Integrations/Okta

Control what your AI agents do in Okta.

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

Request early accessSee how it works →
Okta
Joiner-Mover-Leaver Agent
Group assignments Directory areaOffReadFull use
Users and groups Directory areaOffReadFull use
Policies Directory areaOffReadFull use
Deactivate or delete users
What agents can do

Set what each agent can do across your directory.

Each area of Okta, like users, groups, or app assignments, 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 directory.
Read
Read-only
The agent can read users, groups, and who has access to what. It can't change anything.
Full use
Assign and update
The agent can assign users to groups and apps and update those records.

Some actions stay off until explicitly turned on

Each one locks people out, removes accounts, or weakens your sign-in rules, so it could override the limits set elsewhere.

Deactivating, suspending, or deleting usersChanging sign-in and security policiesResetting passwords and second factors
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 Okta a single time. Bollard AI lays out the areas of your directory, 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, assign, and update records in a single area
Example

A joiner-mover-leaver agent.

An onboarding agent assigns new starters to the right groups and can read your directory, but it can't deactivate anyone or change your security policies.

Group assignments Directory areaOffReadFull use
Users and groups Directory areaOffReadFull use
Policies Directory areaOffReadFull use

Manage access

ALLOWEDJoiner-Mover-Leaver Agent assigned a user in Group assignments
ALLOWEDJoiner-Mover-Leaver Agent read Users and groups
BLOCKEDJoiner-Mover-Leaver Agent tried to change a Policy, 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 Okta, so they never hold your Okta keys and never reach Okta directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and locking people out or changing security policies 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 Okta 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 user or group, and the decision. The record is readable and can't be edited after the fact.

Questions

Okta, answered.

Does connecting Okta hand Bollard AI your whole directory?+
Only the areas you allow. An admin connects your Okta, and you decide which areas, like users or group assignments, each agent can reach. Bollard AI doesn't browse or copy your directory. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent lock people out of their accounts?+
Not unless you turn it on. Deactivating, suspending, and deleting users is held off by default, so an agent can assign access and read the directory without ever locking anyone out, 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 Okta 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 Okta, and the blocked attempt lands in the activity record with the reason.
How do we connect Okta?+
An admin connects the company's Okta once. Bollard AI seals the connection and lays out the areas of your directory 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 Okta, 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 →