Integrations/PostHog

Control what your AI agents do in PostHog.

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

Request early accessSee how it works →
PostHog
Analytics Agent
Insights Analytics areaOffReadFull use
Persons Analytics areaOffReadFull use
Feature flags Analytics areaOffReadFull use
Edit feature flags
What agents can do

Set what each agent can do across your analytics.

Each area of PostHog, like insights, persons, or feature flags, 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 analytics.
Read
Read-only
The agent can read insights and person data in that area. It can't change anything.
Full use
Build and run
The agent can build insights and run queries in that area.

Some actions stay off until explicitly turned on

Each one changes what users experience or removes person data in bulk, so it could override the limits set elsewhere.

Editing or rolling out feature flagsDeleting persons in bulkChanging project 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 PostHog a single time. Bollard AI lays out the areas of your analytics, 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 useBuild and run insights in a single area
Example

A product analytics agent.

An analytics agent builds insights and can read person data, but it can't change feature flags or delete persons.

Insights Analytics areaOffReadFull use
Persons Analytics areaOffReadFull use
Feature flags Analytics areaOffReadFull use

Manage access

ALLOWEDAnalytics Agent built an Insight
ALLOWEDAnalytics Agent read a record in Persons
BLOCKEDAnalytics Agent tried to edit a Feature flag, 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 PostHog, so they never hold your PostHog keys and never reach PostHog directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and changing feature flags 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 PostHog 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 insight or person, and the decision. The record is readable and can't be edited after the fact.

Questions

PostHog, answered.

Does connecting PostHog hand Bollard AI your whole project?+
Only the areas you allow. An admin connects your PostHog, and you decide which areas, like insights or persons, each agent can reach. Bollard AI doesn't browse or copy your analytics. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent change what users experience?+
Not unless you turn it on. Editing and rolling out feature flags is held off by default, so an agent can build insights and read data 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 PostHog 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 PostHog, and the blocked attempt lands in the activity record with the reason.
How do we connect PostHog?+
An admin connects the company's PostHog once. Bollard AI seals the connection and lays out the areas of your analytics 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 PostHog, 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 →