Let your team build AI agents for Plaid. Bollard AI controls what each one can do, area by area.
Each area of Plaid, like transactions, accounts, or identity, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.
Each one exposes bank credentials and personal data or cuts off a connection, so it could override the limits set elsewhere.
Connect once, then control access person by person. No new keys to hand out.
An admin connects your company's Plaid a single time. Bollard AI lays out the areas of your linked accounts, and anything you don't allow stays out of reach for every agent.
From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.
A finance agent reads transactions and can read account balances, but it can't pull bank account numbers or remove a connection.
Manage access
Monitor activity
Bollard AI is access control for AI agents. It sits between your agents and Plaid, so they never hold your Plaid keys and never reach Plaid directly.
Agents send their requests to Bollard AI, not to Plaid. Bollard AI checks each one against your rules and passes only the allowed requests through.
Every area starts off-limits, and reading bank account numbers 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 Plaid 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.
Every attempt is recorded in plain English: who or which agent, what they tried, which account or area, and the decision. The record is readable and can't be edited after the fact.
We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.