Integrations/Stytch
S

Control what your AI agents do in Stytch.

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

Request early accessSee how it works →
SStytch
Identity Agent
Users Account areaOffReadFull use
Organizations Account areaOffReadFull use
Sessions Account areaOffReadFull use
Delete users and revoke sessions
What agents can do

Set what each agent can do across your account.

Each area of Stytch, like users, organizations, or sessions, 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 account.
Read
Read-only
The agent can read users and organizations in that area. It can't change anything.
Full use
Read and update
The agent can read and update user details in that area.

Some actions stay off until explicitly turned on

Each one can lock people out or remove accounts for good, so it could override the limits set elsewhere.

Deleting usersRevoking sessionsChanging authentication settings
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 Stytch 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 and update user details in a single area
Example

A user admin agent.

An identity agent updates user details and can read your organizations, but it can't delete a user or revoke sessions.

Users Account areaOffReadFull use
Organizations Account areaOffReadFull use
Sessions Account areaOffReadFull use

Manage access

ALLOWEDIdentity Agent updated a record in Users
ALLOWEDIdentity Agent read an Organization
BLOCKEDIdentity Agent tried to open Sessions, 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 Stytch, so they never hold your Stytch keys and never reach Stytch directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Stytch. 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 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 Stytch 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 organization, and the decision. The record is readable and can't be edited after the fact.

Questions

Stytch, answered.

Does connecting Stytch hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Stytch, and you decide which areas, like users or organizations, 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 delete users or lock people out?+
Not unless you turn it on. Deleting users, revoking sessions, and changing authentication settings are held off by default, so an agent can update user details and read records 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 Stytch 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 Stytch, and the blocked attempt lands in the activity record with the reason.
How do we connect Stytch?+
An admin connects the company's Stytch 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 Stytch, 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 →