Integrations/Crisp
C

Control what your AI agents do in Crisp.

Let your team build AI agents for Crisp. Bollard AI controls what each one can do, and sending stays off by default.

Request early accessSee how it works →
CCrisp
Support Agent
Conversations Account areaOffReadFull use
Contacts Account areaOffReadFull use
Helpdesk Account areaOffReadFull use
Send messages
What agents can do

Set what each agent can do across your account.

Each area of Crisp, like conversations, contacts, or helpdesk, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and sending is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read conversations and contacts in that area. It can't change or send anything.
Full use
Draft and update
The agent can draft replies and add notes in that area.

Some actions stay off until explicitly turned on

Each one sends messages to customers or removes records for good, so it could override the limits set elsewhere.

Sending messages to customersDeleting conversationsChanging helpdesk settings
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 Crisp a single time. Bollard AI lays out the areas of your account, 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, draft, and add notes in a single area
Example

A support drafting agent.

A support agent drafts replies and can read your contacts, but it can't send a message or delete a conversation.

Conversations Account areaOffReadFull use
Contacts Account areaOffReadFull use
Helpdesk Account areaOffReadFull use

Manage access

ALLOWEDSupport Agent drafted a reply in Conversations
ALLOWEDSupport Agent read a record in Contacts
BLOCKEDSupport Agent tried to open Helpdesk, 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 Crisp, so they never hold your Crisp keys and never reach Crisp directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Crisp. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every area starts off-limits, and sending messages 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 Crisp 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

Crisp, answered.

Does connecting Crisp hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Crisp, and you decide which areas, like conversations or contacts, each agent can reach. Bollard AI doesn't browse or copy your account. 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. Sending messages to customers is held off by default, so an agent can draft replies and read records without ever messaging a customer, 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 Crisp 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 Crisp, and the blocked attempt lands in the activity record with the reason.
How do we connect Crisp?+
An admin connects the company's Crisp once. Bollard AI seals the connection and lays out the areas of your account 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 Crisp, 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 →