Guides

AI for school and exams: rules, citing and checking

What to check before you use AI for school work, how to cite it, and how to use it so you actually learn instead of copying.

Free or paid AI: which plan fits you

A decision guide for choosing between a free tier, a paid plan and the API, based on how you use AI and not on price lists that go stale.

Can you tell if AI wrote a text?

Why AI detectors are unreliable, what signs people notice, and what to do if a tool says your own writing is AI.

Using AI for a CV and cover letter

How to get a CV and cover letter that sound like you, what to give the model, what to check before you send, and what never to paste into a chat.

Where your data goes when you use an AI app

A plain comparison of what to check about privacy in free chat apps, paid plans, work accounts, the API and local models.

How to install a plugin, skill or extension

Where to find the install menu in Claude, ChatGPT, Gemini, Claude Code, Cursor and VS Code, how to check an add-on before you trust it, and what to…

Ways to use AI without paying

The free ways to use AI, where each one runs out, and a simple test for whether free is enough for your task.

Turn a messy task into a prompt in five minutes

Most weak prompts come from a task nobody fully described. A five-step routine to fix that before you type, with a worked example.

Using AI to study without outsourcing the thinking

Reading a good explanation feels like understanding. Trying to use it is what builds understanding. Here is how to make a model push you toward the…

Summaries you can trust

A summary is a claim about a document, so it can be wrong in the same ways as any claim. Four habits keep it honest.

Briefing a coding assistant: the first message

A coding assistant works from what you tell it and what it can see. Here is what to put in the first message so you spend less time correcting it.

How to check what an AI tells you

A few checks that catch most wrong answers: which claims to verify, how to ask for sources, and why a confident tone tells you nothing.

What not to paste into a chat window

Anything you paste goes to a service someone else runs. What to keep out, how to redact in its place, and the one settings check worth doing.

How to write a prompt that actually works

A short checklist to run any prompt through before you send it: who, what, shape and what to leave out. Those four things separate a specific prompt…

Few-shot examples: showing instead of telling

Why two or three worked examples in a prompt often beat a page of written rules, and how to choose examples that teach the right pattern and not an…

Common prompt mistakes and how to fix them

Five patterns that reliably give a worse answer than you meant, each with a one-line fix. Use it as a checklist when a prompt keeps returning…

Add a self-critique pass before the final answer

A two-step pattern: draft, then have the model check its own draft against a specific list of failure modes. It catches a kind of mistake that a…

Force a strict output contract

How to make a model response reliably machine-parseable: exact fields, no preamble, no trailing summary. For anything that downstream code reads and…

Prompt templates worth keeping

Four reusable prompt shapes. They are structures with blanks and not finished prompts, for tasks that come up often enough to save once and stop…

Why prompt injection is not solved

What the problem is, why filtering does not fix it, and what does help. Written for someone about to give a model access to something real.

Tested on Claude Sonnet · May 2026

Meta-prompting: ask the model to write the prompt

Use a model to draft or improve the prompt before you use that prompt for the real task. It pays off for a recurring job and is overkill for a…

Giving a model a role and constraints

How naming the audience, the format and the exclusions turns unpredictable answers into repeatable ones.

Running a model on your own machine

What local models are genuinely good for, what hardware you need, and what to change in prompts that came from a hosted model.

Working with long documents and code

Why long sessions drift, what a large context window actually buys you, and how to keep a model on task across a big input.