Automation specialists, power users of n8n, and developers who have a baseline setup of local LLMs and want to transition from linear workflows to reasoning-based autonomous agents.

Must have n8n and Ollama set up on local machine.

Course Outline:

The Anatomy of an AI Agent

1. 1. Agentic Reasoning: Understanding the difference between a “workflow” and an “Agent”
   2. The AI Agent Node: Deep dive into Model inputs, tools and system prompts
   3. Giving the Agent “Hands”: How tools allow the LLM to execute code and fetch data
   4. Lab: Setting up your first Agent node and defining its “Persona”
2. Memory Management: Giving the AI a Brain
   1. The Context Window Problem: Why “forgetting” happens in long conversations
   2. Window Memory Buffer: Maintaining the last “n” exchanges for immediate relevance
   3. Summary Memory: Using the LLM to compress past interactions for long-term efficiency
   4. Lab: Implementing and testing different memory types in a live chat interface

3. The Research Spirit: Building the Autonomous Researcher
   1. Search Tool Integration: Connecting Tavily and/or Google Search to your Agent
   2. Recursive Problem Solving: How agents break down a prompt into multiple search tasks
   3. Synthesizing Results: Prompt engineering for clean, cited outputs
   4. Lab: Build and run a “Research Agent” that provides a 3-point summary of a trending topic

Training material provided: Yes (Digital format)

Hands-on Lab: Students will be provided with docker compose file and n8n workflow JSON.