Integrations/Rippling
R

Control what your AI agents do in Rippling.

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

Request early accessSee how it works →
RRippling
People Ops Agent
Time off HR areaOffReadFull use
Directory HR areaOffReadFull use
Compensation HR areaOffReadFull use
Read compensation
What agents can do

Set what each agent can do across your HR records.

Each area of Rippling, like the directory, time off, or compensation, 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 your HR records.
Read
Read-only
The agent can read the employee directory and basic details. It can't change anything.
Full use
Update and approve
The agent can update records and approve requests in that area, like leave.

Some actions stay off until explicitly turned on

Each one exposes sensitive personal data or changes who has access, so it could override the limits set elsewhere.

Reading compensation and pay dataChanging org structure and accessRemoving employee records
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 Rippling a single time. Bollard AI lays out the areas of your HR records, 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, update, and approve records in a single area
Example

A people operations agent.

A people ops agent approves leave and can read the directory, but it can't open compensation or change access.

Time off HR areaOffReadFull use
Directory HR areaOffReadFull use
Compensation HR areaOffReadFull use

Manage access

ALLOWEDPeople Ops Agent approved a request in Time off
ALLOWEDPeople Ops Agent read the Directory
BLOCKEDPeople Ops Agent tried to open Compensation, 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 Rippling, so they never hold your Rippling keys and never reach Rippling directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and reading pay data 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 Rippling 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 employee or request, and the decision. The record is readable and can't be edited after the fact.

Questions

Rippling, answered.

Does connecting Rippling hand Bollard AI all your HR records?+
Only the areas you allow. An admin connects your Rippling, and you decide which areas, like the directory or time off, each agent can reach. Bollard AI doesn't browse or copy your HR records. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent see salaries and pay data?+
Not unless you turn it on. Reading compensation and pay data is held off by default, so an agent can manage time off and read the directory without ever seeing pay, 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 Rippling 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 Rippling, and the blocked attempt lands in the activity record with the reason.
How do we connect Rippling?+
An admin connects the company's Rippling once. Bollard AI seals the connection and lays out the areas of your HR records 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 Rippling, 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 →