Skip to content
UncomplicateAI

Guides

Everything, explained properly

Step-by-step guides and short explainers. Each one tells you what it costs, how long it takes, and what usually goes wrong.

Guide · Beginner

How to check an AI answer before you trust it

AI answers sound sure even when they're guessing. Three prompts to check one in two minutes, find what you missed, and spot the slant in anything it summarises.

6 min read

Guide · Intermediate

Claude Code for beginners

A practical guide to using Claude Code for real work: what it does, your first useful task, and the habits that stop it making a mess of your project.

4 min read

Guide · Intermediate

Run Hermes on a VPS (step-by-step)

Run Hermes Agent on a low-cost VPS: what server you need, what it costs, the official install commands, and how to keep it running after you log out.

7 min read

Guide · Intermediate

CLAUDE.md: the note your coding agent reads first

Claude Code reads one file before every task. Most people leave it empty or fill it with junk. What goes in, what stays out, and a prompt that writes it.

2 min read

Guide · Intermediate

Before you add an MCP server, check what it can do

Connecting an MCP server hands your AI new powers, sometimes including sending and deleting. A ten-minute check of who made it, what its tools do, and how to take it away again.

4 min read

Guide · Intermediate

Make Claude Code check its own edits with hooks

A hook is a command Claude Code runs by itself at a set moment, like after every edit. Set up one that tidies each file it touches, check it works, and know how to turn it off.

4 min read

Guide · Intermediate

Why does Ollama struggle with long documents?

On most computers Ollama starts with room for about six to eight pages. Check what yours is using, raise it carefully, and know when to split the document instead.

3 min read

Guide · Intermediate

Reach your local AI from another device privately

Use the Ollama models on your home Mac from your laptop or phone, without opening it to the internet. A free private network, one setting, and two tests to prove it.

4 min read

Explainer · Beginner

Does my AI subscription pay for API use too?

Usually not. ChatGPT and Claude plans are billed separately from their APIs. The exceptions are the companies' own apps, and one setting can quietly switch Claude Code to the API.

3 min read

Explainer · Intermediate

When should Claude Code use a subagent?

A subagent is a helper Claude Code sends off to do one focused job and report back. When that saves you a cluttered session, and when it only burns more of your allowance.

2 min read

Explainer · Beginner

Six more AI tools worth knowing about

Canva, Microsoft Copilot, Descript, Gemini, LM Studio and NotebookLM: what each one is, who it suits and what it costs. Orientation, not reviews.

3 min read

Explainer · Beginner

What is SSH, and what is an SSH key?

SSH is how you log in to a computer somewhere else, like a rented server, from your own terminal. What an SSH key is, and the one command you type.

1 min read

Explainer · Beginner

What is the terminal, and how do I use it?

The terminal is a window where you type instructions to your computer instead of clicking. How to open it on a Mac or Windows, paste a command, and stay safe.

1 min read

Guide · Intermediate

Basic server security for non-developers

You rented a server and put an agent on it. Now robots are probing it. Four things, in order, that handle most of the risk, and a prompt to do them.

2 min read

Guide · Beginner

Check a contract for the bits that bite

Tenancy, phone, gym, freelance job. Paste it and get the clauses that cost you money or lock you in, in plain English, before you sign. Not legal advice.

2 min read

Guide · Beginner

Let it interview you, then write your CV

Writing about yourself is the worst writing there is. Talk about your job for ten minutes instead and get a CV that sounds like you.

2 min read

Guide · Beginner

Projects: keep a long job in one place

ChatGPT Projects and Claude Projects, explained. If a job lasts longer than one chat, it belongs in a Project: the files, instructions and every chat about it.

2 min read

Guide · Beginner

Three automations that actually save time

Not the impressive ones. Three boring, scheduled jobs that quietly changed how my week runs, what each one does, and the prompt to set it up.

3 min read

Guide · Beginner

Turn off 'use my chats to train the model'

How to stop ChatGPT, Claude and Gemini training on your chats. One setting turns it off in each app and changes nothing else. Two minutes, once.

1 min read

Guide · Beginner

Upload a PDF and ask it questions

Upload a PDF to ChatGPT, Claude or Gemini and ask what you want to know, with page numbers so you can check, plus the rule that stops it guessing.

2 min read

Guide · Intermediate

Which local model should you actually run?

The model list changes monthly, so this page does not rank them. What fits in 8 GB or 16 GB of memory, a prompt that picks for your machine, and a one-week test.

2 min read

Guide · Beginner

Your first ten minutes with ChatGPT

Download it, skip the tour, and do four things that show you what it is actually for. Ten minutes, no card, and you will know whether it is for you.

2 min read

Explainer · Beginner

API, decoded

You will see the word on every pricing page. An API is how one program talks to another. What it means for you, when you would use one, and the price trap.

2 min read

Explainer · Beginner

You may already pay for a coding agent

If you pay for ChatGPT, Codex is included: a coding agent that works on your real files. Most subscribers never open it. Try it in five minutes.

2 min read

Explainer · Intermediate

Compact or restart? Keeping Claude Code sharp

Long coding sessions go stale for the same reason long chats do. Claude Code gives you two ways out, and picking the right one makes or breaks the afternoon.

2 min read

Explainer · Beginner

Deepfake, decoded

What is a deepfake? A video, photo or voice faked to look like a real person. How they are made, why phone calls are the dangerous ones, and three checks.

2 min read

Explainer · Beginner

Hallucination, decoded

The word everyone uses for AI making things up, in one page: what it is, why it happens, where it happens most, and the two habits that catch it.

1 min read

Explainer · Beginner

Open source, decoded

Open source means the code or model is public and you can run it yourself. What that buys you, what it costs, and why so many AI tools say it on the label.

2 min read

Explainer · Beginner

Reasoning model, decoded

What is a reasoning model? It works the problem out before answering, so you see a pause. Good for maths, planning and tricky code. Is the wait worth it?

1 min read

Explainer · Beginner

Tokens and the context window, decoded

What is a context window, and what is a token? Two words behind most AI pricing and limits: a token is a piece of a word, the window is how many fit at once.

2 min read

Explainer · Beginner

What AI can actually do for you today

The one-page tour for people who have never really used AI. Nothing to install, nothing to pay for, and a prompt to try in the next two minutes.

2 min read

Explainer · Intermediate

What goes wrong with an always-on agent

I have run one for months. It fails quietly, loops expensively, forgets, and sometimes does the confident wrong thing. Five failures and how to catch each.

2 min read

Explainer · Intermediate

MCP, decoded

What is MCP, and what is an MCP server? MCP is the plug standard that lets an AI assistant use a tool like your calendar. The server is the tool's end of the plug.

2 min read

Explainer · Beginner

Five things never to paste into an AI

Most things are fine to type into ChatGPT or Claude. Five are not, and the list is short enough to remember. Plus the one setting worth turning off.

2 min read

Explainer · Beginner

Which model should I use? The one-page answer

ChatGPT and Claude both have a model menu and neither explains it. The only distinction that matters day to day, and the three-line rule I use to pick.

2 min read

Explainer · Beginner

Why every post here is under 400 words

You came here to do a thing, not to scroll. Every post here is short on purpose: the answer first, one prompt to paste, nothing to wade through.

1 min read

Guide · Intermediate

Open your server's website on your Mac

A small server often cannot open a browser. Here is how to view its website on your Mac, plus a prompt your agent can use to set it up.

2 min read

Explainer · Intermediate

Two ways to let AI use your browser

Two ways to let an AI use a web browser for you. One reads the screen and moves the mouse. The other talks to the browser directly. Which suits a local model.

7 min read

Explainer · Beginner

What is an AI agent?

An AI agent is a program that can decide what steps to take and then take them. Here is the plain English version, and where the idea is oversold.

5 min read

Explainer · Beginner

What is AI, actually?

The plain-English guide to prediction, training data and using AI to learn what you do not yet know.

4 min read

Guide · Intermediate

How to run local AI models (without coding)

A simple guide to running powerful open-source models on your own computer. No coding, no subscription, and nothing you type leaves the machine.

2 min read

Explainer · Beginner

What is a VPS?

A VPS is a small computer you rent on the internet. Here is what that actually means, what it costs, and why you would want one.

5 min read

Explainer · Beginner

What is local AI?

Local AI means running the model on your own computer instead of somebody else's. What you gain, what you give up, and if your machine can cope.

5 min read

Get new guides by email

Occasional and practical. No spam, no hype, unsubscribe whenever.

Occasional practical guides from UncomplicateAI. You will get a confirmation email before anything else is sent. Unsubscribe any time. Privacy

You are not subscribed until you confirm the email. Unsubscribe any time.