Integrations/Productboard

Control what your AI agents do in Productboard.

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

Request early accessSee how it works →
Productboard
Feedback Triage Agent
Notes Product areaOffReadFull use
Features Product areaOffReadFull use
Objectives Product areaOffReadFull use
Delete notes and features
What agents can do

Set what each agent can do across your product workspace.

Each area of Productboard, like notes, features, or objectives, 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 workspace.
Read
Read-only
The agent can read features and feedback in that area. It can't change anything.
Full use
Create and update
The agent can create and update notes in that area.

Some actions stay off until explicitly turned on

Each one removes feedback or features for good, or changes how progress is tracked, so it could override the limits set elsewhere.

Deleting notes or featuresChanging feature statuses in bulkRemoving webhooks
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 Productboard a single time. Bollard AI lays out the areas of your workspace, 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 notes in a single area
Example

A feedback triage agent.

A triage agent files notes and can read your features, but it can't delete notes or change statuses in bulk.

Notes Product areaOffReadFull use
Features Product areaOffReadFull use
Objectives Product areaOffReadFull use

Manage access

ALLOWEDFeedback Triage Agent filed a record in Notes
ALLOWEDFeedback Triage Agent read a Feature
BLOCKEDFeedback Triage Agent tried to open Objectives, 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 Productboard, so they never hold your Productboard keys and never reach Productboard directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Productboard. 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 or features 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 Productboard 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 note or feature, and the decision. The record is readable and can't be edited after the fact.

Questions

Productboard, answered.

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