Integrations/Help Scout

Control what your AI agents do in Help Scout.

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

Request early accessSee how it works →
Help Scout
Support Agent
Conversations Help desk areaOffReadFull use
Customers Help desk areaOffReadFull use
Inboxes Help desk areaOffReadFull use
Delete conversations
What agents can do

Set what each agent can do across your inbox.

Each area of Help Scout, like conversations, customers, or inboxes, 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 inbox.
Read
Read-only
The agent can read conversations and customer details. It can't change anything.
Full use
Reply and update
The agent can reply to conversations and update records in that area.

Some actions stay off until explicitly turned on

Each one removes data for good or changes how your inbox is run, so it could override the limits set elsewhere.

Deleting conversationsChanging workflowsManaging users and inboxes
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 Help Scout a single time. Bollard AI lays out the areas of your inbox, 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, reply, and update records in a single area
Example

A customer support agent.

A support agent replies to conversations and can look up customers, but it can't delete anything or change your inboxes.

Conversations Help desk areaOffReadFull use
Customers Help desk areaOffReadFull use
Inboxes Help desk areaOffReadFull use

Manage access

ALLOWEDSupport Agent replied in Conversations
ALLOWEDSupport Agent read a record in Customers
BLOCKEDSupport Agent tried to open Inboxes, 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 Help Scout, so they never hold your Help Scout keys and never reach Help Scout directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Help Scout. 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 conversations 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 Help Scout 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 conversation or customer, and the decision. The record is readable and can't be edited after the fact.

Questions

Help Scout, answered.

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