Integrations/OpenAI

Control what your AI agents do in OpenAI.

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

Request early accessSee how it works →
OpenAI
Drafting Agent
Responses Account areaOffReadFull use
Models Account areaOffReadFull use
Files Account areaOffReadFull use
Start fine-tuning jobs
What agents can do

Set what each agent can do in your OpenAI account.

Each area of your OpenAI account, like responses, models, or files, 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 OpenAI account.
Read
Read-only
The agent can read available models and account settings. It can't change anything.
Full use
Generate and use
The agent can generate responses and use the models in that area.

Some actions stay off until explicitly turned on

Each one runs up cost, removes data, or trains on your files, so it could override the limits set elsewhere.

Starting fine-tuning and training jobsDeleting files and dataGenerating images, audio, or video
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 OpenAI account a single time. Bollard AI lays out the areas of the 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 useGenerate responses and use models in a single area
Example

A content drafting agent.

A drafting agent generates text responses and can read the available models, but it can't start training jobs or open your uploaded files.

Responses Account areaOffReadFull use
Models Account areaOffReadFull use
Files Account areaOffReadFull use

Manage access

ALLOWEDDrafting Agent generated a response in Responses
ALLOWEDDrafting Agent read the available Models
BLOCKEDDrafting Agent tried to open Files, 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 OpenAI, so they never hold your OpenAI keys and never reach OpenAI directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and starting training 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 OpenAI 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 file, and the decision. The record is readable and can't be edited after the fact.

Questions

OpenAI, answered.

Does connecting OpenAI hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your OpenAI account, and you decide which areas, like responses or models, 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 up cost or train on our files?+
Not unless you turn it on. Starting fine-tuning and training jobs is held off by default, so an agent can generate responses where you allow without ever kicking off costly training on your 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 OpenAI 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 OpenAI, and the blocked attempt lands in the activity record with the reason.
How do we connect OpenAI?+
An admin connects the company's OpenAI account once. Bollard AI seals the connection and lays out the areas of the 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 OpenAI, 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 →