Guides

Handbooks that actually ship.

Developer tutorials written the way we build: reproducible, honest about gotchas, and short enough to finish.

How-to Beginner 35 min read

How to Build an AI Workflow with n8n

Build a working AI workflow in n8n: Chat Trigger to AI Agent with an OpenAI model and a Wikipedia tool, copy-ready import JSON, verification, and real error fixes.

Prereq: An n8n instance (we recommend the free n8n Cloud trial for this walkthrough); a self-hosted instance needs port 5678 reachable · An OpenAI API key - get one at platform.openai.com

Start the guide →

How-to Beginner 30 min read

How to Choose an Open-Weight Model for Your Use Case

License, VRAM, context, coding vs general, price per token - the five decisions that pick the right open-weight model, with a comparison table you can sort.

Prereq: A rough idea of your job: chat, coding, long documents, or agent loops · Know your hardware budget - RAM/VRAM if self-hosting, or an API budget per month

Start the guide →

How-to Intermediate 30 min read

How to Compare AI Models Like a Pro (2026 Method)

Leaderboards are starting points, not verdicts. The 2026 method: define your workload, read harness configs, price the token loop, and run your own blind side-by-side.

Prereq: A workload you actually run (20-50 real prompts on your own data beats any public leaderboard) · Access to at least two candidate models - hosted APIs or your local Ollama from our install guide

Start the guide →

How-to Beginner 30 min read

How to Install and Use Ollama (2026 Guide)

From zero to running open models: install Ollama on macOS, Windows or Linux, pull and chat with your first model, and fix the errors everyone hits.

Prereq: A computer with at least 8GB of RAM (16GB makes models noticeably faster) · A terminal - Terminal.app, PowerShell, or any Linux shell

Start the guide →

How-to Beginner 25 min read

How to Pick an AI Code Assistant

Claude Code, GitHub Copilot, OpenAI Codex, or Gemini CLI? Real pricing, strengths, and limits as of August 2026, plus a decision table to pick yours.

Prereq: Any code editor or terminal you already use · An account you can log into: GitHub (Copilot), Google (Gemini CLI), Anthropic or OpenAI (Claude Code / Codex)

Start the guide →

How-to Beginner 25 min read

How to Protect Yourself from AI Scams

Voice cloning, deepfakes, AI phishing, and fake AI tools: recognize the schemes, verify before you pay, and report - FTC, FBI IC3, and SEC verified.

Prereq: 10 minutes to set up a family code phrase and review your social media privacy settings · A phone where you trust saved contact numbers of family and your financial institutions

Start the guide →

How-to Intermediate 35 min read

How to Run DeepSeek V4-Flash Locally

From 82.5GB IQ1 to the official 166.9GB build: pick your quantization tier, then serve DeepSeek V4-Flash-0731 with Ollama or llama.cpp on the hardware you have.

Prereq: A machine with at least 96GB of system RAM and one GPU with 80GB+ VRAM (two 80GB GPUs if you want the 4-bit tier) · A terminal and 120GB+ free disk space for the model files

Start the guide →

How-to Beginner 25 min read

How to Run Local LLMs on a Laptop

What fits in 8-64GB RAM, what Q4/Q8 quantization really means, CPU vs GPU vs Apple Silicon speed reality, and the exact commands for your first local LLM.

Prereq: A laptop with at least 8GB of RAM (16GB makes a visible difference) · About 10GB of free disk for your first model

Start the guide →

How-to Beginner 30 min read

How to Set Up Claude Code (Install, Permissions, Config)

From zero to a production-ready Claude Code 2.1.231 setup: verified install, auth, permission modes, CLAUDE.md, MCP, and the security settings that keep an agent from running wild.

Prereq: macOS, Linux, or Windows (WSL2) with Node 18+ · A Claude account - the free tier is enough to set up and test permission modes

Start the guide →

How-to Intermediate 30 min read

How to Use MCP (Model Context Protocol)

Connect AI apps to your files, GitHub, and databases with MCP: two copy-ready server configs (Filesystem + GitHub), verify-it-worked checks, and real error fixes.

Prereq: Node.js 18+ (the Filesystem and many other reference servers run through npx) · An MCP-capable client: Claude Desktop, Claude Code, VS Code (Copilot), Cursor, or ChatGPT

Start the guide →

How-to Beginner 30 min read

How to Use Open WebUI

Open WebUI setup: the official Docker command, one-step Ollama connection, first chat, theme and persona basics, and the real errors - all verified today.

Prereq: Ollama installed and running (our install guide gets you there in 10 minutes) · Docker Desktop or Docker Engine (the officially recommended path) - or Python 3.11/3.12 for the pip route (3.13 is NOT supported yet)

Start the guide →

How-to Beginner 25 min read

Run Open-Source LLMs Locally: The 2026 Guide

From zero to a private, offline LLM stack on your own hardware: Ollama, Open WebUI, quantization, and the models worth running in 2026.

Prereq: A Mac, Windows PC, or Linux machine with 16GB+ RAM (an NVIDIA GPU helps but isn't required for 8B models) · A terminal and roughly 1.5GB of free disk

Start the guide →

How-to Intermediate 45 min read

Build Your First Autonomous AI Agent in a Weekend

The 2026 edition: a real, runnable LangGraph agent with tools, memory, and a human-in-the-loop gate - verified against the official quickstart, not pseudo-code.

Prereq: Python 3.10+ and a terminal · A model endpoint - your local Ollama from our install guide works perfectly via localhost:11434/v1

Start the guide →