Integrations/Figma

Control what your AI agents do in Figma.

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

Request early accessSee how it works →
Figma
Design Agent
Marketing ProjectOffReadFull use
Product ProjectOffReadFull use
Brand ProjectOffReadFull use
Manage members and webhooks
What agents can do

Set what each agent can do in every project.

Each project gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't open the project or see that it exists.
Read
Read-only
The agent can read the files and designs in that project. It can't change anything.
Full use
Read and comment
The agent can read files and post comments in that project.

Some actions stay off until explicitly turned on

Each one changes who can reach your designs or your event setup, so it could override the limits set on individual projects.

Managing team members and projectsCreating or removing webhooksDeleting comments
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 Figma a single time and chooses which projects it covers. Any project left out 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 files and post comments in a single project
Example

A design review agent.

A design agent posts review comments in Marketing and can read Product, but it can't open the Brand project or manage members.

Marketing ProjectOffReadFull use
Product ProjectOffReadFull use
Brand ProjectOffReadFull use

Manage access

ALLOWEDDesign Agent posted a comment in Marketing
ALLOWEDDesign Agent read a file in Product
BLOCKEDDesign Agent tried to open the Brand project, 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 Figma, so they never hold your Figma keys and never reach Figma directly.

Everything runs through Bollard AI

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

Denied by default

Every project starts off-limits, and managing members 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 Figma 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 file or project, and the decision. The record is readable and can't be edited after the fact.

Questions

Figma, answered.

Does connecting Figma hand Bollard AI all your projects?+
Only what's connected. An admin chooses which projects Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your designs. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent change who can reach our designs?+
Not unless you turn it on. Managing team members and projects is held off by default, so an agent can read files and post comments where you allow without ever changing who can reach your designs, 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 Figma 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 Figma, and the blocked attempt lands in the activity record with the reason.
How do we connect Figma?+
An admin connects the company's Figma once. Bollard AI seals the connection and builds the list of projects 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 Figma, 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 →