Integrations/Fivetran
F

Control what your AI agents do in Fivetran.

Let your team build AI agents for Fivetran. Bollard AI controls what each one can do, and moving data stays off by default.

Request early accessSee how it works →
FFivetran
Data Pipeline Agent
Connectors Account areaOffReadFull use
Schemas Account areaOffReadFull use
Destinations Account areaOffReadFull use
Trigger syncs
What agents can do

Set what each agent can do across your account.

Each area of Fivetran, like connectors, schemas, or destinations, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and moving data is a separate switch.

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

Some actions stay off until explicitly turned on

Each one moves data between systems or removes a connector for good, so it could override the limits set elsewhere.

Triggering syncsPausing or deleting connectorsChanging destinations
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 Fivetran 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 connector settings in a single area
Example

A pipeline maintenance agent.

A pipeline agent updates connector settings and can read schemas, but it can't trigger a sync or delete a connector.

Connectors Account areaOffReadFull use
Schemas Account areaOffReadFull use
Destinations Account areaOffReadFull use

Manage access

ALLOWEDData Pipeline Agent updated a record in Connectors
ALLOWEDData Pipeline Agent read a Schema
BLOCKEDData Pipeline Agent tried to trigger a sync, 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 Fivetran, so they never hold your Fivetran keys and never reach Fivetran directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and moving data 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 Fivetran 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 connector or schema, and the decision. The record is readable and can't be edited after the fact.

Questions

Fivetran, answered.

Does connecting Fivetran hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Fivetran, and you decide which areas, like connectors or schemas, 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 move data between systems on its own?+
Not unless you turn it on. Triggering syncs, and pausing or deleting connectors, are held off by default, so an agent can manage connector settings and read schemas without ever moving data, 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 Fivetran 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 Fivetran, and the blocked attempt lands in the activity record with the reason.
How do we connect Fivetran?+
An admin connects the company's Fivetran 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 Fivetran, 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 →