Integrations/Auth0

Control what your AI agents do in Auth0.

Let your team build AI agents for Auth0. Bollard AI controls what each one can do, area by area.

Request early accessSee how it works →
Auth0
Identity Agent
Roles Directory areaOffReadFull use
Users Directory areaOffReadFull use
Applications Directory areaOffReadFull use
Delete users and apps
What agents can do

Set what each agent can do across your tenant.

Each area of Auth0, like users, roles, or applications, 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 tenant.
Read
Read-only
The agent can read users, roles, and logs in that area. It can't change anything.
Full use
Assign and update
The agent can assign roles and update records in that area.

Some actions stay off until explicitly turned on

Each one removes accounts for good or changes how sign-in works, so it could override the limits set elsewhere.

Deleting usersCreating or deleting applicationsChanging connections and rules
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 Auth0 a single time. Bollard AI lays out the areas of your tenant, 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

An identity operations agent.

An identity agent assigns roles and can read your users, but it can't delete users or change your applications.

Roles Directory areaOffReadFull use
Users Directory areaOffReadFull use
Applications Directory areaOffReadFull use

Manage access

ALLOWEDIdentity Agent assigned a record in Roles
ALLOWEDIdentity Agent read a record in Users
BLOCKEDIdentity Agent tried to open Applications, 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 Auth0, so they never hold your Auth0 keys and never reach Auth0 directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Auth0. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every area starts off-limits, and deleting users or changing sign-in 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 Auth0 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 role, and the decision. The record is readable and can't be edited after the fact.

Questions

Auth0, answered.

Does connecting Auth0 hand Bollard AI your whole tenant?+
Only the areas you allow. An admin connects your Auth0, and you decide which areas, like users or roles, each agent can reach. Bollard AI doesn't browse or copy your tenant. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete users or change how sign-in works?+
Not unless you turn it on. Deleting users, and changing applications and connections, are held off by default, so an agent can assign roles and read users where you allow without ever removing accounts or changing sign-in, 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 Auth0 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 Auth0, and the blocked attempt lands in the activity record with the reason.
How do we connect Auth0?+
An admin connects the company's Auth0 once. Bollard AI seals the connection and lays out the areas of your tenant 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 Auth0, 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 →