Building AI Workflows in n8n
Connect LLMs to n8n, choose the right model, and build AI agents, chat interfaces and retrieval workflows inside n8n, including the failure modes specific to n8n's AI nodes.
12 lessons in 3 modules.
Lessons
Module 1: LLMs in n8n
- AI Automation with n8n: How to Build Powerful AI Workflows
- How to Connect n8n to OpenAI, Claude, and Local LLMs
- Integrating LLMs with n8n: Building AI-Powered Workflows Without Writing an API Client
- Choosing the Right LLM for Your n8n Automation: Cost, Speed, and Accuracy Tradeoffs
Module 2: Agents in n8n
- How to Build an AI Agent in n8n: A Complete Guide to the AI Agent Node
- n8n Chat Trigger Explained: Giving Your AI Agent a Ready-Made Chat Interface
- Why Your n8n AI Agent Node Stops Following Its System Prompt After an Update
- Why Your n8n AI Agent Burns Through Context Window Before the Task Finishes
- Wiring Claude Tool Calling Into a Slack-to-CRM Automation With n8n
Module 3: Projects
- n8n Vector Store Nodes: Building a RAG Pipeline Without Leaving n8n
- n8n and MCP: Connecting Workflows to Model Context Protocol Servers
- How to Build an AI-Powered Slack Bot with n8n
Final project
Build a Slack or Telegram assistant in n8n that answers questions from a small document set using the vector store nodes, calls one external tool (for example, a CRM lookup), and logs every conversation for review.
Next: AI Agents: From Concepts to Production