Integrations/Wise

Control what your AI agents do in Wise.

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

Request early accessSee how it works →
Wise
Payouts Agent
Recipients Area of the accountOffReadFull use
Balances Area of the accountOffReadFull use
Transfers Area of the accountOffReadFull use
Fund and send transfers
What agents can do

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

Each area of Wise, like recipients, balances, or transfers, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and sending money is a separate switch.

Off
No access
The agent can't open that area or see what's in it.
Read
Read-only
The agent can read balances and transfer details in that area. It can't change anything.
Full use
Create and update
The agent can add and update recipients and prepare transfers in that area.

Some actions stay off until explicitly turned on

Each one sends money out, so it could override the limits set on individual areas.

Funding and sending transfersSetting up new recipient bank detailsChanging account profiles
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 Wise 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, add, and update records in a single area
Example

A payouts support agent.

A payouts agent manages recipients and can read your balances, but it can't fund or send a transfer.

Recipients Area of the accountOffReadFull use
Balances Area of the accountOffReadFull use
Transfers Area of the accountOffReadFull use

Manage access

ALLOWEDPayouts Agent added a record in Recipients
ALLOWEDPayouts Agent read your Balances
BLOCKEDPayouts Agent tried to fund a transfer, 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 Wise, so they never hold your Wise keys and never reach Wise directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Wise. 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 money 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 Wise 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 recipient or transfer, and the decision. The record is readable and can't be edited after the fact.

Questions

Wise, answered.

Does connecting Wise hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Wise, and you decide which areas, like recipients or balances, 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 send money on its own?+
Not unless you turn it on. Funding and sending transfers are held off by default, so an agent can prepare recipients and read balances without ever sending money, 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 Wise 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 Wise, and the blocked attempt lands in the activity record with the reason.
How do we connect Wise?+
An admin connects the company's Wise 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 Wise, 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 →