Integrations/Intercom

Control what your AI agents do in Intercom.

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

Request early accessSee how it works →
Intercom
Support Agent
Conversations Help desk areaOffReadFull use
Contacts Help desk areaOffReadFull use
Articles Help desk areaOffReadFull use
Delete conversations and contacts
What agents can do

Set what each agent can do across your inbox.

Each area of Intercom, like conversations, contacts, or help articles, 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 Intercom.
Read
Read-only
The agent can read conversations and contact 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 messages people directly, so it could override the limits set elsewhere.

Deleting conversations or contactsStarting outbound messages to customersChanging your help articles
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 Intercom 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 reads and replies to conversations and can look up contacts, but it can't delete anyone or edit your help articles.

Conversations Help desk areaOffReadFull use
Contacts Help desk areaOffReadFull use
Articles Help desk areaOffReadFull use

Manage access

ALLOWEDSupport Agent replied in Conversations
ALLOWEDSupport Agent read a record in Contacts
BLOCKEDSupport Agent tried to edit an Article, 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 Intercom, so they never hold your Intercom keys and never reach Intercom directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Intercom. 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 people or 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 Intercom 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 contact, and the decision. The record is readable and can't be edited after the fact.

Questions

Intercom, answered.

Does connecting Intercom hand Bollard AI your whole inbox?+
Only the areas you allow. An admin connects your Intercom, and you decide which areas, like conversations or contacts, 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 message customers on its own?+
Not unless you turn it on. Starting outbound messages to customers is held off by default, so an agent can reply inside the conversations you allow without ever reaching out cold, 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 Intercom 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 Intercom, and the blocked attempt lands in the activity record with the reason.
How do we connect Intercom?+
An admin connects the company's Intercom 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 Intercom, 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 →