<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>DIXON.AI</title><description>A personal financial lab journal about AI agents, prompt discipline, and what survives contact with real decisions.</description><link>https://dixon.ai/</link><item><title>I asked AI to find the downside in a position I was already long. It found things I&apos;d missed.</title><link>https://dixon.ai/posts/i-asked-ai-to-find-the-downside/</link><guid isPermaLink="true">https://dixon.ai/posts/i-asked-ai-to-find-the-downside/</guid><description>An adversarial prompt against my own portfolio. The model surfaced three risks I&apos;d glossed over, and one I&apos;d actively been wrong about.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate></item><item><title>I gave the same investment question to four AI tools. The results were instructive.</title><link>https://dixon.ai/posts/i-gave-the-same-investment-question-to-four-ai-tools/</link><guid isPermaLink="true">https://dixon.ai/posts/i-gave-the-same-investment-question-to-four-ai-tools/</guid><description>Not a ranking. A controlled test on a real question, with notes on what each tool actually produced and why most of it was useless.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate></item><item><title>Perplexity Finance: what it&apos;s good for and what it&apos;s not</title><link>https://dixon.ai/posts/perplexity-finance-honest-review/</link><guid isPermaLink="true">https://dixon.ai/posts/perplexity-finance-honest-review/</guid><description>An honest assessment of Perplexity Finance from someone using it on real positions. Where it earns its place, where it actively misleads, and where I&apos;ve stopped using it entirely.</description><pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate></item><item><title>The prompts I actually use when reviewing a position</title><link>https://dixon.ai/posts/the-prompts-i-actually-use-for-portfolio-review/</link><guid isPermaLink="true">https://dixon.ai/posts/the-prompts-i-actually-use-for-portfolio-review/</guid><description>Not a list of clever prompts to copy. A walkthrough of the actual sequence I run, and why the order matters more than the wording.</description><pubDate>Fri, 01 May 2026 00:00:00 GMT</pubDate></item><item><title>Why I now split every serious AI question into stages before I trust the answer</title><link>https://dixon.ai/posts/why-i-split-every-ai-question-into-stages/</link><guid isPermaLink="true">https://dixon.ai/posts/why-i-split-every-ai-question-into-stages/</guid><description>How I use a four-stage prompting method — Role, Filter, Risk, Verdict — to get useful AI analysis instead of confident-sounding noise.</description><pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate></item></channel></rss>