Integrations/Canny
C

Control what your AI agents do in Canny.

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

Request early accessSee how it works →
CCanny
Feedback Agent
Posts Feedback areaOffReadFull use
Boards Feedback areaOffReadFull use
Categories Feedback areaOffReadFull use
Delete and merge posts
What agents can do

Set what each agent can do across your feedback.

Each area of Canny, like posts, boards, or categories, 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 feedback.
Read
Read-only
The agent can read posts and votes in that area. It can't change anything.
Full use
Create and update
The agent can create and update posts in that area.

Some actions stay off until explicitly turned on

Each one removes or combines feedback for good, so it could override the limits set elsewhere.

Deleting or merging postsDeleting commentsChanging boards and categories
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 Canny a single time. Bollard AI lays out the areas of your feedback, 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 posts in a single area
Example

A feedback triage agent.

A feedback agent updates posts and can read your boards, but it can't delete or merge posts.

Posts Feedback areaOffReadFull use
Boards Feedback areaOffReadFull use
Categories Feedback areaOffReadFull use

Manage access

ALLOWEDFeedback Agent updated a record in Posts
ALLOWEDFeedback Agent read a Board
BLOCKEDFeedback Agent tried to open Categories, 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 Canny, so they never hold your Canny keys and never reach Canny directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Canny. 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 feedback 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 Canny 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 post or board, and the decision. The record is readable and can't be edited after the fact.

Questions

Canny, answered.

Does connecting Canny hand Bollard AI your whole feedback?+
Only the areas you allow. An admin connects your Canny, and you decide which areas, like posts or boards, each agent can reach. Bollard AI doesn't browse or copy your feedback. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete or merge feedback?+
Not unless you turn it on. Deleting and merging posts, and deleting comments, are held off by default, so an agent can triage and update where you allow without ever removing feedback, 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 Canny 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 Canny, and the blocked attempt lands in the activity record with the reason.
How do we connect Canny?+
An admin connects the company's Canny once. Bollard AI seals the connection and lays out the areas of your feedback 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 Canny, 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 →