Skip to main content
Connect Confluence as a knowledge source. The AI agent can then search and reference Confluence pages when answering employee inquiries.

​
Connection types

Two connection types are available for Confluence.
Both types allow the AI agent to search Confluence after connection.

​
Prerequisites

  • Admin role in AI Helpdesk is required
  • Confluence (OAuth): Confluence Cloud admin rights required
  • Confluence (API Key): Requires the ability to generate an API token in Atlassian account settings (Atlassian security settings)
AI Helpdesk does not apply page-level permissions from Confluence. It may use any page that the connected Atlassian account can access. These pages can be used to answer questions from every employee in your organization who uses AI Helpdesk.Take care when connecting spaces or pages that contain sensitive information. Before you run a sync, limit the spaces and pages to import with Space URLs and Page URLs (OAuth, API Key).

​
Connect via Confluence (OAuth)

Connect a Confluence Cloud workspace using Atlassian OAuth.
1

Open Knowledge Integration settings

Select Settings from the left navigation, then open the Integration tab. Click Add Integration in the Knowledge Integration section and select Confluence (OAuth).
2

Authenticate with Atlassian

You are redirected to the Atlassian OAuth page. Log in with your Atlassian account and grant access to AI Helpdesk.
3

Confirm connection

Once authentication succeeds, a connected Confluence (OAuth) card appears in the Knowledge Integration section. Confirm the card status shows Connected.

​
Narrow the crawl scope (optional)

By default, all spaces, pages, and blog posts are crawled. To restrict crawling to specific spaces or pages, configure the following.
  1. Click the Configure (gear icon) on the connected card
  2. To narrow by space, enter space URLs in the Space URLs field, one URL per line (up to 100 URLs). For example, https://yourcompany.atlassian.net/wiki/spaces/IT. When you specify a space URL, the whole space is crawled. You do not need to specify each page or blog post in the space
  3. To crawl only specific pages, enter page URLs in the Page URLs field, one URL per line (up to 100 URLs). Include the page title part in each page URL. For example, https://yourcompany.atlassian.net/wiki/spaces/IT/pages/12345/Page+Title
  4. Select at least one content type to index under Object Types to Crawl (Space / Page / BlogPost / Attachment / Comment)
  5. To filter by file type, select MIME types in Include MIME types (optional) and Exclude MIME types (optional). You can choose from application/pdf, text/plain, image/jpeg, and application/json
  6. Click Save
The following rules apply to MIME type filtering.
  • If you select no MIME types, all supported MIME types are crawled
  • If the include and exclude settings conflict, the exclude setting takes precedence
  • Filtering works by MIME type only. You cannot specify file name patterns or regular expressions

​
Connect via Confluence (API Key)

Connect by entering your Confluence base URL, email address, and API token.

​
Required information

1

Open Knowledge Integration settings

Select Settings from the left navigation, then open the Integration tab. Click Add Integration in the Knowledge Integration section and select Confluence (API Key).
2

Generate an API token

Open Atlassian account security settings and click Create API token. Copy the generated token.
API tokens can only be viewed immediately after creation. If you miss it, generate a new one.
3

Enter connection details

Fill in the Confluence Base URL, Email, and API Token in the connection form.Click Save. A connection test runs automatically.
4

Confirm connection

When the test succeeds, a connected card appears in the Knowledge Integration section. Confirm the status shows Connected.
If the status shows Error, verify the URL, email, and API token.

​
Narrow the crawl scope (optional)

After connecting, all spaces, pages, and blog posts are crawled by default. To restrict crawling to specific spaces or pages, configure the following.
  1. Click the Configure (gear icon) on the connected card
  2. To narrow by space, enter space URLs in the Space URLs field, one URL per line (up to 100 URLs). For example, https://yourcompany.atlassian.net/wiki/spaces/IT. When you specify a space URL, the whole space is crawled. You do not need to specify each page or blog post in the space
  3. To crawl only specific pages, enter page URLs in the Page URLs field, one URL per line (up to 100 URLs). Include the page title part in each page URL. For example, https://yourcompany.atlassian.net/wiki/spaces/IT/pages/12345/Page+Title
  4. Select at least one content type to index under Object Types to Crawl (Space / Page / BlogPost / Attachment / Comment)
  5. To filter by file type, select MIME types in Include MIME types (optional) and Exclude MIME types (optional). You can choose from application/pdf, text/plain, image/jpeg, and application/json
  6. Click Save
The following rules apply to MIME type filtering.
  • If you select no MIME types, all supported MIME types are crawled
  • If the include and exclude settings conflict, the exclude setting takes precedence
  • Filtering works by MIME type only. You cannot specify file name patterns or regular expressions

​
Using Confluence with the AI Agent

Once connected, the AI agent includes Confluence in knowledge searches automatically. The AI agent does not access Confluence each time it answers a question. Instead, it searches the content that each sync imports and indexes. Pages you add or update in Confluence appear in search results after the next sync. The sync schedule is “Manual” by default. With Manual, Confluence syncs only when you click Sync Now. You can find it in the menu of the Confluence card in the Knowledge Integration section. To sync automatically, open Sync schedule in the same menu and change it to Every hour, Every 6 hours, Daily, or Weekly. You need the AI Helpdesk Admin role to run a sync or change the sync schedule. To explicitly reference Confluence in a Playbook step, use the {{document_search}} tool.

​
Read the sync history

Click the badge that shows the Confluence sync status (such as Synced) to open the sync history. The sync history shows the following counts for each of the latest 20 syncs. The sync still includes unchanged documents in Scanned and counts them as Skipped.

​
Disconnect Confluence

1

Open Knowledge Integration settings

Go to Settings > Integration tab and open the Knowledge Integration section.
2

Disconnect

Click the trash icon on the Confluence card you want to disconnect. Click Delete in the confirmation dialog.
After disconnecting, the AI agent will no longer search Confluence.

​
Troubleshooting

Status remains “Error”
  • Confluence (OAuth): Click the Reconnect button to re-run the OAuth flow
  • Confluence (API Key): The token may be expired or revoked. Generate a new token in Atlassian account settings and update the configuration
Certain pages do not appear in search results If Space URLs or Page URLs are configured, only the specified spaces and pages are searched. Check the configuration and confirm the correct URLs are included. All sync history counts are 0 after you set space or page URLs If Scanned is 0 in the sync history, no page matched the URLs you set. It does not mean that nothing changed since the previous sync.
  • Do not type a page URL by hand. Open the target page in your browser, and copy the URL from the address bar as is
  • Enter a space URL up to the space key, for example https://yourcompany.atlassian.net/wiki/spaces/IT
  • Include the page title part in a page URL. For example, https://yourcompany.atlassian.net/wiki/spaces/IT/pages/12345/Page+Title
  • You cannot save a page URL without the title part. If a URL saved earlier has no title part, the page is not imported
  • You cannot specify a folder URL
Last modified on October 1, 2026