Technology
11 min read
Generated code that works can still be vulnerable, depend on a package that should not be trusted, or resemble code with a licence you must respect. This article lists the common security weaknesses, shows a SQL injection example you can run, gives a short security review routine and explains licensing questions without pretending to be legal advice.
Technology
10 min read
AI-written code often passes AI-written tests, because both come from the same assumptions. This article shows how to write tests that check what the code should do, how to use AI as a second reviewer without relying on it, what to look for in AI-generated diffs, and how to refactor safely.
Technology
9 min read
Pasting an error into an assistant can solve a bug in a minute, or produce a patch that hides it. This article gives a safe debugging workflow: reproduce, share safely, ask for hypotheses, test them, review the fix, add a regression test, with a worked example and a list of dangerous 'fixes'.
Technology
10 min read
Reading code is the safest and often most valuable use of an AI assistant: nothing changes until you decide it should. This article covers explaining unfamiliar code, mapping a codebase, learning an API or framework, writing documentation and brainstorming architecture, with the checks that catch confident mistakes.
Technology
9 min read
Autocomplete, chat, edit mode, agents and review bots all promise faster coding. This article explains what each mode does, how to give it the context it needs, what the evidence says about speed and security, and the responsibilities that stay with you no matter who typed the code.
Technology
10 min read
AI is a tireless thinking partner for generating options, breaking work into steps and stress-testing plans. It is a poor decision-maker, because it does not share your values or consequences and tends to agree with you. This article shows how to use it to think better while keeping the decision yours.
Technology
11 min read
AI is excellent at explaining formulas, cleaning messy columns and suggesting how to analyse data, and unreliable as a calculator. This article shows how to have the AI propose the method while the spreadsheet or code does the arithmetic, with reconciliation checks and a worked example of a classic mistake.
Technology
10 min read
AI summaries save hours, and they fail in quiet ways: a missed 'not', an invented owner, a decision that was never made. This article shows how to extract decisions and actions from meetings, summarise long documents for a purpose, and build a note system that you can search and trust.
Technology
10 min read
AI can draft, tighten and restructure workplace writing in seconds, but it can also invent commitments and make everything sound like everyone else. This article gives a facts-first drafting workflow, ways to keep your own voice, and a checklist to run before you hit send.
Learning
9 min read
Using AI in your studies raises three separate questions: what your institution allows, whether you are actually learning, and whether you can still do the work without it. This article gives you honest rules, warning signs of dependency and a personal AI-use agreement you can write in ten minutes.
Learning
10 min read
Turn the notes you already have into questions, flashcards, practice problems and a revision schedule, with AI doing the preparation and you doing the remembering. Includes prompts, a worked example with a deliberate AI error, and a way to keep your cards accurate.
Learning
11 min read
'Explain everything about this topic' produces a wall of text you will forget. This article shows a better loop: tell the AI what you already know, learn in layers, try problems yourself, ask for hints instead of answers, and test your understanding. With a full worked session.
Technology
11 min read
The first AI answer is a draft. This article teaches how to give feedback that actually improves it, how to ask the AI to critique and offer alternatives without being fooled by agreement, how to split big tasks into checkable steps, and when the real problem is not the prompt at all.
Technology
11 min read
Showing the AI one or two examples often beats three paragraphs of description. This article covers example-based prompting, choosing an output format, and requesting structured output such as JSON that a program or spreadsheet can use, with the checks that make it safe.
Technology
9 min read
The single biggest upgrade to AI answers is not a cleverer prompt. It is giving the model the right material to work from and making it show where each claim came from. This article teaches grounding, quote-first answers and how to handle long documents.
Technology
12 min read
A good prompt is not a magic phrase. It is a clear brief. This article shows how to state your goal, give context, set constraints and choose a format, and why each one changes what the AI produces.
Technology
10 min read
Instead of asking which AI product is best, ask which kind of AI fits the task. This article sorts today's tools into capability categories, explains what each is good and bad at, and gives you a method for testing tools on your own work.
Technology
11 min read
Hallucinations are not random glitches. They follow predictable patterns that you can learn to spot. This article explains why fluent AI answers can be false, where errors cluster, and which habits reduce them, with an honest account of what no habit can fix.
