Integrations/LaunchDarkly
LaunchDarkly

Control what your AI agents do in LaunchDarkly.

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

Request early accessSee how it works →
LaunchDarklyLaunchDarkly
Release Agent
Flags Account areaOffReadFull use
Segments Account areaOffReadFull use
Projects Account areaOffReadFull use
Roll out feature flags
What agents can do

Set what each agent can do across your account.

Each area of LaunchDarkly, like flags, segments, or projects, 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 flags and segments in that area. It can't change anything.
Full use
Create and update
The agent can create and update flags in that area.

Some actions stay off until explicitly turned on

Each one changes what your users experience or removes your setup for good, so it could override the limits set elsewhere.

Rolling out or deleting feature flagsDeleting projects or environmentsChanging experiments and metrics
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 LaunchDarkly 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 flags in a single area
Example

A feature flag agent.

A release agent creates flags and can read your segments, but it can't roll a flag out to users or delete a project.

Flags Account areaOffReadFull use
Segments Account areaOffReadFull use
Projects Account areaOffReadFull use

Manage access

ALLOWEDRelease Agent created a record in Flags
ALLOWEDRelease Agent read a record in Segments
BLOCKEDRelease Agent tried to open Projects, 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 LaunchDarkly, so they never hold your LaunchDarkly keys and never reach LaunchDarkly directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and rolling out flags to users 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 LaunchDarkly 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 flag or segment, and the decision. The record is readable and can't be edited after the fact.

Questions

LaunchDarkly, answered.

Does connecting LaunchDarkly hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your LaunchDarkly, and you decide which areas, like flags or segments, 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 change what our users experience?+
Not unless you turn it on. Rolling out and deleting feature flags, and deleting projects, are held off by default, so an agent can build flags where you allow without ever changing what your users experience, 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 LaunchDarkly 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 LaunchDarkly, and the blocked attempt lands in the activity record with the reason.
How do we connect LaunchDarkly?+
An admin connects the company's LaunchDarkly 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 LaunchDarkly, 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 →