Connecting Confluence to Knowledge Management
The Confluence knowledge integration syncs pages, blog posts, and attachments from your Confluence Cloud spaces into the Rezolve.ai Knowledge Base. The Virtual Agent can then use that content to answer questions and link back to the source page.
This page covers the Confluence-specific setup. For the wizard, sync status, bounced files, and other functions that all integrations share, see Knowledge Integrations.
Prerequisites
- Confluence Cloud (
https://<your-site>.atlassian.net). Confluence Server and Data Center are not supported. - A Confluence user account that can view every space you want to sync. A dedicated service account is recommended.
- An Atlassian API token for that account.
- Knowledge Management admin access in the Rezolve.ai console.
Rezolve.ai sees exactly what the connecting account sees. Pages the account can't view, because of space permissions or page restrictions, are not ingested.
Step 1: Create an Atlassian API token
- Sign in as the integration account at id.atlassian.com/manage-profile/security/api-tokens.
- Click Create API token, enter a label (for example
Rezolve.ai Knowledge), and set an expiry. - Copy the token. Atlassian shows it only once.
Note the token's expiry date. When it expires, syncs fail until you update the connection with a new token.
Step 2: Create the Confluence integration
- In the Rezolve.ai console, go to Knowledge Management → Knowledge Integrations.
- Click Add Integrations and select Confluence.
2a. Connection setup
Enter a Title for the integration. Then either choose an existing Confluence connection or select Create New Connection and enter these details:
| Field | Description | Example |
|---|---|---|
| Name | A descriptive name for the connection | Engineering Confluence |
| Instance URL | Your Confluence Cloud site root. Leave out /wiki and the trailing slash. | https://yourcompany.atlassian.net |
| Username | Email address of the integration account | kb-sync@yourcompany.com |
| Password / API Token | The API token from Step 1. Account passwords don't work with Confluence Cloud. | ATATT3x... |
Enter the site root only. If the URL ends in /wiki or /, the connection fails, because Rezolve.ai adds /wiki itself.
The Instance URL can't be edited after the integration is created.
2b. Content selection
Content is organized into one or more content sets. In each content set:
- Tick one or more spaces.
- Only current global spaces are listed. Personal and archived spaces aren't available.
- All current pages and blog posts in a ticked space are synced. You can't select individual pages, page trees, or labels.
- To limit who can get answers from this content set, open the ⋮ menu, turn on Restrict Access, and choose Restrict by Audience.
2c. Configuration
Under Sync Details, set the Frequency (daily, weekly, or monthly), Start Time, Timezone, and Schedule Start Date. Optionally turn on Subscribe to Sync Reports and add User Subscribers. Then click Save. See Knowledge Integrations → Step 3: Configuration.
What gets ingested
| Content | Details |
|---|---|
| Pages and blog posts | The current published version of each page and blog post in the selected spaces. Drafts, archived pages, and trashed pages are excluded. |
| Inline images | Images embedded in pages are kept and shown with the answer. Text inside images is not read. |
| Attachments | Supported files attached to pages are ingested as separate knowledge items |
Page formatting
- Headings, lists, tables, links, and code blocks are preserved.
- Table of contents, page tree, and expand macros are removed. Anything inside an expand macro is not ingested, so keep important content outside expand sections.
- For other macros, only their plain-text content is kept. Dynamic macros such as Jira issue lists and reports produce no content.
Supported attachment types
| Category | Extensions |
|---|---|
| Documents | .pdf, .doc, .docx, .txt, .rtf, .md |
| Presentations | .ppt, .pptx |
| Web and data | .html, .htm, .xml, .json |
.eml, .msg | |
| Archives | .zip, .rar, .7z (supported files inside are extracted) |
Excel (.xls, .xlsx) and CSV attachments are not ingested. Other unsupported types appear in Bounced Files.
Limits
| Limit | Default |
|---|---|
| Maximum attachment size | 25 MB |
| Archive contents | Up to 10 files and 50 MB uncompressed |
| Retries per file | A file that fails 3 times is skipped until it's resolved in Bounced Files |
Metadata and source links
Each item keeps its title, author, last-modified time, and any lang:, language:, or region: labels. Answers link to the page in Confluence, for example https://yourcompany.atlassian.net/wiki/spaces/HR/pages/12345/Leave+Policy.
Sync behavior
| Behavior | Details |
|---|---|
| First sync | Full ingestion of all selected spaces |
| Later syncs | Incremental. Pages and attachments are re-ingested only when their Confluence version changes. |
| Deleted, archived, or restricted pages | Removed from the Knowledge Base on the next sync |
| Throttling | Rate-limit (HTTP 429) and temporary server errors are retried automatically |
If the integration account loses access to a space, Confluence returns the space as empty and the next sync removes that space's content from the Knowledge Base. Check the account's permissions before changing space permissions.
Access control
Access to Confluence content in Rezolve.ai comes from the Audience you set on each content set. Confluence page restrictions and space permissions are not inherited. Every user in the audience can get answers from every page in the content set.
To keep restricted content private, do one of the following:
- put it in a separate content set with a narrower audience, or
- leave it out of the sync.
Troubleshooting
| Symptom | Likely cause | Resolution |
|---|---|---|
| Connection fails with an authentication error | Wrong email, or an expired or revoked API token | Create a new token and update the connection |
| Connection fails, or no spaces are listed | The site URL includes /wiki or a trailing slash, or the account can't view any spaces | Use https://<site>.atlassian.net and check the account's space permissions |
| A space is missing from the list | It's a personal or archived space | Only current global spaces can be synced |
| Some spaces sync and others don't | The account lacks access to those spaces | Grant the account view access, then click Sync Now |
| Part of a page's content is missing from answers | It's inside an expand or another dynamic macro | Move the content outside the macro |
| Attachment in Bounced Files as not supported | For example Excel, CSV, or image files | Convert to a supported format such as PDF |
| Attachment bounced for size limit | File is over 25 MB | Split or compress the file |
Download the CSV log for any sync run from the Sync Status tab.
Next Steps
- Manage syncs, logs, and bounced files in Knowledge Integrations
- Set up audience targeting for Confluence content
- Monitor usage with analytics