Integrations/X (Twitter)

Control what your AI agents do in X (Twitter).

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

Request early accessSee how it works →
X (Twitter)
Social Agent
Mentions Social areaOffReadFull use
Timeline Social areaOffReadFull use
Direct messages Social areaOffReadFull use
Post and send DMs
What agents can do

Set what each agent can do across your X account.

Each area of X, like mentions, your timeline, or direct messages, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and posting is a separate switch.

Off
No access
The agent can't see that part of your X account.
Read
Read-only
The agent can read posts, mentions, and your timeline. It can't change or send anything.
Full use
Draft and organise
The agent can draft posts and organise content in that area.

Some actions stay off until explicitly turned on

Each one posts in public in your name or messages people directly, so it could override the limits set elsewhere.

Posting or reposting in your nameSending direct messagesDeleting posts
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 X account a single time. Bollard AI lays out the areas of the 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, draft, and organise content in a single area
Example

A social listening agent.

A social agent reads and drafts replies to mentions, but it can't post in your name or open direct messages.

Mentions Social areaOffReadFull use
Timeline Social areaOffReadFull use
Direct messages Social areaOffReadFull use

Manage access

ALLOWEDSocial Agent drafted a reply in Mentions
ALLOWEDSocial Agent read the Timeline
BLOCKEDSocial Agent tried to open Direct messages, 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 X (Twitter), so they never hold your X (Twitter) keys and never reach X (Twitter) directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and posting in your name 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 X (Twitter) 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 post or message, and the decision. The record is readable and can't be edited after the fact.

Questions

X (Twitter), answered.

Does connecting X hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your X account, and you decide which areas, like mentions or your timeline, 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 post or message people on its own?+
Not unless you turn it on. Posting, reposting, and sending direct messages are held off by default, so an agent can read and draft where you allow without ever posting in your name or messaging people, 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 X (Twitter) 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 X (Twitter), and the blocked attempt lands in the activity record with the reason.
How do we connect X (Twitter)?+
An admin connects the company's X account once. Bollard AI seals the connection and lays out the areas of the 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 X (Twitter), 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 →