Integrations/Guru
G

Control what your AI agents do in Guru.

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

Request early accessSee how it works →
GGuru
Knowledge Agent
Cards Knowledge areaOffReadFull use
Collections Knowledge areaOffReadFull use
Groups Knowledge areaOffReadFull use
Delete cards and folders
What agents can do

Set what each agent can do across your knowledge base.

Each area of Guru, like cards, collections, or groups, 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 knowledge base.
Read
Read-only
The agent can read cards and collections in that area. It can't change anything.
Full use
Create and update
The agent can create and update cards in that area.

Some actions stay off until explicitly turned on

Each one removes knowledge for good or changes who can reach it, so it could override the limits set elsewhere.

Deleting cards or foldersDeleting commentsChanging groups and access
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 Guru a single time. Bollard AI lays out the areas of your knowledge base, 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 cards in a single area
Example

A knowledge base agent.

A knowledge agent updates cards and can read your collections, but it can't delete cards or change groups.

Cards Knowledge areaOffReadFull use
Collections Knowledge areaOffReadFull use
Groups Knowledge areaOffReadFull use

Manage access

ALLOWEDKnowledge Agent updated a record in Cards
ALLOWEDKnowledge Agent read a Collection
BLOCKEDKnowledge Agent tried to open Groups, 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 Guru, so they never hold your Guru keys and never reach Guru directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and deleting knowledge 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 Guru 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 card or collection, and the decision. The record is readable and can't be edited after the fact.

Questions

Guru, answered.

Does connecting Guru hand Bollard AI your whole knowledge base?+
Only the areas you allow. An admin connects your Guru, and you decide which areas, like cards or collections, each agent can reach. Bollard AI doesn't browse or copy your knowledge base. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete knowledge or change access?+
Not unless you turn it on. Deleting cards and folders, and changing groups and access, are held off by default, so an agent can write and read where you allow without ever removing knowledge or changing who can reach it, 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 Guru 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 Guru, and the blocked attempt lands in the activity record with the reason.
How do we connect Guru?+
An admin connects the company's Guru once. Bollard AI seals the connection and lays out the areas of your knowledge base 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 Guru, 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 →