie 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 Opsgenie, and the blocked attempt lands in the activity record with the reason.
How do we connect Opsgenie?+
An admin connects the company's Opsgenie once. Bollard AI seals the connection and lays out the areas of your account 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 Opsgenie, 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 →