Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Chatbots & Messaging Bots

Chatbots & Messaging Bots

Answer Slack DMs from Confluence with an OpenAI Agent

When a Slack direct message arrives by webhook, an OpenAI agent with memory searches Confluence and replies in Slack.

Import it free Sign in to open it

What it does

![n8n]({{ $env.WEBHOOK_URL }} ## Build n8n workflow to query Knowledge Base Building your own tools for an AI Agent to use is simple and straightforward, but requires that you build a second workflow and then connect it to this one by inputting the workflow ID from the workflow URL in the *Custom n8n KB Tool* sub node. This gives you the freedom to work with any tool, whether n8n has support for it or not. In this sample build, we have connected the AI agent to Confluence, which does not have a native built in n8n node. For this we use the HTTP request node and pointed it to Confluence's search api. It then returns a response that the AI agent uses to generate a final slack message response to the user.

The steps

  1. Verify Webhook
  2. OpenAI Chat Model
  3. No Operation, do nothing
  4. Window Buffer Memory
  5. Check if Bot
  6. Send Initial Message
  7. Delete Initial Message
  8. Send Message
  9. Receive DMs
  10. Call Confluence Workflow Tool
  11. AI Agent
  12. Error Handler
  13. Stopanderror 1
  14. Error Handler for 96ef3bfe

34 steps in total.

Similar automations

Chatbots & Messaging BotsAnswer Slack Mentions and DMs with a Context-Aware Bot12 stepsRAG & Knowledge BasesChat with a Confluence Page Using an OpenAI Chatbot34 stepsRAG & Knowledge BasesChat with Confluence Pages Using GPT-4o-mini12 stepsDocuments, PDF & OCRCreate Confluence Pages from Templates via Webhook33 steps