Integrations/Confluence

Control what your AI agents do in Confluence.

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

Confluence
Docs Agent
Engineering SpaceOffReadFull use
Product SpaceOffReadFull use
HR SpaceOffReadFull use
Delete pages
What agents can do

Set what each agent can do in every space.

Each space gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see the space or that it exists.
Read
Read-only
The agent can read the pages and blog posts in that space. It can't change anything.
Full use
Create and update
The agent can create and update pages in that space.

Some actions stay off until explicitly turned on

Each one removes pages for good or changes who can reach a space, so it could override the limits set on individual spaces.

Deleting pages or blog postsDeleting attachmentsChanging space permissions
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 Confluence a single time and chooses which spaces it covers. Any space left out 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 pages in a single space
Example

A documentation agent.

A docs agent updates pages in Engineering and can read Product, but it can't open the HR space or delete a page.

Engineering SpaceOffReadFull use
Product SpaceOffReadFull use
HR SpaceOffReadFull use

Manage access

ALLOWEDDocs Agent updated a page in Engineering
ALLOWEDDocs Agent read a page in Product
BLOCKEDDocs Agent tried to open the HR space, 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 Confluence, so they never hold your Confluence keys and never reach Confluence directly.

Everything runs through Bollard AI

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

Denied by default

Every space starts off-limits, and deleting pages 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 Confluence 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 space or page, and the decision. The record is readable and can't be edited after the fact.

Questions

Confluence, answered.

Does connecting Confluence hand Bollard AI all your spaces?+
Only what's connected. An admin chooses which spaces Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your pages. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent delete pages or change who can reach a space?+
Not unless you turn it on. Deleting pages and blog posts, and changing space permissions, are held off by default, so an agent can write where you allow without ever removing pages or exposing a space, 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 Confluence 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 Confluence, and the blocked attempt lands in the activity record with the reason.
How do we connect Confluence?+
An admin connects the company's Confluence once. Bollard AI seals the connection and builds the list of spaces 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 Confluence, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.