Integrations/Grafana

Control what your AI agents do in Grafana.

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

Request early accessSee how it works →
Grafana
Ops Agent
Dashboards Account areaOffReadFull use
Data sources Account areaOffReadFull use
Alerting Account areaOffReadFull use
Delete dashboards and data sources
What agents can do

Set what each agent can do across your account.

Each area of Grafana, like dashboards, data sources, or alerting, 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 dashboards and data sources in that area. It can't change anything.
Full use
Create and update
The agent can create and update dashboards in that area.

Some actions stay off until explicitly turned on

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

Deleting dashboards or foldersDeleting data sourcesChanging alert rules
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 Grafana 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, create, and update dashboards in a single area
Example

A dashboards agent.

An ops agent builds dashboards and can read your data sources, but it can't delete data sources or change alert rules.

Dashboards Account areaOffReadFull use
Data sources Account areaOffReadFull use
Alerting Account areaOffReadFull use

Manage access

ALLOWEDOps Agent created a Dashboard
ALLOWEDOps Agent read the Data sources
BLOCKEDOps Agent tried to change Alerting, 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 Grafana, so they never hold your Grafana keys and never reach Grafana directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Grafana. 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 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 Grafana 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 data source, and the decision. The record is readable and can't be edited after the fact.

Questions

Grafana, answered.

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