Integrations/Coda

Control what your AI agents do in Coda.

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

Request early accessSee how it works →
Coda
Docs Agent
Team wiki DocOffReadFull use
Specs DocOffReadFull use
Finance DocOffReadFull use
Delete docs and pages
What agents can do

Set what each agent can do in every doc.

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

Off
No access
The agent can't see the doc or that it exists.
Read
Read-only
The agent can read the pages and tables in that doc. It can't change anything.
Full use
Edit and update
The agent can edit pages and update rows in that doc.

Some actions stay off until explicitly turned on

Each one removes a doc or its data for good, or changes who can reach it, so it could override the limits set on individual docs.

Deleting docs or pagesDeleting rows in bulkChanging sharing and permissions
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 Coda a single time and chooses which docs it covers. Any doc 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, edit pages, and update rows in a single doc
Example

A docs editing agent.

A docs agent edits the Team wiki and can read Specs, but it can't open the Finance doc or delete a page.

Team wiki DocOffReadFull use
Specs DocOffReadFull use
Finance DocOffReadFull use

Manage access

ALLOWEDDocs Agent edited a page in the Team wiki
ALLOWEDDocs Agent read a page in Specs
BLOCKEDDocs Agent tried to open the Finance doc, 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 Coda, so they never hold your Coda keys and never reach Coda directly.

Everything runs through Bollard AI

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

Denied by default

Every doc starts off-limits, and deleting docs 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 Coda 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 doc or page, and the decision. The record is readable and can't be edited after the fact.

Questions

Coda, answered.

Does connecting Coda hand Bollard AI all your docs?+
Only what's connected. An admin chooses which docs Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your docs. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent delete docs or change who can reach them?+
Not unless you turn it on. Deleting docs and pages, and changing sharing and permissions, are held off by default, so an agent can edit where you allow without ever removing docs or exposing them, 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 Coda 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 Coda, and the blocked attempt lands in the activity record with the reason.
How do we connect Coda?+
An admin connects the company's Coda once. Bollard AI seals the connection and builds the list of docs 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 Coda, 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 →