Practical Projects
Build-along projects: bots, agents, chatbots and pipelines you can reproduce.
Articles in Practical Projects
- How to Build a Golden Test Set for LLM Extraction and Classification Workflows — Tweaking a prompt without measuring it just trades one failure for another. A golden test set turns opinion into evidence. Here is how to source examples, label them, choose metrics and run the set on every change.
- n8n Vector Store Nodes: Building a RAG Pipeline Without Leaving n8n — n8n's LangChain-based nodes cover the full RAG loop -- document loading, chunking, embedding, and storage in a vector index -- as native nodes, which means a basic retrieval-augmented generation pipeline can be built entirely inside n8n without a separate application layer.
- n8n and MCP: Connecting Workflows to Model Context Protocol Servers — MCP standardizes how an AI agent discovers and calls tools. n8n now speaks both sides of that protocol -- it can act as an MCP client, calling tools exposed by an external MCP server, and expose its own workflows as MCP tools for other agents to call.
- Building Your First AI Agent with the GPT-6 Astra API: A Step-by-Step Developer Guide — A hands-on walkthrough of building a tool-calling research agent with GPT-6 Astra, covering tool definitions, the reasoning loop, structured output, error handling, and where human checkpoints belong.
- Building a Content Moderation Pipeline with the Gemini API — Safety settings control what Gemini will and will not generate. A moderation pipeline is a different problem: using Gemini to classify content other users submitted. Here is how to build one correctly, including what to log and how to handle appeals.
- Building a Discord Bot with the Gemini API — A working Gemini-powered Discord bot is a few dozen lines of Python: one event handler, one Gemini call, one reply. Here is the complete pattern, including the conversation-memory and streaming details a naive version misses.
- Building Multi-Tool Agents with the Gemini API — Function calling, code execution, grounding, and File Search each work well alone. An agent is what happens when a model decides, turn by turn, which of them to reach for. Here is how to build one, manually and with Google ADK.
- Building AI Agents with LLM Function Calling: A Developer's Integration Guide — Every AI agent, no matter how sophisticated it looks from the outside, is built on the same primitive underneath: a loop where the model requests a function call, your code executes it, and the result goes back in. Here's how that loop actually works.
- Building an LLM-Powered Chatbot: Architecture, Integration, and Deployment Guide (2026) — A chatbot demo and a chatbot people actually use daily differ in everything the demo skips: conversation state, streaming, guardrails, and what happens when the model tries to do something it shouldn't. Here's the full architecture.
- How to Build an AI-Powered Slack Bot with n8n — A step-by-step guide to building an AI-powered Slack bot in n8n that answers questions, looks up information, and takes action inside Slack — using the AI Agent node and Slack's app events.
- How to Build an AI Agent in n8n: A Complete Guide to the AI Agent Node — A hands-on guide to n8n's AI Agent node — how it differs from a plain LLM call, how to configure models, tools, and memory, and how to build a reliable AI agent workflow step by step.
- How to Build a RAG Chatbot with n8n and Supabase — A step-by-step guide to building a RAG chatbot using n8n and Supabase's pgvector - no separate vector database or custom backend required.