Tabled two 5-year returns from different sources side by side without units — VWRL 11.83% next to VUSA 86.21% — then flagged them…
Injected personal context from earlier chats into a standard fund comparison, unprompted, making the answer non-reproducible — a…
Served the out-of-date 0.22% ongoing charge for VWRL despite running a web search before answering; the current published figure…
I work out how to get reliable answers from AI — and test the methods with real money.
The work is ongoing. One email a week: what worked, what didn’t, and the prompts I’d run again.
No spam. Unsubscribe any time.
// The author
// New here? Start here. 4 parts · ~14 min · no jargon
A short, plain-English path to trusting what AI tells you.
Four short reads. By the end you’ll have a simple check you can run on any answer that matters — a contract, a letter from a doctor, an email you’re not sure about.
Start with part 1 →// From the field · 6 new this week
Field Notes
Is ChatGPT accurate? I asked four AIs one simple money question and checked every number
Is ChatGPT accurate? I asked four AIs one common money question and checked every number against the source. Here's what each got right and made up.
Decision ProcessHow to tell if an AI answer is true in 30 seconds
Two questions — and a prompt you can copy — that catch a confident, wrong AI answer before you act on it. No jargon, no AI knowledge needed.
Decision ProcessMake it show its working
An AI hallucination is a model mixing what it knows with what it's making up, in the same smooth tone. One prompt makes it sort the two into separate lists — so you can see the invented parts.
// Archive
Decision Process The whole method, in four questions Decision Process Where I actually use this Field Notes Gemini audited my website — and reviewed a different business entirely Decision Process The AI prompt I run before every sell decision Prompt Stack AI earnings call red flags: three phrases that flag almost every time Decision Process What every AI stock research comparison gets wrong
// The Method Four prompts that stop AI inventing the answer.
Read →