Integrations/Aha!
A

Control what your AI agents do in Aha!.

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

Request early accessSee how it works →
AAha!
Roadmap Agent
Features Roadmap areaOffReadFull use
Ideas Roadmap areaOffReadFull use
Releases Roadmap areaOffReadFull use
Delete roadmap work
What agents can do

Set what each agent can do across your roadmap.

Each area of Aha!, like features, ideas, or releases, 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 roadmap.
Read
Read-only
The agent can read features and ideas in that area. It can't change anything.
Full use
Create and update
The agent can create and update features in that area.

Some actions stay off until explicitly turned on

Each one removes roadmap work for good or reshapes how your roadmap is built, so it could override the limits set elsewhere.

Deleting features or initiativesDeleting releases or epicsChanging the roadmap structure
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 Aha! a single time. Bollard AI lays out the areas of your roadmap, 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 features in a single area
Example

A roadmap tidy-up agent.

A roadmap agent updates features and can read your ideas, but it can't delete releases or reshape the roadmap.

Features Roadmap areaOffReadFull use
Ideas Roadmap areaOffReadFull use
Releases Roadmap areaOffReadFull use

Manage access

ALLOWEDRoadmap Agent updated a record in Features
ALLOWEDRoadmap Agent read an Idea
BLOCKEDRoadmap Agent tried to open Releases, 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 Aha!, so they never hold your Aha! keys and never reach Aha! directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Aha!. 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 roadmap work 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 Aha! 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 feature or idea, and the decision. The record is readable and can't be edited after the fact.

Questions

Aha!, answered.

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