Investigate CI/CD incidents in Mattermost with an AI agent

Overview

It is a sub-workflow that investigates CI/CD failures reported by engineers in Mattermost. It is invoked by a parent classifier and it runs an autonomous AI Agent that diagnoses the failing pipeline, job, or
deployment without making any changes.

Requirements

• OpenRouter/OpenAI/Anthropic API key — for the chat model .
• MCP servers (see MCP section) .
• Mattermost credentials (native n8n node) — used to post the final reply back into the thread.
• attachmentsAnalyzer sub-workflow — must be present in the same n8n instance; analyzes files attached to the originating Mattermost message and returns a textual context.
• httpProbeTool sub-workflow — provides the probe_url tool that the agent uses to verify reachability of external dependencies; must return structured
• Parent workflow — a classifier that calls this workflow via Execute Workflow

How it works

• The workflow is invoked by another workflow via Execute Workflow Trigger
• Call 'attachmentsAnalyzer' invokes a separate sub-workflow that fetches and analyzes any files the user attached to the originating Mattermost post
• The successful branch returns enriched attachment context; the error branch goes through
• SetVars materializes the runtime configuration
• The agent is instructed to call get_thread so it can read the conversation history before pulling
  logs from anywhere else
• Post a message sends the final answer back into theoriginal channel

How to use

• Deploy MCP servers
• Configure the SetVars node with your environment
• Edit the AI Agent system prompt to match your organization
• Import sibling sub-workflows:
  • attachmentsAnalyzer
  • httpProbeTool - for probe_url node tool
• Connect a parent classifier that calls this workflow via Execute Workflow