Integrations/Slack

Control what your AI agents do in Slack.

Let your team build AI agents for Slack. Bollard AI controls what each one can do.

Request early accessSee how it works →
Slack
Support Agent
#support ChannelOffReadFull use
#engineering ChannelOffReadFull use
#finance ChannelOffReadFull use
Workspace-wide message search
What agents can do

Set what each agent can do in every channel.

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

Off
No access
The agent can’t open the channel or see that it exists.
Read
Read-only
The agent can read a channel’s messages, threads, files, and who’s in it. It can’t post or change anything.
Full use
Post, react, share
The agent can post and edit its own messages, add reactions, and share files in that channel.

Some actions stay off until explicitly turned on

Each one reaches across the entire workspace, messages people directly, or deletes data, so it could override the limits set on individual channels.

Workspace-wide message searchReading the member directory and everyone’s email addressesDirect messages to individual peopleDeleting messages or files, and archiving a channel
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 the company’s Slack a single time and adds it to the channels it should cover, from one channel to all of them. Any channel it isn’t in 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, post, react, and share files in a single channel
Example

A customer-support agent.

A support agent has full use of the #support channel, can read #engineering, and has no access to #finance.

#support ChannelOffReadFull use
#engineering ChannelOffReadFull use
#finance ChannelOffReadFull use

Manage access

ALLOWEDSupport Agent posted a reply in #support
ALLOWEDSupport Agent read recent messages in #engineering
BLOCKEDSupport Agent tried to post in #finance, 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 Slack, so they never hold your Slack keys and never reach Slack directly.

Everything runs through Bollard AI

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

Denied by default

Every channel starts off-limits. 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 Slack 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 channel, and the decision. The record is readable and can’t be edited after the fact.

Questions

Slack, answered.

Does connecting Slack hand Bollard AI your whole workspace?+
Only the channels you add it to. The connection reaches the channels it’s been invited to, and that sets the most any agent could reach. Bollard AI doesn’t browse or copy your Slack. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read or send people’s direct messages?+
No, not unless you turn it on. By default an agent works inside the channels you allow, never in people’s private DMs. Messaging individuals directly is one of the actions held off until you explicitly switch it on.
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 Slack 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 Slack, and the blocked attempt lands in the activity record with the reason.
How do we connect Slack?+
An admin connects the company’s Slack once and adds it to the channels it should cover. Bollard AI seals the connection and builds the list of channels 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 Slack, 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 →