Integrations/Perplexity

Control what your AI agents do in Perplexity.

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

Request early accessSee how it works →
Perplexity
Research Agent
Search Account areaOffReadFull use
Models Account areaOffReadFull use
API keys Account areaOffReadFull use
Run deep research
What agents can do

Set what each agent can do in your Perplexity account.

Each area of your Perplexity account, like search, models, or API keys, 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 available models and settings. It can't change anything.
Full use
Search and answer
The agent can search the web and get grounded answers in that area.

Some actions stay off until explicitly turned on

Each one runs up cost at scale or hands out access, so it could override the limits set elsewhere.

Running deep research reportsRevoking API keysPulling embeddings in bulk
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 Perplexity account a single time. Bollard AI lays out the areas of the 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 useSearch and answer in a single area
Example

A research assistant agent.

A research agent searches the web and gets grounded answers, but it can't run costly deep-research reports or change API keys.

Search Account areaOffReadFull use
Models Account areaOffReadFull use
API keys Account areaOffReadFull use

Manage access

ALLOWEDResearch Agent ran a query in Search
ALLOWEDResearch Agent read the available Models
BLOCKEDResearch Agent tried to open API keys, 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 Perplexity, so they never hold your Perplexity keys and never reach Perplexity directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and running deep research at cost 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 Perplexity 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 model, and the decision. The record is readable and can't be edited after the fact.

Questions

Perplexity, answered.

Does connecting Perplexity hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Perplexity account, and you decide which areas, like search or models, 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 run up cost on its own?+
Not unless you turn it on. Running deep research reports and pulling embeddings in bulk are held off by default, so an agent can search and answer where you allow without ever running costly jobs, 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 Perplexity 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 Perplexity, and the blocked attempt lands in the activity record with the reason.
How do we connect Perplexity?+
An admin connects the company's Perplexity account once. Bollard AI seals the connection and lays out the areas of the 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 Perplexity, 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 →