About

By

Hi — I'm Mitch, and I started The AI Cheat Sheet for a simple reason: AI tools are useful, but most of the writing about them is either breathless hype or so technical it's useless to a normal person who just wants to get something done.

Who I am, and why I write this

I work as a software analyst. My day job is writing requirements for software features, manually testing them before they reach customers, and digging through databases when something doesn't behave the way it should. I've spent years on the unglamorous side of software — the part where you find out that the thing which demos beautifully falls apart on the third real-world edge case.

That's the lens I bring here. Testing software for a living makes you permanently suspicious of a polished feature list. It also gives you a habit that turns out to be exactly right for writing about AI tools: you don't trust what a product claims, you go use it on a real task and see what actually happens. Every article on this site comes out of that process — me sitting down with a tool, giving it a job I actually needed done, and reporting back on where it helped and where it quietly fell over.

I'm not an AI researcher and I don't pretend to be. I'm a working person who uses these tools daily and writes down what I learn, for other working people.

What I test on

As of September 2026, I run these guides on a ChatGPT Plus subscription, a Claude Max subscription, and the free tier of Gemini. Where a guide covers a tool I only have on a free plan, I say so in the article, because free and paid tiers often behave differently. I pay for these accounts myself; no vendor provides access or sees a draft.

Who this site is for

Everything here is written for people who aren't developers or "AI experts" — solo workers, small-business owners, students, and anyone who's curious but doesn't want a computer science degree to make sense of it all. I focus on practical, specific, do-it-today guidance: how to actually clean up a messy spreadsheet, draft an email that still sounds like you, or turn a 40-page PDF into something you can skim in a minute.

If you've ever opened ChatGPT, typed something in, gotten a mediocre answer back, and quietly concluded the whole thing was overhyped — this site is for you. Usually the tool wasn't the problem. Usually nobody had told you the one or two things that make it work.

How I write these articles

A few standards I hold myself to, so you know what you're reading:

  • I use the tool before I write about it. Not a feature page, not a press release — the actual product, on an actual task.
  • I don't invent numbers. You will never find a made-up accuracy percentage, a fabricated star rating, or a benchmark score I didn't run on this site. If I don't have a hard number, I describe what I observed instead.
  • I name the limits. Every tool I cover has things it's bad at, and I'd rather tell you up front than have you discover it on something that matters. Most articles here have a section devoted to exactly this.
  • I'm careful with prices and features. This industry changes weekly. I avoid quoting exact prices that will be wrong in a month, and I tell you to check current terms yourself.
  • I update instead of abandoning. When a tool changes meaningfully, I go back and fix the article rather than leaving stale advice up to rot.
  • I correct mistakes. If I get something wrong and you tell me, I'll fix it and say that I did.
  • How AI is used on this site. Most of what you read here is drafted and edited by an AI (Claude) working from my instructions — this site is partly an experiment in whether an AI can run a useful website. The tests happen in my own paid accounts, I set the topics and the standards, and I'm the one answerable for mistakes: email me and I'll fix it.

What's been tested so far (updated 12 September 2026): the same email prompt in ChatGPT, Claude and Gemini; a four-row customer list cleaned in ChatGPT; a BLS statistic traced to its source page; ChatGPT's data-controls page with model training switched off; a resume rewritten; a week's meal plan; a pasted spreadsheet analysed; a paragraph proofread for errors only; flashcards made from one passage; rough notes turned into a clean summary; a professional email drafted from a four-part prompt; and a prompt rewritten with the framework from the prompts guide. When a post has no screenshot, I haven't run that test yet.

How this site makes money

The AI Cheat Sheet is free to read and funded by display advertising. Ads are served by Google AdSense and are chosen automatically — I don't hand-pick them, and no advertiser has ever seen an article before it was published, let alone influenced one.

If I ever add affiliate links to tools I recommend, I'll label them clearly on the page where they appear. What I won't do is let a payout decide a ranking. A recommendation on this site is worth exactly nothing to you if it can be bought, so it isn't for sale.

Get in touch

Corrections, questions and disagreements are welcome — the disagreements especially. Email me at acheatsheet@gmail.com or use the Contact page. If you report a factual error, I'll fix the article and add a dated note saying what changed.

Get the next guide by email

A new tested how-to when there is one — usually a couple a month. No hype, unsubscribe any time.

© 2026 The AI Cheat Sheet  ·  About  ·  Contact  ·  Privacy Policy  ·  RSS
Tested in real accounts. No affiliate links.

Popular posts from this blog

How to Use AI to Write and Tailor Your Resume and Cover Letter

By
Image
Applying for a job has a cruel little math problem at the center of it. To have a real shot, every resume and cover letter should be tailored to the specific posting — but tailoring twenty applications by hand is exhausting, so most people send the same generic resume everywhere and wonder why they never hear back. This is exactly the kind of tedious, repetitive writing that AI tools like ChatGPT , Claude , and Gemini are good at. Not because they'll invent a better you, but because they'll help you take the real experience you already have and aim it precisely at the job in front of you, in a fraction of the time. The key thing to understand up front: AI is not going to write your resume from nothing, and you don't want it to. It doesn't know your accomplishments, and if you let it guess, it will make things up . What it's brilliant at is taking material you feed it and reshaping, tightening, and matching it to a target. Give it the raw truth about you...
Read more

How to Spot AI Scams and Deepfakes Before They Cost You

By
Image
Not long ago, you could spot a scam by its bad grammar. The clumsy email from a "prince," the text riddled with typos, the robotic phone voice — they carried their own warning labels. That era is ending. The same AI tools that help you write a clean email now help scammers write flawless ones, clone a voice from a few seconds of audio, and generate a photo of a person who doesn't exist. This isn't a reason to panic, but it is a reason to update your instincts. The old tells are fading, and a few new habits do a much better job of keeping you safe. The good news is that AI has not changed what scammers ultimately want or how they operate. They still need you to do something — send money, hand over a password, click a link, buy gift cards. AI just makes their bait more convincing. So while you can't always spot the fake by looking at it anymore, you can still catch nearly all of these schemes by paying attention to what you're being asked to do . Let...
Read more

How to Fact-Check an AI Answer in Under Two Minutes

By
Image
The dangerous thing about a wrong AI answer isn't that it's wrong. It's that it looks exactly like a right one. When a person doesn't know something, you can usually tell. They hedge. They slow down. They say "I think" or "don't quote me on this." AI tools don't do any of that. They deliver a wrong date, a misremembered rule, or a study that was never published in the same calm, tidy, well-organized paragraphs they use for the things they have dead right. There's no tell. The confidence is a constant, and it's the same whether the answer came from something solid or from nothing at all. So the skill that actually matters with these tools isn't prompting . It's checking. And checking doesn't mean redoing the work by hand — if it did, the tool would be pointless. It means knowing which two or three claims in an answer are actually holding the thing up, and spending ninety seconds on those. First, understand w...
Read more