Skip to main content

Confluence

Connect your Confluence wiki to Squid to give AI agents searchable knowledge of your documentation​

The Confluence connector's functionality​

The Confluence connector reads the pages in your Confluence spaces into a knowledge base, enabling Squid AI agents to answer questions using your documentation:

  • Squid syncs your Confluence spaces in the background, refreshing every 10 minutes. Page content is indexed for semantic search, and images embedded in pages are included.
  • AI agents connected to the Confluence connector can perform semantic searches over the indexed content, so users can ask questions like "How do we onboard a new customer?" and get answers sourced from your wiki.
  • Both Confluence Cloud and Data Center instances are supported.

The connector provides read-only access: agents can search and reference your Confluence content, but cannot create or edit pages.

Creating a Confluence API token​

Adding the Confluence connector to your Squid application​

  1. Navigate to the Connectors tab in the Squid Console.

  2. Click Available Connectors.

  3. Find the Confluence connector, and select Add Connector.

  4. Provide the following configuration details:

Connector ID: A string that uniquely identifies the connector in your code.

Domain: The fully qualified domain of your Confluence instance, such as mycompany.atlassian.net.

Email: For Confluence Cloud, the email address associated with your Atlassian API token. Leave empty for Data Center instances using a Personal Access Token.

API Key: Your Atlassian API token (Cloud) or Personal Access Token (Data Center). The token is stored securely as a Squid secret.

Cloud ID: Optional. Your Atlassian Cloud ID, required when your instance cannot be accessed via its subdomain. When set, API calls are routed through api.atlassian.com.

Spaces: Optional. A comma-separated list of Confluence space keys to sync, such as ENG, DOCS. To scope a space to specific top-level pages, use the format spaceKey[pageId1, pageId2]. Leave empty to sync all spaces.

note

Personal spaces are not synced unless you explicitly include them in the Spaces list. After adding the connector, allow some time for the initial sync of your spaces to complete.

Using the Confluence connector in your application​

No-code Studio​

  1. Navigate to the Studio tab in the Squid Console.

  2. Click Create AI Agent.

  3. Provide an agent ID and description, such as "docs-agent" and "This agent answers questions using our Confluence documentation".

  4. Click Add Abilities.

  5. Expand the Confluence entry and select the Confluence connector you created earlier.

  6. Give a description for how the agent should use this connection, such as "Call this when a user asks a question that may be answered by our internal documentation."

  7. Click on Test and try asking the agent a question about content in your wiki.

Using the Squid SDK​

If you are creating your AI agent with the Squid SDK, connect the Confluence connector by adding it to the connectedIntegrations option of the ask() function:

await this.squid
  .ai()
  .agent('AGENT_ID')
  .ask('How do we onboard a new customer?', {
    connectedIntegrations: [
      {
        integrationId: 'CONFLUENCE_CONNECTOR_ID',
        integrationType: 'confluence',
        description: 'Call this connector to search our Confluence documentation',
      },
    ],
  });

To learn more about interacting with an agent from the SDK, view the AI agent documentation.