Integrations/Ramp
R

Control what your AI agents do in Ramp.

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

Request early accessSee how it works →
RRamp
Spend Agent
Transactions Area of the accountOffReadFull use
Cards Area of the accountOffReadFull use
Spend limits Area of the accountOffReadFull use
Change spend limits and cards
What agents can do

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

Each area of Ramp, like transactions, cards, or spend limits, 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 transactions and card details in that area. It can't change anything.
Full use
Tidy and update
The agent can tidy and update records in that area, like categorising transactions.

Some actions stay off until explicitly turned on

Each one changes who can spend or moves money, so it could override the limits set on individual areas.

Changing spend limits and programsIssuing or changing cardsApproving reimbursements
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 Ramp 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, tidy, and update records in a single area
Example

An expense tidy-up agent.

A spend agent categorises transactions and can read your cards, but it can't change spend limits or approve reimbursements.

Transactions Area of the accountOffReadFull use
Cards Area of the accountOffReadFull use
Spend limits Area of the accountOffReadFull use

Manage access

ALLOWEDSpend Agent categorised a record in Transactions
ALLOWEDSpend Agent read a record in Cards
BLOCKEDSpend Agent tried to open Spend limits, 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 Ramp, so they never hold your Ramp keys and never reach Ramp directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and changing who can spend 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 Ramp 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 transaction or card, and the decision. The record is readable and can't be edited after the fact.

Questions

Ramp, answered.

Does connecting Ramp hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Ramp, and you decide which areas, like transactions or cards, 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 change who can spend or issue cards?+
Not unless you turn it on. Changing spend limits and programs, and issuing or changing cards, are held off by default, so an agent can tidy transactions and read cards without ever changing who can spend, 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 Ramp 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 Ramp, and the blocked attempt lands in the activity record with the reason.
How do we connect Ramp?+
An admin connects the company's Ramp 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 Ramp, 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 →