- Collections: files, pasted text and web pages stored in xpander, searched by meaning and by exact words.
- Live sources: Google Drive, SharePoint, OneDrive, Confluence and Jira, searched at question time with the account of the person asking. Nothing is copied into xpander unless an admin keeps a copy of a folder.
Answers carry citations
An answer that used the brain ends with Sources, one numbered chip per document or live item. A stored document opens at the cited passage. A live item opens in its source, with your own account. See Citations in the conversation.Each person gets only what they can already open
The brain never widens access:- Stored documents are filtered by who may read them before ranking, so a document someone may not open never reaches the answer.
- Live sources are read with the person’s own account. A permission removed in the source applies on the next question.
- Sources a person has not connected give them nothing. There is no shared or service account to fall back on. The answer names the skipped sources and offers Connect for each.
What it reads
On every live source an admin can also exclude by path, label, file type and age. Uploads can be PDF, Word, PowerPoint, Excel, Markdown, HTML or images, up to 25 MB each. Scanned pages are read with OCR.
Where you manage it
Next steps
Set it up for your organization
Brains, collections and sources.
Connect your own sources
Your knowledge settings.
Use it from agents and MCP clients
Attach brains and read citations.
Run it self-hosted
Data location and chart values.

