Source types
| Type | Description |
|---|---|
confluence | Confluence wiki pages from a specified space |
file | Uploaded files (PDF, text, markdown) |
inline | Text content entered directly |
url | Web pages fetched and indexed |
Sync lifecycle
Each knowledge source goes through a sync process:| Status | Meaning |
|---|---|
pending | Source added but not yet synced |
syncing | Sync in progress (fetching, chunking, indexing) |
synced | Ready for use. Chunk count is available. |
error | Sync failed. Check source configuration. |
Chunks
Documents are split into searchable chunks during sync. The chunk count is tracked per source. During a query, relevant chunks are retrieved and passed to the language model as context. The number of knowledge chunks used per query is recorded in the audit log.Knowledge gaps
When the AI cannot answer a question from available knowledge, it is recorded as a knowledge gap. Gaps are tracked per workspace and surfaced in:- The Knowledge tab (gaps sub-tab)
- The workspace dashboard
- Conversation stats