Integrations/Greenhouse

Control what your AI agents do in Greenhouse.

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

Request early accessSee how it works →
Greenhouse
Recruiting Agent
Applications Recruiting areaOffReadFull use
Candidates Recruiting areaOffReadFull use
Offers Recruiting areaOffReadFull use
Read and send offers
What agents can do

Set what each agent can do across your hiring.

Each area of Greenhouse, like candidates, applications, or offers, 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 hiring.
Read
Read-only
The agent can read candidates and applications in that area. It can't change anything.
Full use
Update and advance
The agent can advance applications and update records in that area.

Some actions stay off until explicitly turned on

Each one exposes sensitive feedback or pay, or removes hiring records, so it could override the limits set elsewhere.

Reading or sending offersReading scorecards and feedbackRemoving candidates or interviews
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 Greenhouse a single time. Bollard AI lays out the areas of your hiring, 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, advance, and update records in a single area
Example

A recruiting coordinator agent.

A recruiting agent advances applications and can read candidates, but it can't open offers or read interview feedback.

Applications Recruiting areaOffReadFull use
Candidates Recruiting areaOffReadFull use
Offers Recruiting areaOffReadFull use

Manage access

ALLOWEDRecruiting Agent advanced an Application
ALLOWEDRecruiting Agent read a record in Candidates
BLOCKEDRecruiting Agent tried to open Offers, 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 Greenhouse, so they never hold your Greenhouse keys and never reach Greenhouse directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Greenhouse. 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 or sending offers 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 Greenhouse 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 candidate or application, and the decision. The record is readable and can't be edited after the fact.

Questions

Greenhouse, answered.

Does connecting Greenhouse hand Bollard AI all your hiring data?+
Only the areas you allow. An admin connects your Greenhouse, and you decide which areas, like candidates or applications, each agent can reach. Bollard AI doesn't browse or copy your hiring data. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read offers or interview feedback?+
Not unless you turn it on. Reading and sending offers, and reading scorecards, are held off by default, so an agent can move applications along and read candidates without ever seeing pay or private feedback, 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 Greenhouse 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 Greenhouse, and the blocked attempt lands in the activity record with the reason.
How do we connect Greenhouse?+
An admin connects the company's Greenhouse once. Bollard AI seals the connection and lays out the areas of your hiring 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 Greenhouse, 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 →