Integrations/Amplitude
Amplitude

Control what your AI agents do in Amplitude.

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

Request early accessSee how it works →
AmplitudeAmplitude
Analytics Agent
Reports Analytics areaOffReadFull use
Taxonomy Analytics areaOffReadFull use
Raw export Analytics areaOffReadFull use
Export raw event data
What agents can do

Set what each agent can do across your analytics.

Each area of Amplitude, like reports, taxonomy, or raw export, 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 your event taxonomy and the figures behind reports. It can't change anything.
Full use
Run and build
The agent can run segmentation and funnel reports in that area.

Some actions stay off until explicitly turned on

Each one copies your raw data in bulk or changes how events are defined, so it could override the limits set elsewhere.

Exporting raw event data in bulkSending or changing eventsEditing taxonomy and properties
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 Amplitude 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 useRun and build reports in a single area
Example

A product analytics agent.

An analytics agent runs funnels and can read your taxonomy, but it can't export your raw data or change event definitions.

Reports Analytics areaOffReadFull use
Taxonomy Analytics areaOffReadFull use
Raw export Analytics areaOffReadFull use

Manage access

ALLOWEDAnalytics Agent ran a funnel in Reports
ALLOWEDAnalytics Agent read the Taxonomy
BLOCKEDAnalytics Agent tried to open Raw export, 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 Amplitude, so they never hold your Amplitude keys and never reach Amplitude directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and exporting raw data in bulk 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 Amplitude 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 report or dataset, and the decision. The record is readable and can't be edited after the fact.

Questions

Amplitude, answered.

Does connecting Amplitude hand Bollard AI your whole project?+
Only the areas you allow. An admin connects your Amplitude, and you decide which areas, like reports or taxonomy, 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 export our raw data?+
Not unless you turn it on. Exporting raw event data in bulk is held off by default, so an agent can run reports and read your data through them without ever pulling the whole dataset, 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 Amplitude 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 Amplitude, and the blocked attempt lands in the activity record with the reason.
How do we connect Amplitude?+
An admin connects the company's Amplitude 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 Amplitude, 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 →