Confluence
Search and read Confluence pages and create new ones.
The Confluence integration opens your wiki to Kasimir: search pages, read them in full and create new pages.
Connect
In the sidebar, open Customize → Integrations (/integrations).
On the Confluence tile, click Connect.
Sign in with Atlassian and confirm access.
Creating connections requires the Connect integrations permission – by default only owners and admins have it; owners or admins enable it for members under Roles and permissions.
The tile then shows “Connected as …” and three counters: Sources, Files and Tools. Use Disconnect to remove the connection again.
Every connection is a deliberate opt-in. In the chat you switch it on under Knowledge sources → Connected services; tools that create or change something are set to Ask first by default.
What Kasimir can do with it
Tool | Effect |
|---|---|
| Find pages via full-text search |
| Read a page in full |
| Create a new page |
The requested permissions are read:confluence-content.all, write:confluence-content, read:confluence-space.summary and search:confluence. Here too: Kasimir only sees what your account is allowed to see.
Read live, not indexed
The tool reads Confluence afresh for every question; Kasimir does not build an index for it. Confluence cannot be connected as an indexed knowledge source under External sources – only file stores such as OneDrive, SharePoint, Google Drive, Nextcloud and ownCloud are available there.
Triggers for workflows
Confluence can also start workflows: when a new page is created or a page is changed, optionally limited to one space. The triggers are listed in the tile's detail view under Triggers; in the workflow builder you select them as trigger nodes.