Obsidian + Codex Federated Knowledge Base
Shows how kb status, lookup, promote, and publish form narrow interfaces that let AI reuse, promote, and publish knowledge without crossing boundaries.
Guides, implementation notes, and repeatable workflows for tools and projects.
Choose the route that matches your current problem, then read the connected pieces in order.
Shows how kb status, lookup, promote, and publish form narrow interfaces that let AI reuse, promote, and publish knowledge without crossing boundaries.
You do not need to become an AI expert first, and you do not need to learn a pile of jargon. What ordinary people really need to practice is describing goals, boundaries, and acceptance criteria clearly. One command-line window where you type plain English and an AI does the work.
A plain-language entry point for people who use phones and computers but do not yet know hosting, GitHub, or DNS: start from one clean folder and let Codex guide the route.
A beginner-friendly guide for creators, families, engineers, and non-programmers who want a durable home on the web.
Browse every published guide after you have chosen a route, or when you are looking for one specific article.
Shows how knowledge moves from evidence to wiki, then through publication source, prepare, review, and sync into a traceable public article.
Shows how kb status, lookup, promote, and publish form narrow interfaces that let AI reuse, promote, and publish knowledge without crossing boundaries.
A practical comparison and installation guide for Codex CLI, OpenCode + MiniMax-M2.7, and Qwen Code + MiniMax-M2.7 as local AI coding CLI workflows.
Series appendix, long-term maintained. Only entries that ordinary people will encounter and that affect their choices or safety boundaries. Each entry under 250 words. When products change, update facts first without rewriting series positions.
The same AI capability in a different interface can do completely different things. A phone app is best for quick questions, a web chat for writing, a desktop client for local materials, and CLI is best for turning one directory into an AI workstation.
"Most advanced" does not equal "most suitable for ordinary people to use reliably." Different regions, account types, phone numbers, payment methods, and network conditions affect which tools you can actually use. The best combination for ordinary people is one that reliably gets things done.
You do not need to memorize a list of product names. ChatGPT, Claude, Codex, Perplexity, Kimi — they are all essentially four types of tools: conversational, search, generative, and action. Know the four types and you will not get lost in product names.
You do not need to become an AI expert first, and you do not need to learn a pile of jargon. What ordinary people really need to practice is describing goals, boundaries, and acceptance criteria clearly. One command-line window where you type plain English and an AI does the work.
The first step should not be folder design. Create one empty folder, start Codex there, and let Codex choose the first project structure.
After Codex creates the first personal website in an empty folder, focus on the local preview, clear pages, and privacy risks.
After the local site works, let Codex guide the GitHub and Cloudflare Pages authorization flow with copy-paste prompts instead of manual upload.
After the free URL works, ask Codex whether a custom domain is worth buying. You confirm accounts, domain choices, and page states; you do not need to learn DNS first.
After launch, change one thing at a time: ask Codex for a plan, preview locally, check, and publish with the workflow this project actually uses.
Once your personal site can be published and updated, copy one fixed pre-publish prompt so Codex checks privacy, images, links, and phone readability before every release.
A plain-language entry point for people who use phones and computers but do not yet know hosting, GitHub, or DNS: start from one clean folder and let Codex guide the route.
Only explains the terms that affect ordinary people's choices and safety boundaries. Each term in three sentences: one plain-language explanation, one scenario, one suggestion. No academic definitions, no jargon explaining jargon.
Wrapping up the series with a copyable personal workflow configuration. One stable computer, one project directory, one command-line AI tool, one confirmation habit — this is the foundation for ordinary people using AI for real work.
Ground abstract capabilities into real life and work. Ten categories of things ordinary people can complete with AI today — each with a concrete scenario and a copyable prompt.
Establishing safety boundaries so this series does not read like advertising. Do not casually upload ID cards, bank cards, or complete family privacy details. Do not let AI make medical, legal, or investment decisions for you. Letting AI do work does not mean handing over your judgment.
CLI is not advanced — it is the cleanest entry point: no buttons to navigate, just one question — what do you want to do? Ordinary people do not need to learn a full software workflow first. They just need to state the goal and let AI guide them through the rest.
We start not from cd, npm, or git theory, but from one real scene: create a folder, open Codex, type one complete goal. Codex will guide you through the entire process. You only need to confirm at key moments.
A beginner-friendly guide for creators, families, engineers, and non-programmers who want a durable home on the web.
A practical cost breakdown for Codex, domains, static hosting, storage, email, and the upgrades that may come later.