Skip to content
// Start Here

New here? Read these two first.

DIXON.AI documents real-world experiments with AI agents and prompting methods, run against an actual investment portfolio. No predictions, no positions, no returns. Just the methodology and what survives contact with real decisions.

// Read these first
Decision Process

5 questions to ask AI before buying any stock

Five questions to ask AI before buying any stock — for the hour before you commit capital, when the research is done and the decision is about to be made.

Start here if you want the method in practice. Five diagnostic questions to run before any buy decision — the checklist I actually use before committing capital.

Read it →
Prompt Stack

7 AI prompts for covered calls

AI prompts for covered calls that work: seven prompts built around real chain data, covering position fit, IV regime, strike selection, and roll decisions.

Start here if covered calls are part of your income strategy. Seven prompts built around real chain data, from position fit to roll decisions.

Read it →
// The method

One question, four stages

Most AI tools are happy to skip straight to a verdict. The Prompt Stack forces four stages instead — pin down the role, separate fact from assumption, surface the downside, then commit to one practical action. It's a discipline for getting honest output, not impressive-sounding output.

Read the full methodology →


// Working on now

What's open in the lab

Testing how well different AI tools handle earnings analysis — the moment where hype and reality diverge fastest. Plus a proper audit of where the Prompt Stack breaks down, because it does.

Browse all posts →

// The Lab Book

Get the working material.

Five copy-paste prompts for when a stock has moved and you need to decide what to do next. Thesis check, earnings read, conviction check, drawdown discipline, exit planning. Free when you subscribe.

Get the prompts →