Still working out which AI answers I can trust — tested on ten years of my own money.
DIXON.AI is a personal site. Not a product, not a fund, not a newsletter with a VC behind it. One person working out how to get reliable answers from AI — and testing the methods on real financial decisions, mine.
How I got here.
I started about ten years ago, but not with a stock pick. I'd had an operation, was off work, and learned how to extract bookmaker bonuses through matched betting — the kind where you lay off every position for guaranteed profit. I tracked every single bet on a spreadsheet. By the time the bonuses dried up, I'd built a reasonable pot and a working belief that there's almost always an edge somewhere if you look for it.
Peer-to-peer lending came next. Low yield, very boring, very instructive — it taught me how badly capital gets used when it sits idle. From there I started actually investing: early-stage via Seedrs, then index funds, then a few years of S&P 500 ETF as the base. I read the obvious ones — Graham's Intelligent Investor, Bogle's Little Book of Common Sense Investing — and a fair bit beyond. I learned about free cash flow analysis from Joseph Carlson and the Qualtrim software he built, which is where I started looking at companies properly rather than just owning the index.
These days I run a UK ISA on Robinhood, hold US individual stocks and a couple of crypto positions, and sell covered calls on what I own. The options side I learned from Invest With Henry on YouTube and refined into something I trust. I'm not a fund manager. I don't run anyone else's money, and I have no interest in doing so. That's the context for every prompt on this site.
How I think about using AI for investing.
Show the working before the answer.
If an AI output jumps to a verdict before laying out the facts it's drawing on, it isn't doing its job. Every prompt on this site puts the evidence step first — the verdict only comes when the evidence supports one.
In practice: the covered-call prompt puts the trade thesis in writing before asking for the verdict.
Make it argue back.
I don't ask AI to agree with me. The prompts force it to find what would make the case wrong, and name the signal that would prove it.
In practice: the RISK step asks the AI to name what would prove the thesis wrong — not whether the thesis is right.
One thing, properly.
The prompts I trust do one job. The ones that tried to do everything produced impressive-sounding nothing — I deleted them.
In practice: the four-step Prompt Stack replaced six earlier prompts that each tried to do too much.
Write it down.
What I asked, what I got, what I'd do differently. The writing-up is where most of the actual learning happens. The site exists partly to keep me honest.
In practice: this site exists partly because I kept forgetting what had changed between sessions.
The Prompt Stack is also an open repository at github.com/CtrlCursor/prompt-stack — share, adapt, credit.
Where the work lives.
The principles above are claims. The four pages below are where they get tested — closed positions with real outcomes, AI failures by tool and type, AI catches that surprised me, and what's on the desk right now.
When I'm not running experiments.
Mostly outside. Hiking with my girlfriend and the dog. Riding the motorbike. Kitesurfing and efoiling when the weather lets me. Gardening — six years in, still learning, still losing the occasional fight to slugs. Music in the background most of the day. I'm not a serious person, despite the subject matter on the site. The fun is in the learning and the doing.
A site worth reading.
I'd like dixon.ai to become a place where someone who already invests, and is reasonably suspicious of AI tools, can find methodology that holds up. Not stock picks. Not hype. Just the experiments, the failures, and the prompts that have worked.
Specifically: honest comparisons and audits of AI tools and models, on the tasks that cost real money to get wrong — including where a tool simply isn’t worth paying for.
I also believe, more broadly, that everyone capable of putting a bit of money away each month should be doing so. Compounding is real. Looking after your own money is a basic adult skill the school system forgot to teach. If anything on this site helps a reader get better at that — even outside investing, even just applying the methodology to a different kind of decision — that's a good outcome.
The site is its own test case.
The site itself is built and run by an AI agent I direct — roughly a hundred sessions of real work, logged in the open, costs and mistakes included. It’s the same test I put every other tool through, run on the one closest to home. And with nothing to sell you, there’s nothing to soften the verdicts for.
What this site is not.
This is not financial advice. Nothing on this site is a recommendation to buy or sell anything. I'm documenting my own process for my own reasons. If it's useful to you too, even better.
I'm also not claiming AI is reliably useful for investing. My working view is that it's useful in narrow, well-defined situations with careful prompting, and actively misleading in others. Telling the difference is what the experiments are for.
What I'm using right now → · Something to say? Get in touch →