Skip to main content

Confluence User Connector

Connect your own Confluence account to Abacus.AI so that ChatLLM Teams chats with RouteLLM, the Abacus AI Agent and Custom Chatbots can work with your Confluence data under your own identity. The connector can only see what your Confluence account can see, and the activity is recorded against your account in Confluence.

Prerequisites​

  • Access to ChatLLM Teams
  • A Confluence account with access to the spaces you want to search

Scopes and permissions​

The Confluence connector uses the Abacus.AI application and requests a fixed set of permissions (OAuth scopes) that the Confluence tool needs. You review and approve them on the Confluence consent screen when you connect, and you can only ever access data that your own Confluence account is allowed to see.

No configuration is needed on the Abacus.AI side, and there is no config connector for Confluence. To revoke access later, remove Confluence from Profile → User Connectors; you can also revoke the Abacus.AI app from your Confluence account settings.

Use Confluence in ChatLLM​

Step 1 — Connect Confluence​

In ChatLLM Teams, click the Connectors link on the home page, or click your profile in the top right and navigate to Profile → User Connectors.

Add Connectors panel listing available user connectors
  1. Scroll the connector list and click Confluence.
  2. A browser pop-up opens asking you to sign in to Confluence and authorize Abacus.AI.
  3. Review the requested permissions and click Allow (or Authorize).
  4. After authorization completes, Confluence appears under your connected services and is ready to use.
info

User connectors are configured once per user and run under your own identity. After the connector is set up, every chatbot and the Abacus AI Agent in your workspace can query data from it.

Step 2 — Chat with RouteLLM​

  1. Open a new chat in ChatLLM Teams.
  2. From the model selector, choose RouteLLM (route-llm). RouteLLM automatically routes each request to the most suitable underlying model, and is available for unlimited use to ChatLLM subscribers.
Selecting RouteLLM from the chat model selector
  1. Ask a question that references Confluence, for example "Find Confluence pages about our onboarding process". RouteLLM invokes the Confluence tool, fetches the data under your identity, and responds in chat.

The first time you query a newly connected service in a chat, you may be prompted to authorize the connector. Complete the sign-in once and the request continues automatically; subsequent requests reuse the connection.

tip

You don't need to train a Custom Chatbot to use Confluence with RouteLLM. Once the connector is configured in the User Connectors panel, it is immediately available across your workspace chats and to the Abacus AI Agent.

Optional: use Confluence in a purpose-built Custom Chatbot

If you want a dedicated bot with its own instructions and a restricted set of tools, train a Custom Chatbot in the Developer Platform and, under Advanced Options → Tool Use, select Confluence_tool. End users of that chatbot are prompted to sign in to Confluence once, and the bot then acts under each user's own identity. See the Custom Chatbots guide for the full training and deployment walkthrough.

Troubleshooting​

  • The authorization pop-up does not appear: allow pop-ups for the Abacus.AI site in your browser and click Confluence in the User Connectors panel again.
  • "Not authorized" or stale results: remove Confluence from Profile → User Connectors and connect it again to refresh the authorization.
  • Some items are missing: the connector cannot see more than your own Confluence account can. Check your access in Confluence itself.