Integrations/Honeycomb
H

Control what your AI agents do in Honeycomb.

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

Request early accessSee how it works →
HHoneycomb
Observability Agent
Queries Account areaOffReadFull use
Boards Account areaOffReadFull use
Triggers Account areaOffReadFull use
Change SLOs and triggers
What agents can do

Set what each agent can do across your account.

Each area of Honeycomb, like queries, boards, or triggers, 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 boards and query results in that area. It can't change anything.
Full use
Run and build
The agent can run queries and build boards in that area.

Some actions stay off until explicitly turned on

Each one changes your alerting or sends data that runs up cost, so it could override the limits set elsewhere.

Deleting markers or triggersChanging SLOs and burn alertsSending telemetry events
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 Honeycomb 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, run, and build in a single area
Example

An observability agent.

An observability agent runs queries and can read your boards, but it can't change triggers or your SLOs.

Queries Account areaOffReadFull use
Boards Account areaOffReadFull use
Triggers Account areaOffReadFull use

Manage access

ALLOWEDObservability Agent ran a query in Queries
ALLOWEDObservability Agent read a record in Boards
BLOCKEDObservability Agent tried to change a Trigger, 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 Honeycomb, so they never hold your Honeycomb keys and never reach Honeycomb directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Honeycomb. 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 alerting 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 Honeycomb 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 query or board, and the decision. The record is readable and can't be edited after the fact.

Questions

Honeycomb, answered.

Does connecting Honeycomb hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Honeycomb, and you decide which areas, like queries or boards, 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 our alerting?+
Not unless you turn it on. Deleting triggers and changing SLOs and burn alerts are held off by default, so an agent can run and build where you allow without ever changing your alerting, 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 Honeycomb 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 Honeycomb, and the blocked attempt lands in the activity record with the reason.
How do we connect Honeycomb?+
An admin connects the company's Honeycomb 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 Honeycomb, 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 →