Control what your AI agents do in Apollo.

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

Apollo
Sales Agent
Sequences Sales areaOffReadFull use
Contacts Sales areaOffReadFull use
Deals Sales areaOffReadFull use
Reveal emails and phone numbers
What agents can do

Set what each agent can do across your sales workflow.

Each area of Apollo, like contacts, sequences, or deals, 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 Apollo.
Read
Read-only
The agent can read your contacts and accounts. It can't change anything.
Full use
Add and update
The agent can add contacts to sequences and update records in that area.

Some actions stay off until explicitly turned on

Each one pulls personal contact details or starts outreach, so it could override the limits set elsewhere.

Revealing emails and phone numbersSending emails to contactsDeleting contacts and accounts
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 Apollo a single time. Bollard AI lays out the areas of your sales workflow, 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, add, and update records in a single area
Example

A sales prospecting agent.

A prospecting agent adds contacts to sequences and can read your accounts, but it can't reveal personal contact details or open your deals.

Sequences Sales areaOffReadFull use
Contacts Sales areaOffReadFull use
Deals Sales areaOffReadFull use

Manage access

ALLOWEDSales Agent added a contact to Sequences
ALLOWEDSales Agent read a record in Contacts
BLOCKEDSales Agent tried to open Deals, 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 Apollo, so they never hold your Apollo keys and never reach Apollo directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and revealing personal contact details 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 Apollo 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 contact or sequence, and the decision. The record is readable and can't be edited after the fact.

Questions

Apollo, answered.

Does connecting Apollo hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Apollo, and you decide which areas, like contacts or sequences, 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 pull personal emails and phone numbers?+
Not unless you turn it on. Revealing emails and phone numbers is held off by default, so an agent can build sequences and read your records without ever pulling personal contact details, 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 Apollo 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 Apollo, and the blocked attempt lands in the activity record with the reason.
How do we connect Apollo?+
An admin connects the company's Apollo once. Bollard AI seals the connection and lays out the areas of your sales workflow 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 Apollo, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.