Integrations/Nutshell
N

Control what your AI agents do in Nutshell.

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

Request early accessSee how it works →
NNutshell
Sales Agent
People Area of the accountOffReadFull use
Leads Area of the accountOffReadFull use
Companies Area of the accountOffReadFull use
Delete records and export in bulk
What agents can do

Set what each agent can do in every area of your account.

Each area of Nutshell, like people, leads, or companies, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't open that area or see what's in it.
Read
Read-only
The agent can read records in that area, like leads or people. It can't change anything.
Full use
Create and update
The agent can create and update records in that area, like adding a person.

Some actions stay off until explicitly turned on

Each one removes records for good or copies your customer list out in bulk, so it could override the limits set on individual areas.

Deleting recordsExporting people in bulkChanging pipelines
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 Nutshell a single time. Bollard AI lays out the areas of the 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, create, and update records in a single area
Example

A sales CRM agent.

A sales agent updates people and can read your leads, but it can't delete records or export people in bulk.

People Area of the accountOffReadFull use
Leads Area of the accountOffReadFull use
Companies Area of the accountOffReadFull use

Manage access

ALLOWEDSales Agent updated a record in People
ALLOWEDSales Agent read a Lead
BLOCKEDSales Agent tried to open Companies, 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 Nutshell, so they never hold your Nutshell keys and never reach Nutshell directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and removing or exporting records 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 Nutshell 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 person or lead, and the decision. The record is readable and can't be edited after the fact.

Questions

Nutshell, answered.

Does connecting Nutshell hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Nutshell, and you decide which areas, like people or leads, 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 delete records or export our customer list?+
Not unless you turn it on. Deleting records and exporting people in bulk are held off by default, so an agent can manage and read records without ever removing data or copying your customer list out, 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 Nutshell 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 Nutshell, and the blocked attempt lands in the activity record with the reason.
How do we connect Nutshell?+
An admin connects the company's Nutshell once. Bollard AI seals the connection and lays out the areas of the 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 Nutshell, 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 →