Integrations/Airtable

Control what your AI agents do in Airtable.

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

Request early accessSee how it works →
Airtable
Ops Agent
Projects BaseOffReadFull use
Roadmap BaseOffReadFull use
HR BaseOffReadFull use
Change a base’s structure
What agents can do

Set what each agent can do in every base.

Each base, an Airtable workspace of tables and records, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can’t open the base or see that it exists.
Read
Read-only
The agent can read the records in that base. It can’t change anything.
Full use
Create and update
The agent can create and update records in that base.

Some actions stay off until explicitly turned on

Each one rewrites how a base is built, removes records in bulk, or reaches every base at once, so it could override the limits set on individual bases.

Changing a base’s tables and fieldsDeleting records in bulkReaching every base at once
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 Airtable a single time and chooses which bases it covers. Any base 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, create, and update records in a single base
Example

An operations agent.

An ops agent adds and updates records in the Projects base and can read the Roadmap, but it can’t open the HR base or change a base’s structure.

Projects BaseOffReadFull use
Roadmap BaseOffReadFull use
HR BaseOffReadFull use

Manage access

ALLOWEDOps Agent added a record to Projects
ALLOWEDOps Agent read the Roadmap base
BLOCKEDOps Agent tried to open the HR base, 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 Airtable, so they never hold your Airtable keys and never reach Airtable directly.

Everything runs through Bollard AI

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

Denied by default

Every base starts off-limits, and changing a base’s structure 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 Airtable 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 base or record, and the decision. The record is readable and can’t be edited after the fact.

Questions

Airtable, answered.

Does connecting Airtable hand Bollard AI all your bases?+
Only what’s connected. An admin chooses which bases Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn’t browse or copy your bases. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent change how our bases are built?+
Not unless you turn it on. Changing a base’s tables and fields is held off by default, so an agent can add and update records without ever altering the structure, 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 Airtable 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 Airtable, and the blocked attempt lands in the activity record with the reason.
How do we connect Airtable?+
An admin connects the company’s Airtable once. Bollard AI seals the connection and builds the list of bases 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 Airtable, 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 →