Set up the sync
Open Data Sources
Go to AI Training → Data Sources.
Add a Confluence source
Click Add source → Confluence.
| Field | Example | Where to get it |
|---|---|---|
| Domain | yourcompany.atlassian.net | Your Atlassian instance domain. No https://. |
[email protected] | The Atlassian account the API token belongs to. | |
| API Token | ATATT… | Generate at Atlassian API tokens. The token needs Confluence read access. |
Start the sync
Click Connect. The first run does a full pull of every page the credentials can read. Large instances take longer — expect 10 minutes to an hour for thousands of pages.
Verify in AI Instructions
Open AI Training → AI Instructions. Pages appear under Confluence, each linked to its source URL in your instance.
What gets synced
All pages the credentials can read
All pages the credentials can read
Whole-instance pull. Page titles, body content (converted from Confluence storage format to HTML), and the
webui back-link.Visibility by space type
Visibility by space type
- Personal spaces (key starts with
~) → internal — the AI uses them only in agent-facing surfaces. - All other spaces → public — the AI can cite them in customer replies.
Full refresh, not incremental
Full refresh, not incremental
Each sync run is a full re-pull with overwrite. The benefit: deletions in Confluence propagate correctly. The cost: each run is heavier than an incremental pull. Typical cadence is set by Airbyte’s scheduler — adjust on the connection schedule if you need it less often for a huge instance.
Limits
| Value | |
|---|---|
| Streams synced | pages |
| Sync mode | full_refresh_overwrite |
| Sync cadence | Airbyte polling — typically every few hours |
| Credential type | Domain + email + Atlassian API token |
| Deployment | Cloud only. Server / Data Center not supported. |
| Selective scoping | None today — whole instance pulled |
| Attachments | Not synced |
Related Documentation
Confluence overview
What this source does and doesn’t.
Troubleshooting
Auth errors, missing pages, slow syncs.
Website crawler
Fallback for scoped subsets.
Connect a knowledge source
All sources.