Integrations/Twilio

Control what your AI agents do in Twilio.

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

Request early accessSee how it works →
Twilio
Notifications Agent
Message logs Account areaOffReadFull use
Phone numbers Account areaOffReadFull use
Voice Account areaOffReadFull use
Send SMS and make calls
What agents can do

Set what each agent can do across your Twilio account.

Each area of Twilio, like messaging, voice, or phone numbers, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and sending is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read message and call logs in that area. It can't change or send anything.
Full use
Read and update
The agent can read and tidy records in that area, like message logs.

Some actions stay off until explicitly turned on

Each one sends messages or calls in your name, runs up cost, or changes your numbers, so it could override the limits set elsewhere.

Sending SMS and messagesMaking voice callsBuying or releasing phone numbers
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 Twilio 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 and tidy records in a single area
Example

A delivery-notifications agent.

A notifications agent reads and tidies message logs and can read your phone numbers, but it can't send an SMS or make a call.

Message logs Account areaOffReadFull use
Phone numbers Account areaOffReadFull use
Voice Account areaOffReadFull use

Manage access

ALLOWEDNotifications Agent read a record in Message logs
ALLOWEDNotifications Agent read your Phone numbers
BLOCKEDNotifications Agent tried to send an SMS, 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 Twilio, so they never hold your Twilio keys and never reach Twilio directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and sending messages or calls 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 Twilio 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 message or number, and the decision. The record is readable and can't be edited after the fact.

Questions

Twilio, answered.

Does connecting Twilio hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Twilio, and you decide which areas, like messaging or voice, 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 send texts or make calls on its own?+
Not unless you turn it on. Sending SMS and making voice calls are held off by default, so an agent can read and tidy logs without ever messaging or calling anyone in your name, 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 Twilio 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 Twilio, and the blocked attempt lands in the activity record with the reason.
How do we connect Twilio?+
An admin connects the company's Twilio 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 Twilio, 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 →