Slack · Connector
How do we connect Slack to AI agents on our own infrastructure?
Katonic connects to Slack with a bot token, reads the messages in the channels the bot can see and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from those conversations with a model you serve, so your messages and the questions are not sent to a public AI service.
What it reads.
From Slack.
- 01Messages in public and private channels the bot can see
- 02Thread replies
- 03Only the channels you name, where you list them
Through: Slack Web API
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
The token of a Slack bot that you install in your workspace, with permission to list channels and read their history.
The set-up dialog asks for
- Bot token
- Channels (optional)
Permissions
Access is set on the source in Katonic: everyone given access to the source can retrieve its documents.
Sync
Incremental, from the time of the last message read, and full.
You set how often the source is read again, in minutes, hours, days or weeks.
Limits
- By default the connector reads public and private channels. Direct messages are not in the default.
Does it read direct messages?
Not by default. It reads the public and private channels the bot can see.
Can we limit it to some channels?
Yes. You list the channels to read. Leave the list empty and it reads every channel the bot can see.
Where are the messages indexed?
In the Knowledge Engine, on infrastructure you own or control. They are not sent to a public AI service.