Integrations/Typeform

Control what your AI agents do in Typeform.

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

Request early accessSee how it works →
Typeform
Survey Agent
Forms Forms areaOffReadFull use
Responses Forms areaOffReadFull use
Workspaces Forms areaOffReadFull use
Delete forms and responses
What agents can do

Set what each agent can do with your forms.

Each area of Typeform, like forms, responses, or workspaces, 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 Typeform.
Read
Read-only
The agent can read forms and the responses people have submitted. It can't change anything.
Full use
Create and edit
The agent can create and edit forms in that area.

Some actions stay off until explicitly turned on

Each one removes a form or the answers people gave for good, so it could override the limits set elsewhere.

Deleting forms or responsesDeleting a workspaceRemoving webhooks and themes
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 Typeform 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, create, and edit forms in a single area
Example

A survey building agent.

A survey agent builds and edits forms and can read the responses, but it can't delete a form or remove people's answers.

Forms Forms areaOffReadFull use
Responses Forms areaOffReadFull use
Workspaces Forms areaOffReadFull use

Manage access

ALLOWEDSurvey Agent created a form in Forms
ALLOWEDSurvey Agent read the Responses
BLOCKEDSurvey Agent tried to open Workspaces, 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 Typeform, so they never hold your Typeform keys and never reach Typeform directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and deleting forms or responses 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 Typeform 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 form or response, and the decision. The record is readable and can't be edited after the fact.

Questions

Typeform, answered.

Does connecting Typeform hand Bollard AI all your forms?+
Only the areas you allow. An admin connects your Typeform, and you decide which areas, like forms or responses, 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 delete a form or people's answers?+
Not unless you turn it on. Deleting forms and responses is held off by default, so an agent can build forms and read submissions without ever removing anything, 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 Typeform 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 Typeform, and the blocked attempt lands in the activity record with the reason.
How do we connect Typeform?+
An admin connects the company's Typeform 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 Typeform, 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 →