Integrations/New Relic

Control what your AI agents do in New Relic.

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

Request early accessSee how it works →
New Relic
Observability Agent
Dashboards Account areaOffReadFull use
Entities Account areaOffReadFull use
Alerts Account areaOffReadFull use
Delete dashboards and alerts
What agents can do

Set what each agent can do across your account.

Each area of New Relic, like dashboards, entities, or alerts, 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 entities and query results in that area. It can't change anything.
Full use
Create and update
The agent can build dashboards and run queries in that area.

Some actions stay off until explicitly turned on

Each one removes monitoring for good or silences your alerts, so it could override the limits set elsewhere.

Deleting dashboards or workloadsDeleting alert policies and conditionsChanging synthetics
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 New Relic 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, build, and query in a single area
Example

A monitoring agent.

An observability agent builds dashboards and can read your entities, but it can't delete alert policies or change synthetics.

Dashboards Account areaOffReadFull use
Entities Account areaOffReadFull use
Alerts Account areaOffReadFull use

Manage access

ALLOWEDObservability Agent built a Dashboard
ALLOWEDObservability Agent read an Entity
BLOCKEDObservability Agent tried to change Alerts, 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 New Relic, so they never hold your New Relic keys and never reach New Relic directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and silencing alerts 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 New Relic 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 dashboard or entity, and the decision. The record is readable and can't be edited after the fact.

Questions

New Relic, answered.

Does connecting New Relic hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your New Relic, and you decide which areas, like dashboards or entities, 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 monitoring or silence alerts?+
Not unless you turn it on. Deleting dashboards and workloads, and deleting alert policies, are held off by default, so an agent can build and read where you allow without ever removing monitoring or silencing alerts, 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 New Relic 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 New Relic, and the blocked attempt lands in the activity record with the reason.
How do we connect New Relic?+
An admin connects the company's New Relic 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 New Relic, 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 →