Integrations/Ironclad
I

Control what your AI agents do in Ironclad.

Let your team build AI agents for Ironclad. Bollard AI controls what each one can do, and launching a contract stays off by default.

Request early accessSee how it works →
IIronclad
Contracts Agent
Records Account areaOffReadFull use
Workflows Account areaOffReadFull use
Approvals Account areaOffReadFull use
Launch contract workflows
What agents can do

Set what each agent can do across your account.

Each area of Ironclad, like records, workflows, or approvals, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and launching a contract is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read records and workflow status in that area. It can't change or launch anything.
Full use
Create and update
The agent can create and update contract records in that area.

Some actions stay off until explicitly turned on

Each one starts a legal process, removes records for good, or changes who has to approve, so it could override the limits set elsewhere.

Launching contract workflowsDeleting recordsChanging approval steps
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 Ironclad 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, create, and update records in a single area
Example

A contract records agent.

A contracts agent updates records and can read workflow status, but it can't launch a contract workflow or change approval steps.

Records Account areaOffReadFull use
Workflows Account areaOffReadFull use
Approvals Account areaOffReadFull use

Manage access

ALLOWEDContracts Agent updated a record in Records
ALLOWEDContracts Agent read a Workflow
BLOCKEDContracts Agent tried to open Approvals, 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 Ironclad, so they never hold your Ironclad keys and never reach Ironclad directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and launching a contract 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 Ironclad 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 record or workflow, and the decision. The record is readable and can't be edited after the fact.

Questions

Ironclad, answered.

Does connecting Ironclad hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Ironclad, and you decide which areas, like records or workflows, 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 launch a contract or change approvals?+
Not unless you turn it on. Launching contract workflows, and changing approval steps, are held off by default, so an agent can manage records and read workflow status without ever starting a legal process, 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 Ironclad 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 Ironclad, and the blocked attempt lands in the activity record with the reason.
How do we connect Ironclad?+
An admin connects the company's Ironclad 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 Ironclad, 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 →