Integrations/Microsoft Teams
Teams

Control what your AI agents do in Microsoft Teams.

Let your team build AI agents for Microsoft Teams. Bollard AI controls what each one can do, channel by channel.

Request early accessSee how it works →
TeamsMicrosoft Teams
Comms Agent
#general ChannelOffReadFull use
#engineering ChannelOffReadFull use
#leadership ChannelOffReadFull use
Read private chats
What agents can do

Set what each agent can do in every channel.

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

Off
No access
The agent can't see the channel or that it exists.
Read
Read-only
The agent can read the messages in that channel. It can't post or change anything.
Full use
Post and reply
The agent can post and reply to messages in that channel.

Some actions stay off until explicitly turned on

Each one reaches people's private messages or reshapes your workspace, so it could override the limits set on individual channels.

Reading people's private chatsCreating or deleting teams and channelsRemoving members
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 Microsoft Teams a single time and chooses which channels it covers. Any channel 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, post, and reply in a single channel
Example

A team comms agent.

A comms agent posts updates in #general and can read #engineering, but it can't open #leadership or read private chats.

#general ChannelOffReadFull use
#engineering ChannelOffReadFull use
#leadership ChannelOffReadFull use

Manage access

ALLOWEDComms Agent posted an update in #general
ALLOWEDComms Agent read messages in #engineering
BLOCKEDComms Agent tried to open #leadership, 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 Microsoft Teams, so they never hold your Microsoft Teams keys and never reach Microsoft Teams directly.

Everything runs through Bollard AI

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

Denied by default

Every channel starts off-limits, and reading private chats 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 Microsoft Teams 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 or message, and the decision. The record is readable and can't be edited after the fact.

Questions

Microsoft Teams, answered.

Does connecting Microsoft Teams hand Bollard AI your whole workspace?+
Only the channels you add it to. The connection reaches the channels you allow, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your Teams. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read people's private chats?+
No, not unless you turn it on. By default an agent works inside the channels you allow, never in people's private chats. Reading private chats 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 Microsoft Teams 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 Microsoft Teams, and the blocked attempt lands in the activity record with the reason.
How do we connect Microsoft Teams?+
An admin connects the company's Microsoft Teams once. 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 Microsoft Teams, 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 →