Integrations/dbt
dbt

Control what your AI agents do in dbt.

Let your team build AI agents for dbt. Bollard AI controls what each one can do, and running jobs stays off by default.

Request early accessSee how it works →
dbtdbt
Analytics Engineering Agent
Models Account areaOffReadFull use
Runs Account areaOffReadFull use
Jobs Account areaOffReadFull use
Trigger job runs
What agents can do

Set what each agent can do across your account.

Each area of dbt, like models, runs, or jobs, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and running jobs is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read models and past runs in that area. It can't change or run anything.
Full use
Create and update
The agent can create and update models in that area.

Some actions stay off until explicitly turned on

Each one runs against your warehouse or changes how jobs run, so it could override the limits set elsewhere.

Triggering job runsChanging job schedulesDeleting jobs
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 dbt 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 models in a single area
Example

An analytics engineering agent.

An analytics agent updates models and can read past runs, but it can't trigger a job run or change a schedule.

Models Account areaOffReadFull use
Runs Account areaOffReadFull use
Jobs Account areaOffReadFull use

Manage access

ALLOWEDAnalytics Engineering Agent updated a record in Models
ALLOWEDAnalytics Engineering Agent read a Run
BLOCKEDAnalytics Engineering Agent tried to trigger a job run, 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 dbt, so they never hold your dbt keys and never reach dbt directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and running jobs 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 dbt 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 model or job, and the decision. The record is readable and can't be edited after the fact.

Questions

dbt, answered.

Does connecting dbt hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your dbt, and you decide which areas, like models or runs, 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 run jobs against our warehouse?+
Not unless you turn it on. Triggering job runs and changing schedules are held off by default, so an agent can manage models and read past runs without ever running against your warehouse, 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 dbt 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 dbt, and the blocked attempt lands in the activity record with the reason.
How do we connect dbt?+
An admin connects the company's dbt 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 dbt, 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 →