Integrations/Gmail

Control what your AI agents do in Gmail.

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

Request early accessSee how it works →
Gmail
Inbox Agent
Inbox MailboxOffReadFull use
Support LabelOffReadFull use
Private LabelOffReadFull use
Send email
What agents can do

Set what each agent can do with your mail.

Each agent is set to Off, Read, or Full use, and you can narrow that to specific labels if your team uses them. Anything not allowed is denied, and sending is a separate switch.

Off
No access
The agent can’t read the mail or see it at all.
Read
Read-only
The agent can read and search the mail it’s given. It can’t change or send anything.
Full use
Read, draft, organise
The agent can read, draft replies, and tidy mail. Sending stays a separate switch.

Some actions stay off until explicitly turned on

Each one sends mail in your name, deletes data for good, or reaches the whole mailbox, so it could override the limits set on individual labels.

Sending emailPermanently deleting mailChanging mailbox settings, filters, and forwarding
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 Gmail a single time and chooses how much it covers, from a single label to the whole mailbox. Anything left out 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 organise the mail it’s given
Example

An inbox triage agent.

An inbox agent reads new mail and drafts replies under the Support label, but it can’t send them or open the Private label.

Inbox MailboxOffReadFull use
Support LabelOffReadFull use
Private LabelOffReadFull use

Manage access

ALLOWEDInbox Agent read a new message in Inbox
ALLOWEDInbox Agent drafted a reply under Support
BLOCKEDInbox Agent tried to send the reply, 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 Gmail, so they never hold your Gmail keys and never reach Gmail directly.

Everything runs through Bollard AI

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

Denied by default

Mail the agent hasn’t been given stays off-limits, and sending 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 Gmail 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 message or label, and the decision. The record is readable and can’t be edited after the fact.

Questions

Gmail, answered.

Does connecting Gmail hand Bollard AI your whole mailbox?+
Only what’s connected. At setup an admin chooses how much Bollard AI covers, from a single label to the whole mailbox, and that sets the most any agent could reach. Bollard AI doesn’t browse or copy your mail. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent send email on its own?+
Not unless you turn it on. By default an agent can read and draft replies, but sending is held off. You can leave it drafting for a person to send, or switch sending on for a specific agent.
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 Gmail 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 Gmail, and the blocked attempt lands in the activity record with the reason.
How do we connect Gmail?+
An admin connects the company’s Gmail once. Bollard AI seals the connection and lays out the mailbox to set rules for, including any labels your team uses. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team’s agents to work in Gmail, 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 →